WO2019087971A1 - Medical image processing device and endoscope device - Google Patents

Medical image processing device and endoscope device Download PDF

Info

Publication number
WO2019087971A1
WO2019087971A1 PCT/JP2018/039920 JP2018039920W WO2019087971A1 WO 2019087971 A1 WO2019087971 A1 WO 2019087971A1 JP 2018039920 W JP2018039920 W JP 2018039920W WO 2019087971 A1 WO2019087971 A1 WO 2019087971A1
Authority
WO
WIPO (PCT)
Prior art keywords
discrimination
medical image
illumination light
unit
image
Prior art date
Application number
PCT/JP2018/039920
Other languages
French (fr)
Japanese (ja)
Inventor
加來　俊彦
Original Assignee
富士フイルム株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 富士フイルム株式会社 filed Critical 富士フイルム株式会社
Priority to JP2019550327A priority Critical patent/JP6834019B2/en
Publication of WO2019087971A1 publication Critical patent/WO2019087971A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
    • A61B1/045—Control thereof

Definitions

  • the present invention relates to a medical image processing apparatus using an analysis result of a medical image, and an endoscope apparatus.
  • medical devices those that acquire images (hereinafter referred to as medical images) including a subject image present the acquired medical images to the doctor. Then, the doctor uses the medical image obtained from the medical device as one of the determination materials to make a diagnosis and the like.
  • the discrimination of the condition of the subject or the like using the medical image at the time of diagnosis is based on the skill and experience of the doctor.
  • the endoscope apparatus described in Patent Document 1 is abnormal using a fluorescence image taken using fluorescence or a narrow band light image taken using light having a specific narrow wavelength band (so-called narrow band light). Locate the area where And the position of the area
  • a notable area including one or more parts where abnormality such as a lesion is recognized by analyzing a medical image (lesion part or a part having a possibility of a lesion) Or, it is an area called an abnormal area etc.
  • an abnormal area it is simply referred to as an abnormal area, and the position etc. is presented to support diagnosis and the like.
  • the doctor or the like distinguishes the type and the degree of progress of the lesion or the like in the abnormal area presented by the medical device, but the type and the degree of progression of the lesion or the like still bear a heavy burden. For this reason, in recent years, in order to further reduce the burden on a doctor or the like, it is required to provide detailed information as a material for discrimination about the type and the degree of progression of a lesion or the like.
  • An object of the present invention is to provide a medical image processing apparatus and an endoscope apparatus capable of presenting more detailed and accurate information on a lesion or the like than ever.
  • a medical image processing apparatus uses a first medical image captured using a first illumination light having a specific spectrum among medical images, and a medical image acquisition unit for acquiring a medical image including a subject image.
  • the first discrimination processing unit that performs a first discrimination process for detecting one or more types of first abnormal regions, and the second illumination light having a spectrum different from that of the first illumination light in the medical image
  • a second discrimination processing unit for performing a second discrimination process of identifying the type of abnormality included in each of the first abnormal areas using the second medical image; first illumination light and second illumination light of the medical image
  • a third discrimination processing unit that performs a third discrimination process of identifying the degree of progression of the abnormality included in the first abnormal area using the third medical image captured using the third illumination light having different spectra.
  • the second discrimination processing unit identifies the type of abnormality included in the first abnormal area by performing the second discrimination processing on the second abnormal area included in the second medical image corresponding to the first abnormal area. Is preferred.
  • the third discrimination processing unit performs the third discrimination processing on the third abnormal region included in the third medical image corresponding to at least one of the first abnormal region or the second abnormal region, whereby the first abnormal region is It is preferable to specify the degree of progression of the abnormality included.
  • the third discrimination processing unit preferably selects the third medical image using the result of the second discrimination processing.
  • determination process part selects the 3rd medical image acquired by the spectrum of 3rd illumination light matched with the result of a 2nd discrimination process.
  • the medical image acquisition unit acquires a medical image for observation other than the first medical image, the second medical image, and the third medical image, and displays the medical image for observation on the display unit.
  • the first discrimination processing unit preferably performs the first discrimination processing
  • the second discrimination processing unit performs the second discrimination processing
  • the third discrimination processing unit preferably performs the third discrimination processing.
  • the medical image acquisition unit sets any one of the first medical image, the second medical image, and the third medical image as a medical image for observation, and while displaying the medical image for observation on the display unit
  • the first discrimination processing unit preferably performs the first discrimination processing
  • the second discrimination processing unit performs the second discrimination processing
  • the third discrimination processing unit preferably performs the third discrimination processing.
  • the setting unit changes settings of each spectrum or combination of the first illumination light, the second illumination light, or the third illumination light.
  • the medical chart acquisition unit includes a medical chart acquisition unit for acquiring a medical chart, and the setting unit sets the information using information included in the medical chart.
  • the setting unit preferably includes, in the type of the abnormality identified in the second discrimination process, a specific lesion determined by the information included in the medical record.
  • a discrimination result correction unit that corrects the result of the second discrimination process or the result of the third discrimination process.
  • reports the result of a 2nd discrimination process, or the result of a 3rd discrimination process as a result of a 1st discrimination process.
  • the endoscope apparatus of the present invention is photographed using an endoscope image acquisition unit for acquiring an endoscope image including a subject image, and a first illumination light having a specific spectrum of the endoscope image.
  • a first discrimination processing unit that performs a first discrimination process of detecting one or more types of first abnormal areas using the first endoscopic image, and a spectrum of the first illumination light in the endoscopic image have different spectra.
  • a second discrimination processing unit that performs a second discrimination process of identifying the type of abnormality included in each of the first abnormal areas using a second endoscopic image captured using a second illumination light; and an endoscope A third medical image captured using a third illumination light having a spectrum different from that of the first illumination light and the second illumination light in the image is used to specify the progression degree of the anomaly included in the first anomaly region.
  • a discrimination processing unit that performs a second discrimination process of identifying the type of abnormality included in each of the first abnormal areas using a second endoscopic image captured using a second illumination light; and an endoscope A third medical image captured using a third illumination light having a spectrum different from that of the first illumination light and the second illumination light in the image is used to specify the progression degree of the anomaly included in the first anomaly region.
  • determination process part selects the spectrum of the illumination light used when acquiring a 3rd medical image using the result of a 2nd discrimination process.
  • the medical image processing apparatus and the endoscope apparatus of the present invention can provide more detailed and accurate information on lesions and the like than ever before.
  • FIG. 1 It is a block diagram of a medical image processing device. It is a block diagram of an endoscope apparatus. It is a graph which shows the spectrum of the illumination light which a light source device can emit. It is a graph which shows the spectrum of the illumination light for observation. It is a graph which shows the spectrum of the illumination light for discrimination of pattern 1.
  • FIG. It is a graph which shows the spectrum of the illumination light for discrimination of pattern 2.
  • FIG. It is a graph which shows the spectrum of the illumination light for discrimination of pattern 3.
  • FIG. It is a graph which shows the spectrum of the illumination light for discrimination of pattern 4.
  • FIG. It is a graph which shows the spectrum of the illumination light for discrimination of pattern 5.
  • FIG. 6 shows the spectrum of the illumination light for discrimination of pattern 6.
  • the medical image processing apparatus 10 includes a medical image acquisition unit 11, a medical image analysis processing unit 12, a display unit 13, a display control unit 15, an input reception unit 16, an overall control unit 17, and a storage unit. It has eighteen.
  • the medical image acquisition unit 11 is a medical image including a subject image directly from the endoscope apparatus 21 or the like which is a medical apparatus, or via a management system such as a PACS (Picture Archiving and Communication System) 22 or other information system.
  • the medical image is a still image or a moving image (so-called test moving image).
  • the medical image acquiring unit 11 can acquire a frame image constituting the moving image as a still image after the examination.
  • displaying the medical image includes reproducing the moving image one or more times in addition to displaying a still image of one representative frame constituting the moving image.
  • the medical device such as the endoscope device 21 or the like receives the imaging instruction of the doctor in addition to the image photographed by the doctor using the medical device such as the endoscope device 21 or the like. Includes images taken automatically regardless of
  • the medical image acquisition unit 11 can acquire a plurality of medical images, it can selectively acquire one or more medical images among these medical images. Further, the medical image acquisition unit 11 can acquire a plurality of medical images acquired in a plurality of different examinations. For example, one or both of a medical image acquired by an examination performed in the past and a medical image acquired by the latest examination can be acquired. That is, the medical image acquisition unit 11 can arbitrarily acquire a medical image.
  • the medical image processing apparatus 10 is connected to the endoscope apparatus 21 and acquires a medical image from the endoscope apparatus 21. That is, in the present embodiment, the medical image is an endoscopic image.
  • the medical image acquisition unit 11 acquires a plurality of endoscopic images (medical images) at least having mutually different imaging conditions.
  • the medical image acquisition unit 11 displays an endoscopic image for observation displayed on the display unit 13 (hereinafter referred to as an endoscopic image for observation 101 (medical image for observation); see FIG. 22).
  • An endoscopic image hereinafter referred to as the first endoscopic image 61; see FIG.
  • the observation endoscopic image 101, the first endoscopic image 61, the second endoscopic image 63, and the third endoscopic image 66 have different imaging conditions from one another in order to match the purpose of use. .
  • the imaging condition is a condition relating to imaging of a medical image, and is, for example, the spectrum of illumination light or the presence or absence or intensity of image processing at the time of generating a medical image.
  • the spectrum of illumination light is an intensity distribution for each wavelength, and includes the concepts of wavelength band and central wavelength.
  • the image processing at the time of generating a medical image is, for example, processing relating to adjustment of a color or the like that emphasizes a specific tissue or a lesion.
  • the endoscope apparatus 21 to which the medical image processing apparatus 10 is connected shoots a subject by irradiating at least one of light of a white wavelength band or light of a specific wavelength band.
  • the endoscope 31 includes an image sensor 41 for imaging a subject using illumination light in which the subject is reflected or scattered, or fluorescence from which the subject or a drug or the like administered to the subject emits light.
  • the image sensor 41 is, for example, a complementary metal-oxide-semiconductor (CMOS) color sensor (a sensor having a color filter).
  • CMOS complementary metal-oxide-semiconductor
  • the light source device 32 includes a light source unit 42 and a light source control unit 47.
  • the light source unit 42 emits a plurality of types of illumination light having different spectra.
  • the light source unit 42 includes, for example, a light emitting device such as a light emitting diode (LED), a laser diode (LD), or a xenon lamp.
  • the light source unit 42 is provided with a prism, a mirror, an optical fiber, an optical filter for adjusting a wavelength band, a light amount, and the like as needed.
  • the light source unit 42 includes a V-LED 43 that emits violet light with a center wavelength of about 405 nm, a B-LED 44 that emits blue light with a center wavelength of about 450 nm, and a green light with a center wavelength of about 540 nm. It comprises a G-LED 45 emitting light and an R-LED 46 with a center wavelength of about 630 nm.
  • the light source control unit 47 controls the light emission source included in the light source unit 42, and generates illumination light used by the endoscope 31 for photographing an object. Further, when the light source unit 42 includes a plurality of light emitting devices, the light source control unit 47 can control the light emission timing and the light emission amount of each light emitting device. Therefore, the light source device 32 can supply the endoscope 31 with a plurality of types of illumination light having different spectra, at any timing and at any intensity. That is, in the present embodiment, the light source device 32 controls two or more of purple light, blue light, green light, red light or light of each color other than white light under the control of the light source control unit 47. Light mixed at an arbitrary intensity ratio can be emitted as illumination light at an arbitrary timing and an arbitrary intensity.
  • the light source device 32 emits violet light (represented by a symbol “V”. The same applies hereinafter) emitted by the V-LED 43 and blue light emitted by the B-LED 44.
  • the green light emitted by the G-LED 45 (represented by the code “G”. The same applies hereinafter) and the red light emitted by the R-LED 46 (indicated by the code “R”) And the same.) And can emit light.
  • the light source control unit 47 arbitrarily controls the light amount of each color light of purple light V, blue light B, green light G, and red light R included in the illumination light according to the purpose of photographing.
  • the light source device 32 when obtaining the observation endoscope image 101, the light source device 32 emits illumination light (hereinafter, referred to as observation illumination light) having the observation spectrum shown in FIG.
  • the observation illumination light is so-called white light.
  • the light source device 32 has, for example, illumination having a spectrum shown in FIG. Light (hereinafter referred to as discrimination illumination light of pattern 1), illumination light having a spectrum shown in FIG. 6 (hereinafter referred to as discrimination illumination light of pattern 2), illumination light having a spectrum shown in FIG. 7 (hereinafter pattern 3) Illumination light having a spectrum shown in FIG.
  • discrimination illumination light for pattern 4 illumination light having a spectrum shown in FIG. 9 (hereinafter referred to as discrimination illumination light for pattern 5) 10), illumination light having the spectrum shown in FIG. 10 (hereinafter referred to as discrimination illumination light for pattern 6), illumination light having the spectrum shown in FIG. 11 (hereinafter referred to as discrimination illumination light for pattern 7), Illumination light having to the spectral or the illumination light having a spectrum shown in FIG. 13 (hereinafter, referred to as differential illumination light pattern 9) emits light switched appropriately.
  • the identification illumination light for pattern 1 (see FIG. 5) is used when acquiring the first endoscopic image 61.
  • the identification illumination light for pattern 2 (see FIG. 6) is used when acquiring the second endoscopic image 63.
  • the illumination light for discrimination of pattern 6 (see FIG. 10), the illumination light for discrimination of pattern 3 (see FIG. 7), and the illumination light for discrimination of pattern 4 (see FIG. 4) form the third endoscopic image 66 Used when acquiring.
  • the discrimination illumination light of pattern 6 is used when acquiring the third endoscopic image 66 for discriminating the degree of progression of the polyp
  • the differentiation illumination light of pattern 3 is ulcerative It is used when acquiring the 3rd endoscopic image 66 for discriminating the degree of progression of colitis
  • the illumination light for discrimination of pattern 4 is the 3rd endoscope for differentiating the degree of progression of Crohn's disease It is used when acquiring the image 66.
  • the light source device 32 can emit light having a specific narrow wavelength band (so-called narrow band light) as illumination light according to the characteristics of the light emitting device or the use of an optical filter. For example, it is possible to emit light in a wavelength band shorter than the green wavelength band, in particular, light in the blue band or purple band in the visible range.
  • narrow band light a specific narrow wavelength band
  • the processor device 33 acquires an endoscopic image from the image sensor 41, or generates an endoscopic image by performing image processing on the endoscopic image acquired from the image sensor 41.
  • the image sensor 41 and the endoscope image generation unit 48 constitute an “endoscope image acquisition unit” in the endoscope apparatus 21.
  • the endoscopic image acquisition unit acquires an endoscopic image including an object image by photographing the object using the illumination light.
  • the medical image processing apparatus 10 is connected to the processor 33. Then, the medical image acquisition unit 11 acquires an endoscope image directly from the endoscope image generation unit 48 of the endoscope apparatus 21.
  • the medical image analysis processing unit 12 performs analysis processing using an endoscopic image which is a medical image acquired by the medical image acquisition unit 11. Specifically, as shown in FIG. 14, it includes a first discrimination processing unit 51, a second discrimination processing unit 52, a third discrimination processing unit 53, and a setting unit 56.
  • the first discrimination processing unit 51 discriminates the presence or absence of the abnormal area 102 using the medical image. Specifically, of the medical images acquired by the medical image acquisition unit 11, the first discrimination processing unit 51 uses one or more of the first medical images captured using the first illumination light having a specific spectrum. A first discrimination process of detecting a plurality of types of abnormal areas 102 is performed.
  • “first illumination light having a specific spectrum” is illumination light for discrimination of pattern 1 and, as shown in FIG. 15, the first medical image is the first endoscopic image 61. is there.
  • the abnormal area 102 in the first endoscopic image 61 is referred to as a “first abnormal area”.
  • the first discrimination processing unit 51 calculates one or a plurality of predetermined feature amounts using the first endoscopic image 61, and detects the abnormal area 102 using the calculated feature amounts.
  • the predetermined feature amount is, for example, color or brightness, shape of a specific tissue or structure such as a blood vessel, length, thickness, depth from a mucosal surface, density, size, distribution, etc., number of branches, etc. , Complexity, disorder of regularity, or other characteristic quantities.
  • the first discrimination processing unit 51 can perform the first discrimination processing by, for example, texture analysis or pattern matching using a regular shape, instead of using the feature amount.
  • a target detected by the first discrimination processing unit 51 as the abnormal area 102 is a feature of a color or shape different from one or more lesions, surrounding tissues, etc.
  • Area, drug-applied area, or treatment is an area including the target of the area etc.).
  • the lesion or the like is, for example, inflammation associated with an inflammatory disease such as ulcerative colitis, Crohn's disease, or a polyp (raised lesion) or the like.
  • polyps are hyperplastic polyp (HP), sessile serrated adenoma / polyp (SSA), adenoma, cancer, etc.
  • HP hyperplastic polyp
  • SSA sessile serrated adenoma / polyp
  • adenoma cancer
  • the area having characteristics of color or shape different from the surrounding tissue or the like is, for example, the subject's redness, atrophy, diverticulum, or a treatment scar.
  • the first discrimination processing unit 51 detects the abnormal area 102 for a part or all of the medical image. That is, the first discrimination processing unit 51 performs the first discrimination processing on a pixel-by-pixel basis, in a case where the endoscope image is divided into small regions, for each small region, or with respect to the entire endoscope image, It can be carried out. In the present embodiment, the first discrimination processing unit 51 determines, for each small area including a predetermined number of pixels, whether the area is the abnormal area 102 or not. Therefore, the first discrimination processing unit 51 can detect the abnormal area 102 at one or more places of the medical image. The first discrimination processing unit 51 can include, in the result of the first discrimination processing, “probability” indicating the certainty of the processing result.
  • the second discrimination processing unit 52 discriminates the type of abnormality included in the first abnormal area (the abnormal area 102 in FIG. 15). Specifically, in the medical image acquired by the medical image acquisition unit 11, the second discrimination processing unit 52 captures a second medical image captured using a second illumination light having a spectrum different from that of the first illumination light. A second discrimination process is performed to identify the type of abnormality included in each first abnormality area.
  • the “second illumination light having a spectrum different from that of the first illumination light” is the illumination light for discrimination of pattern 2 and, as shown in FIG. It is an endoscopic image 63.
  • the second discrimination processing unit 52 performs the second discrimination processing on at least the “second abnormal area included in the second medical image” corresponding to the first abnormal area, whereby the abnormality included in the first abnormal area is Identify the type.
  • the second abnormal area is the abnormal area 102 in the second endoscopic image 63 (second medical image).
  • the second abnormal area (abnormal area 102 in FIG. 16) corresponds to the first abnormal area in the position and the like in the subject.
  • the second discrimination processing unit 52 does not specify the position or the like of the second abnormal area, and the second endoscope
  • the second discrimination process can be performed on the entire image 63 to identify the type of abnormality included in the first abnormal area.
  • the second discrimination processing unit 52 includes one or more type discrimination units according to the number of “types of abnormality” to be discriminated.
  • the type identification unit identifies whether the abnormality included in the abnormal area 102 is a specific lesion.
  • the second discrimination processing unit 52 includes a first type discrimination unit 71, a second type discrimination unit 72, a third type discrimination unit 73, and other type discrimination units ( Not shown).
  • the first type discrimination unit 71 is an abnormality included in the abnormal area 102 detected in the first identification process (in the case where a plurality of abnormal areas 102 are detected, the abnormal area 102 is a specific abnormal area 102 among them. The same applies hereinafter).
  • the second type identification unit 72 identifies whether the abnormality included in the abnormal area 102 detected in the first identification process is “ulcerative colitis”.
  • the third type discrimination unit 73 discriminates whether or not the abnormality included in the abnormal area 102 detected in the first discrimination process is "Crohn's disease”. Similarly, the other type identification unit identifies whether the abnormality included in the abnormal area 102 is a specific lesion.
  • the result of the second discrimination process includes information ("polyp”, “ulcerative colitis”, “Crohn's disease”, etc.) indicating at least the type of abnormality included in the abnormal area 102.
  • the result of the second discrimination process does not necessarily identify the type of abnormality definitely as one, and says “40% probability that it is ulcerative colitis and 40% probability that it is Crohn's disease”
  • it is the information which can narrow down the kind of plausible abnormality together with the probability (probability) showing the certainty of the discrimination result in each kind discrimination part. Therefore, “specifying the type of abnormality” in the second discrimination process means obtaining information that can narrow down the type of abnormality.
  • the third discrimination processing unit 53 discriminates the degree of progression of the abnormality included in the first abnormal area (the abnormal area 102 in FIG. 15). Specifically, in the medical image acquired by the medical image acquisition unit 11, the third discrimination processing unit 53 is photographed using the third illumination light having a spectrum different from that of the first illumination light and the second illumination light. A third discrimination process is performed to specify the degree of progression of the abnormality included in the abnormal area 102 using the third medical image.
  • the “third illumination light having a different spectrum from the first illumination light and the second illumination light” is any of the discrimination illumination light of the patterns 3 to 9, and as shown in FIG.
  • the third medical image is the third endoscopic image 66.
  • the third discrimination processing unit 53 performs the third discrimination processing on the “third abnormal area included in the third medical image” corresponding to at least one of the first abnormal area or the second abnormal area. Identify the degree of progression of the anomaly included in the first anomaly region.
  • the third abnormal area is the abnormal area 102 in the third endoscopic image 66 (third medical image).
  • the third abnormal area (abnormal area 102 in FIG. 18) corresponds to the first abnormal area or the second abnormal area in the position and the like in the subject.
  • the third discrimination processing unit 53 may, for example, determine the position of the third abnormal area, for example, without specifying the position of the third abnormal area.
  • the third discrimination process can be performed on the entire image 66 to identify the type of abnormality included in the first abnormal area.
  • the third discrimination processing unit 53 includes one or more progress degree discrimination units in accordance with the number of “types of abnormality” to be discriminated.
  • the progress discrimination unit discriminates the progress of a specific type of abnormality.
  • the third discrimination processing unit 53 includes a first progression discrimination unit 81, a second progression discrimination unit 82, a third progression discrimination unit 83, and other progressions.
  • a degree discrimination unit (not shown) is provided.
  • the first progression discrimination unit 81 discriminates the progression of the polyp.
  • the second progression discrimination unit 82 discriminates the progression of ulcerative colitis.
  • the third progression discrimination unit 83 discriminates the progression degree of Crohn's disease. The same applies to the other progress discrimination units.
  • the result of the third discrimination process is the degree of progression of a lesion or the like.
  • the medical image is an endoscopic image
  • the degree of progression is discriminated according to a so-called endoscopic findings classification.
  • Endoscopic classification when targeting polyps (including cancer) is, for example, NICE (The Narrow-band imaging International Colorectal Endoscopic) classification, or JNET (The Japan NBI (Narrow Band Imaging) Expert Team) classification. There are classification etc.
  • classification is made into “NICE Type 1”, “NICE Type 2”, or “NICE Type 3” according to the NICE classification.
  • NICE Type 1 represents hyperplastic lesion
  • NICE Type 2 represents adenoma (adenoma) to intramucosal cancer (so-called M cancer)
  • NICE Type 3 represents submucosal invasion cancer (so-called SM cancer) .
  • the endoscopic findings classification of ulcerative colitis includes, for example, Mayo classification, Matts classification, UCEIS (Ulcerative Colitis Endoscopic. Index of Severity) classification, and the like.
  • the degree of progression of ulcerative colitis is classified according to the Mayo classification.
  • the Mayo classification has four grades of Mayo 0 (grade 0), Mayo 1 (grade 1), Mayo 2 (grade 2), and Mayo 3 (grade 3).
  • Mayo0 is a grade that represents normal or inactive (including remission).
  • Mayo 1 is a grade that indicates mildness, and is generally in a state in which redness, blood vessel image obscurity, or mild bleeding tendency is observed.
  • Mayo 2 is a grade that represents moderate disease, and in general, conditions such as marked redness, disappearance of angiogram, hemorrhage, adherence of purulent secretions, mucous membrane prostheses, wrinkles, or partial ulcers etc. It is. Mayo 3 is a grade representing severe (active stage), and in general, it is a state in which obvious spontaneous bleeding, edema, ulcer (including extensive ulcer) and the like are recognized. In the third differential treatment, dysplasia associated with ulcerative colitis is differentiated.
  • the endoscopic findings classification of Crohn's disease includes, for example, SESCD (Simple Endoscopic Score for Crohn's Disease).
  • SESCD Simple Endoscopic Score for Crohn's Disease
  • the degree of progression of Crohn's disease is classified into "SESCD 0", "SESCD 1", “SESCD 2", or "SESCD 3" according to SESCD.
  • the degree of progression for each type of lesion is differentiated, and the degree of progression for one or more lesions is Output as the result of the third discrimination process.
  • the result of the second discrimination process is "probability 40% for ulcerative colitis and 40% probability for Crohn's disease”
  • the degree of progression of ulcerative colitis in the third discrimination process Differentiate the degree of progression of Crohn's disease.
  • the degree of progression of each lesion narrowed down in the second differentiation process is "20% of the probability that Mayo 1 is ulcerative colitis” and "95% of the probability that SESCD 1 is Crohn's disease” Among these results, the result relating to the latter Crohn's disease is output as the result of the third discrimination process.
  • the third discrimination processing unit 53 selects one or more third medical images using the result of the second discrimination processing. Further, the third discrimination processing unit 53 selects the third medical image acquired in the spectrum of the third illumination light associated with the result of the second discrimination processing. For example, when the result of the second discrimination process includes “polyp”, an endoscopic image captured using the discrimination illumination light of pattern 6 is selected and acquired as the third endoscopic image 66.
  • the medical image acquisition part 11 can acquire the medical image which the 2nd discrimination process part 52 and the 3rd discrimination process part 53 may request
  • the first discrimination process, the second discrimination process, and the third discrimination process are performed in the background while displaying the medical image for observation on the display unit 13. That is, while the medical image for observation (in the present embodiment, the endoscopic image for observation 101) is displayed on the display unit 13, the first discrimination processing unit 51 performs the first discrimination processing, and the second discrimination processing The part 52 performs a second discrimination process, and the third discrimination processing unit 53 performs a third discrimination process.
  • the medical image acquisition unit 11 acquires a medical image for observation other than the first medical image, the second medical image, and the third medical image, but the medical image acquisition unit 11 When one of the first medical image, the second medical image, and the third medical image is set as the medical image for observation (the first medical image, the second medical image, or the third medical image for medical observation And also when it is used.
  • the display control unit 15 can appropriately update the observation endoscope image 101 displayed on the display unit 13 while performing the first discrimination process, the second discrimination process, or the third discrimination process.
  • the setting unit 56 can store and change the setting of the type of abnormality (discrimination target) identified in the second discrimination processing or the classification (discrimination content) of the progress degree identified in the third discrimination processing. .
  • the setting unit 56 causes the display unit 13 to display a setting change menu window shown in FIG.
  • a doctor or the like puts a check (“RE”) in the check box 91 using a mouse or the like, the corresponding discrimination target and the discrimination content can be validated.
  • “polyp” and “ulcerative colitis” are activated as discrimination targets
  • “NICE Type 1”, “NICE Type 2”, and “NICE Type 3” are activated for polyps, and ulcers are detected.
  • the second discrimination processing unit 52 discriminates whether the abnormality included in the abnormal area 102 is a polyp and whether it is ulcerative colitis. Further, when the abnormality included in the abnormal area 102 is a polyp, the third discrimination processing unit 53 discriminates the progress degree of the abnormality into “NICE Type 1”, “NICE Type 2”, or “NICE Type 3”. Similarly, when the abnormality included in the abnormal area 102 is ulcerative colitis, the third discrimination processing unit 53 discriminates the progress degree to “Mayo 0”, “Mayo 1”, or “Mayo 2”.
  • the setting unit 56 can set or change each spectrum or combination of the first illumination light, the second illumination light, or the third illumination light. Setting the type of abnormality (differentiation target) to be identified in the second discrimination process, or the classification (discrimination content) of the progress degree to be identified in the third discrimination process, and the first illumination light, the second illumination light, or Setting each spectrum or combination of the third illumination light exerts substantially the same setting effect with respect to the first discrimination process, the second discrimination process, and the third discrimination process.
  • the display unit 13 is a display that displays the medical image acquired by the medical image acquisition unit 11.
  • the display unit 13 displays at least a medical image for observation.
  • the display unit 13 can display one or more of the result of the first discrimination process, the result of the second discrimination process, and the result of the third discrimination process.
  • a monitor or display included in a device or the like connected to the medical image processing apparatus 10 can be shared and used as the display unit 13 of the medical image processing apparatus 10.
  • the display control unit 15 controls the display mode of the medical image for observation or the like on the display unit 13.
  • the abnormal area 102 (first abnormal area) detected by the first discrimination processing unit 51 is superimposed on the observation endoscope image 101 and displayed.
  • the display control unit 15 displays on the display unit 13 the type of abnormality included in the abnormal area 102, characters (character string or message) indicating the progress of abnormality included in the abnormal area 102, and the like.
  • the display control unit 15 may use the sound (including sound), light (partial blinking of the observation endoscope image 101, etc.), display of coordinates, or any other appropriate method, such as an abnormal area.
  • the position of 102, the type of abnormality included in the abnormal area 102, and the degree of progression of abnormality included in the abnormal area 102 can be indicated.
  • the input reception unit 16 receives input from a mouse, a keyboard, and other operation devices connected to the medical image processing apparatus 10. The operation of each part of the medical image processing apparatus 10 can be controlled using these operation devices.
  • the integrated control unit 17 integrally controls the operation of each unit of the medical image processing apparatus 10.
  • the overall control unit 17 controls each unit of the medical image processing apparatus 10 according to the operation input.
  • the storage unit 18 is a storage device (not shown) such as a memory included in the medical image processing apparatus 10 or a medical device such as the endoscope apparatus 21 or a storage device (not shown) included in the PACS 22 as needed.
  • the position of the abnormal area 102, the type of abnormality included in the abnormal area 102, the degree of progress of abnormality included in the abnormal area 102, and the like are stored.
  • the medical image acquisition unit 11 appropriately acquires the observation endoscopic image 101 which is a medical image for observation (step S110), and the display control unit 15 acquires the endoscopic image 101 for observation. Are appropriately displayed on the display unit 13 (step S111).
  • the medical image acquisition unit 11 acquires the first endoscopic image 61, which is a medical image for the first discrimination process (step In step S112, the first discrimination processing unit 51 executes the first discrimination process of discriminating the presence or absence of the abnormal area 102 using the first endoscopic image 61 (step S113).
  • the medical image acquisition unit 11 acquires the second endoscopic image 63 which is a medical image for the second discrimination process (step S114), and the second discrimination processing unit A second discrimination process is performed to discriminate the type of abnormality included in the abnormal area 102 using the second endoscopic image 63 (step S115). Thereafter, the medical image acquisition unit 11 acquires the third endoscopic image 66 which is a medical image for the third discrimination process (step S116), and the third discrimination processing unit 53 obtains the third endoscopic image 66. A third discrimination process of discriminating the degree of progression of the abnormality included in the abnormal area 102 is executed (step S117).
  • the display control unit 15 displays these results on the display unit 13 (step S118). For example, as shown in FIG. 22, the display control unit 15 displays the position of the abnormal area 102 by indicating the outline of the abnormal area 102 in the observation endoscope image 101 or the like. Further, the display control unit 15 displays that the abnormality included in the abnormal area 102 is, for example, “ulcerative colitis” in the specific display column 103 for indicating the result of the second discrimination processing, and the third discrimination In the specific display field 104 for indicating the result of the process, it is displayed that the progress degree is, for example, "Mayo 1".
  • the medical image processing apparatus 10 detects the abnormal area 102 and discriminates the type and the degree of progress of the abnormality included in the detected abnormal area 102
  • the medical image processing apparatus 10 captures an image with illumination light suitable for each of the discrimination.
  • I use medical images.
  • the first discrimination process the first endoscopic image 61 suitable for discrimination of the presence or absence of the abnormal area 102 is used, and in the second discrimination process, for discrimination of the type of abnormality included in the abnormal area 102
  • a suitable second endoscopic image 63 is used, and a third endoscopic image 66 suitable for differentiation of the degree of progression is used in the third discrimination process.
  • the medical image processing apparatus 10 can further provide the type of abnormality included in the abnormal area 102 and accurate information on the progression of the abnormality included in the abnormal area 102. That is, the medical image processing apparatus 10 can provide more detailed information on lesions and the like than in the past, and can support diagnosis and the like more effectively.
  • the first discrimination processing unit 51, the second discrimination processing unit 52, and the third discrimination processing unit 53 in the first embodiment use a so-called AI (Artificial Intelligence) program learned by machine learning or deep learning. Can be configured.
  • AI Artificial Intelligence
  • the medical image acquiring unit 11 In the second discrimination process, when the types of abnormalities are narrowed down to a plurality of types, the medical image acquiring unit 11 respectively obtains the third endoscopic image 66 suitable for the third discrimination process for each type of abnormality.
  • the third discrimination processing unit 53 acquires and discriminates the degree of progress of each type of abnormality. For example, when it is specified that “probability 40% is ulcerative colitis and probability 40% is Crohn's disease” in the second discrimination processing, medical image acquisition unit 11 discriminates the progression degree of ulcerative colitis.
  • the third endoscopic image 66 required and the third endoscopic image 66 necessary for discrimination of the degree of progression of Crohn's disease are obtained, and the third discrimination processing unit 53 calculates each third endoscopic image 66 The degree of progression of ulcerative colitis (the degree of progression when the type of abnormality is ulcerative colitis) and the degree of progression when Crohn's disease is the type of abnormality ) And.
  • the display control unit 15 displays at least the discrimination result with the highest accuracy.
  • the display control unit 15 displays at least the type “Aberrant type“ Crohn's disease ”and the progression“ SESCE1 ”.
  • the medical image analysis processing unit 12 includes the chart acquisition unit 121 in addition to the first discrimination processing unit 51, the second discrimination processing unit 52, the third discrimination processing unit 53, and the setting unit 56. You may have.
  • the chart acquisition unit 121 acquires the chart of the patient to be examined from the medical device such as the endoscope apparatus 21 or the PACS 22 or the like.
  • a medical record is information that records the progress of medical treatment or examination about a patient, and includes, for example, the patient's name, sex and age, disease name, major symptoms, contents of prescription or treatment, or records of medical history etc. .
  • the setting unit 56 specifies the type of abnormality (differentiation target) specified in the second discrimination process or the third discrimination process using information included in the medical chart. It is possible to set classification (differentiated content) of the degree of progress.
  • the setting unit 56 can include, in the type of abnormality identified in the second discrimination process, a specific lesion determined by the information included in the medical record. Specifically, if there is a history of ulcerative colitis, even if ulcerative colitis is not the main lesion that is the main target of the examination, setting unit 56 differentiates ulcerative colitis as a secondary lesion. It is set as an object.
  • the medical image analysis processing unit 12 has a discrimination result correction unit 131. May be provided.
  • the discrimination result correction unit 131 corrects the result of the first discrimination process, the result of the second discrimination process, or the result of the third discrimination process based on the operation input using the input reception unit 16 such as a doctor. By providing the discrimination result correction unit 131, it is possible to correct erroneous discrimination in the first discrimination process, the second discrimination process, or the third discrimination process.
  • a doctor or the like can arbitrarily correct the position, size, range, number, etc., of the abnormal area 102 detected in the first discrimination process. Further, the type of the abnormality identified in the second discrimination process can be arbitrarily selected again, or the doctor or the like can arbitrarily discriminate the degree of progress specified in the third discrimination process.
  • the discrimination result correction unit 131 corrects the result of the first discrimination process
  • the second discrimination processing unit 52 executes the second discrimination process reflecting the result of the first discrimination process after correction
  • the third discrimination The processing unit 53 executes the third discrimination process by reflecting the result of the second discrimination process that reflects the result of the first discrimination process after correction.
  • the discrimination result correction unit 131 corrects the result of the first discrimination process
  • the second discrimination processing unit 52 can redo the second discrimination processing reflecting the result of the first discrimination processing after the correction based on the instruction by the etc.
  • the third discrimination processing unit 53 performs the correction after the modification. It is possible to redo the third discrimination process by reflecting the result of the second discrimination process reflecting the result of the first discrimination process.
  • the third discrimination processing unit 53 executes the third discrimination process, reflecting the result of the second discrimination process after the correction.
  • the discrimination result correction unit 131 corrects the result of the second discrimination process, if the third discrimination process is already completed, the third discrimination is automatically performed or based on an instruction by a doctor etc.
  • the processing unit 53 can redo the third discrimination process by reflecting the result of the second discrimination process after the correction.
  • the medical image analysis processing unit 12 has a discrimination result notification unit 141. May be provided.
  • the discrimination result notifying unit 141 reports the result of the first discrimination process, the result of the second discrimination process, or the result of the third discrimination process at an arbitrary timing.
  • the discrimination result notifying unit 141 reports the result of the first discrimination process in real time after the completion of the first discrimination process, for example, the result of the second discrimination process is real time after the completion of the second discrimination process Alert to
  • the discrimination result notifying unit 141 can display the respective discrimination results as in the first embodiment using the display control unit 15 and the display unit 13, and can also use sound (including sound), light (observation endoscope image 101).
  • the result of the first discrimination process, the result of the second discrimination process, and the result of the third discrimination process can be reported by any other method such as the partial blinking of the character of the symbol, the display of coordinates, and the like.
  • the medical image processing apparatus 10 and the endoscope apparatus 21 are separate apparatuses, but the endoscope apparatus 21 can include the medical image processing apparatus 10.
  • each unit 520 constituting the medical image processing apparatus 10 is provided in the processor apparatus 33.
  • the display unit 13 can share the monitor 34 of the endoscope apparatus 21.
  • the medical image acquisition part 11 is corresponded to the "endoscope image acquisition part" which the image sensor 41 and the endoscope image generation part 48 form. For this reason, it is sufficient to provide the processor 33 with components other than the medical image acquisition unit 11 and the display unit 13.
  • the configuration of the other components is the same as that of the first embodiment.
  • a new endoscope apparatus can be configured as a whole of the medical image processing apparatus 10 of each of the above-described embodiments and the other modifications and the endoscope apparatus 21 of FIG. 2.
  • An endoscope apparatus 510 including the medical image processing apparatus 10 is basically an apparatus for observing a subject in real time. For this reason, the endoscope apparatus 510 can obtain an endoscope image which is a medical image, a first discrimination process, a second discrimination process, a third discrimination process, and a display process of these results, etc. It can be performed in real time while capturing an image, or at any timing caused by the operation of various operation units and the like.
  • the endoscope apparatus 510 captures an object using the observation illumination light, appropriately acquires the observation endoscope image 101 (step S210), and the display control unit 15 performs observation
  • the endoscopic image 101 for endoscope is suitably displayed on the monitor 34 (step S211).
  • the integrated control unit 17 sets the observation endoscope image 101 during the series of imaging of the observation endoscope image 101.
  • the imaging for the first discrimination process is intermittently interrupted at a predetermined timing that does not affect continuous display. That is, the endoscope apparatus 510 appropriately switches the illumination light to the discrimination illumination light of pattern 1 in accordance with the timing of imaging of the image sensor 41 (step S212), and the interval between the frames for imaging the endoscopic image 101 for observation Then, a frame for photographing a subject using the discrimination illumination light of pattern 1 is inserted as appropriate. Thereby, the endoscope apparatus 510 acquires the first endoscopic image 61 for the first discrimination process (step S213), and the first discrimination processing unit 51 uses the first endoscopic image 61. The first discrimination process is executed (step S214).
  • the general control unit 17 determines that the continuous display of the observation endoscope image 101 is not interrupted during the imaging of the series of observation endoscope images 101.
  • the imaging for the second discrimination process is intermittently interrupted. That is, the endoscope apparatus 510 appropriately switches the illumination light to the discrimination illumination light of pattern 2 in accordance with the timing of imaging of the image sensor 41 (step S215), and the interval between the frames for imaging the endoscopic image 101 for observation Then, a frame for photographing a subject using the discrimination illumination light of pattern 2 is inserted as appropriate. Thereby, the endoscope apparatus 510 acquires the second endoscopic image 63 for the second discrimination process (step S216), and the second discrimination processing unit 52 uses the second endoscopic image 63. The second discrimination process is executed (step S217).
  • the integrated control unit 17 intermittently performs the third identification at predetermined timing that does not affect continuous display of the observation endoscope image 101 during capturing of the series of observation endoscope images 101. Interrupt the shooting for processing. That is, the endoscope apparatus 510 appropriately switches to the identification illumination light for a specific pattern having a spectrum suitable for the third identification processing according to the result of the second identification processing (step S218). At this time, the third discrimination processing unit 53 selects the spectrum of the illumination light used when acquiring the third medical image, using the result of the second discrimination processing. As a result of switching the illumination light, a frame for photographing a subject using the illumination light for the third discrimination process is inserted as needed between the frames for photographing the observation endoscope image 101.
  • the endoscope apparatus 510 acquires the third endoscopic image 66 for the third discrimination process (step S219), and the third discrimination processing unit 53 uses the third endoscopic image 66. And execute the third discrimination process (step S220).
  • the display control unit 15 displays at least the result of the third discrimination process on the display unit 13 (step S221).
  • the endoscope apparatus 510 including the medical image processing apparatus 10 may perform the first discrimination process, the second discrimination process, and the third discrimination process in real time to support diagnosis etc. in real time. it can.
  • the endoscope apparatus 510 including the medical image processing apparatus 10 further includes a zoom mechanism 531, a zoom control unit 541, a light amount control unit 542, a motion detection unit 543, an imaging control unit 545, and the like. Is preferred.
  • the zoom mechanism 531 is a mechanical mechanism or an electronic mechanism that changes the imaging magnification.
  • the mechanical mechanism is a so-called optical zoom
  • the electronic mechanism is a so-called electronic zoom.
  • the zoom control unit 541 controls the zoom mechanism 531 to set an imaging magnification.
  • the endoscope apparatus 510 can obtain the imaging magnification using the zoom control unit 541.
  • the light amount control unit 542 is appropriate according to the observation distance (the distance between the tip of the endoscope 31 and the subject, including the substantial distance between the tip of the endoscope 31 and the subject due to the change of the imaging magnification). Set the amount of illumination light.
  • the light source control unit 47 uses the light source unit 42 to emit observation illumination light and discrimination illumination light of each pattern with the light amount set by the light amount control unit 542.
  • the motion detection unit 543 uses the endoscope image such as the observation endoscope image 101 or the like to perform the motion of the subject or the relative motion of the subject and the endoscope 31 (hereinafter simply referred to as “motion”). It detects the direction, speed or movement amount.
  • the imaging control unit 545 controls the frequency of imaging for the first discrimination process, the frequency of imaging for the second discrimination process, or the frequency of imaging for the third discrimination process according to the observation condition.
  • the observation conditions are the imaging magnification at the time of imaging an endoscopic image, the light amount of illumination light, or the situation regarding movement.
  • the shooting control unit 545 can obtain the shooting magnification from the zoom control unit 541, can obtain the light quantity of the illumination light from the light quantity control unit 542, and can obtain the movement from the movement detection unit 543.
  • the photographing control unit 545 sets the photographing frequency for the first discrimination process, the photographing for the second discrimination process, and the photographing condition for the first discrimination process according to the photographing condition, the light amount of the illumination light, and the observation condition combining the motion. Control the frequency of imaging for the third discrimination process.
  • observation condition X1 having a relatively small imaging magnification, a relatively large amount of illumination light, and a relatively large movement is observed with a high frequency of occurrence in a so-called screening situation. It is a condition. Therefore, the imaging control unit 545 relatively increases the frequency of imaging of the observation endoscope image 101 and the frequency of imaging for the first discrimination process, and for the second discrimination process and the third discrimination process. Reduce the frequency of imaging for discrimination processing relatively. This is because, in general, screening mainly aims at general observation of an object or detection of an abnormal area 102.
  • observation condition X2 in which the imaging magnification is relatively large, the amount of illumination light is relatively small, and the movement is relatively small is an observation that occurs frequently when the object is observed in detail for diagnosis etc. It is a condition.
  • the imaging control unit 545 relatively reduces the imaging frequency of the observation endoscope image 101 and the imaging frequency for the first discrimination process, and for the second discrimination process and the third discrimination process. Relatively increase the frequency of shooting. In a situation where the subject is observed in detail for diagnosis etc., it is required that the results of the second discrimination process and the third discrimination process be presented promptly and accurately, following the slight change in appearance of the subject, etc. Because
  • the frequency of imaging of the observation endoscope image 101 As described above, using the observation conditions, the frequency of imaging of the observation endoscope image 101, the frequency of imaging for the first discrimination process, the frequency of imaging for the second discrimination process, and for the third discrimination process If the frequency of photographing is changed, discrimination results such as the result of the third discrimination processing can be presented at an appropriate updating frequency according to the situation of photographing (the purpose of photographing).
  • the frequency of imaging means to increase or decrease the frequency of imaging based on the frequency of specific imaging under the observation condition X1, the observation condition X2, or other observation conditions. . In this modification, the frequency of imaging under observation condition X1 is compared with the frequency of imaging under observation condition X2.
  • the endoscope apparatus 510 includes the medical image processing apparatus 10.
  • the diagnostic support apparatus 610 used in combination with the endoscope apparatus 21 and other modality is The medical image processing apparatus 10 of the said embodiment and the other modification can be included.
  • various inspection devices such as the first inspection device 621, the second inspection device 622, ..., the N-th inspection device 623, etc., including the endoscope device 21, for example, via the arbitrary network 626
  • the medical service support device 630 to be connected can include the medical image processing device 10 of the above-described embodiment and other modified examples.
  • the medical image processing apparatus 10 various apparatuses including the medical image processing apparatus 10, and various apparatuses or systems including the functions of the medical image processing apparatus 10 can be used with various modifications described below. .
  • a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band can be used.
  • a specific wavelength band can use a band narrower than the white wavelength band.
  • the specific wavelength band is, for example, a blue band or a green band in the visible range.
  • the specific wavelength band is a blue band or a green band in the visible range
  • the specific wavelength band includes a wavelength band of 390 nm to 450 nm or 530 nm to 550 nm, and light of the specific wavelength band is 390 nm or more It is preferable to have a peak wavelength within a wavelength band of 450 nm or less or 530 nm or more and 550 nm or less.
  • the specific wavelength band is, for example, a red band in the visible range.
  • the specific wavelength band is a red band in the visible range
  • the specific wavelength band includes a wavelength band of 585 nm to 615 nm or 610 nm to 730 nm, and light of the specific wavelength band is 585 nm to 615 nm or 610 nm It is preferable to have a peak wavelength within the wavelength band of not less than 730 nm.
  • the specific wavelength band includes, for example, wavelength bands in which the absorption coefficient is different between oxygenated hemoglobin and reduced hemoglobin, and light of a specific wavelength band is a peak wavelength in the wavelength band where absorption coefficients are different between oxygenated hemoglobin and reduced hemoglobin You can have
  • a specific wavelength band includes wavelength bands whose absorption coefficients are different between oxyhemoglobin and reduced hemoglobin, and light of a specific wavelength band has peak wavelengths in wavelength bands whose absorption coefficients are different between oxyhemoglobin and reduced hemoglobin
  • the specific wavelength band includes the wavelength bands of 400 ⁇ 10 nm, 440 ⁇ 10 nm, 470 ⁇ 10 nm, or 600 nm to 750 nm
  • the light of the specific wavelength band is 400 ⁇ 10 nm, 440 ⁇ 10 nm
  • this in-vivo image can have information of fluorescence emitted from a fluorescent substance in the living body.
  • fluorescence fluorescence obtained by irradiating excitation light having a peak wavelength of 390 nm or more and 470 nm or less into a living body can be used.
  • the above-mentioned specific wavelength band can utilize the wavelength band of infrared light.
  • the specific wavelength band is a wavelength band of 790 nm to 820 nm or 905 nm to 970 nm
  • light of a specific wavelength band preferably has a peak wavelength in a wavelength band of 790 nm or more and 820 nm or less or 905 nm or more and 970 nm or less.
  • the medical image acquisition unit 11 acquires a special light image having a signal of a specific wavelength band based on a normal light image obtained by irradiating light of a plurality of wavelength bands as light of the white band or light of the white band. It can have a special light image acquisition unit. In this case, a special light image can be used as a medical image.
  • a signal of a specific wavelength band can be obtained by an operation based on RGB or CMY color information included in a normal light image.
  • a feature amount image generation unit that generates a feature amount image can be provided.
  • the feature amount image can be used as a medical image.
  • a capsule endoscope can be used as the endoscope 31.
  • the light source device 32 and part of the processor device 33 can be mounted on the capsule endoscope.
  • the hardware-like structure of a processing unit that executes various processes is various processors as shown below.
  • CPU Central Processing Unit
  • PROM Programmable Logic Device
  • a programmable logic device which is a possible processor
  • a dedicated electric circuit which is a processor having a circuit configuration specially designed to execute various processes, are included.
  • One processing unit may be configured of one of these various processors, or configured of a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs or a combination of a CPU and an FPGA) It may be done.
  • a plurality of processing units may be configured by one processor.
  • one processor is configured by a combination of one or more CPUs and software as represented by computers such as clients and servers; There is a form in which this processor functions as a plurality of processing units.
  • SoC system on chip
  • IC integrated circuit
  • circuitry in the form in which circuit elements such as semiconductor elements are combined.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biomedical Technology (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biophysics (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Endoscopes (AREA)

Abstract

Provided are a medical image processing device whereby it is possible to present information about a lesion or the like that is more detailed and accurate than that of the prior art, and an endoscope device. A medical image processing device (10) is provided with: a medical image acquiring unit (11) for acquiring medical images including a subject image; a first discrimination processing unit (51) for performing first discrimination processing for detecting one or a plurality of types of abnormality regions using a first medical image, from among the medical images, that is captured using first illumination light having a specific spectrum; a second discrimination processing unit (52) for performing second discrimination processing for specifying a type of abnormality included by each abnormality region using a second medical image, from among the medical images, that is captured using second illumination light having a different spectrum than the first illumination light; and a third discrimination processing unit (53) for performing third discrimination processing for specifying the degree of progress of an abnormality included by an abnormality region using a third medical image, from among the medical images, that is captured using third illumination light having a different spectrum than the first illumination light and the second illumination light.

Description

医療画像処理装置、及び、内視鏡装置MEDICAL IMAGE PROCESSING DEVICE AND ENDOSCOPIC DEVICE
　本発明は、医療画像の解析結果を用いる医療画像処理装置、及び、内視鏡装置に関する。 The present invention relates to a medical image processing apparatus using an analysis result of a medical image, and an endoscope apparatus.
　従来、医療に係る装置（以下、医療装置という）のうち、被写体像を含む画像（以下、医療画像という）を取得するものは、取得した医療画像を医師に提示する。そして、医師は、医療装置から得る医療画像を判断材料の１つとして使用して診断等をする。当然ながら、診断の際に医療画像を用いてする被写体の状態等の鑑別は、医師の技量及び経験等に基づく。 Conventionally, among devices related to medical treatment (hereinafter referred to as medical devices), those that acquire images (hereinafter referred to as medical images) including a subject image present the acquired medical images to the doctor. Then, the doctor uses the medical image obtained from the medical device as one of the determination materials to make a diagnosis and the like. As a matter of course, the discrimination of the condition of the subject or the like using the medical image at the time of diagnosis is based on the skill and experience of the doctor.
　近年においては、画像解析技術が進歩したので、医療画像を解析することで、医療画像から客観的な情報または定量的な情報を得ることができる。このため、医療画像の解析結果を医師等に提示することにより、鑑別及び診断等を支援する医療装置が増えてきている。例えば、特許文献１に記載の内視鏡装置は、蛍光を用いて撮影した蛍光画像または特定の狭い波長帯域を有する光（いわゆる狭帯域光）を用いて撮影した狭帯域光画像を用いて異常がある領域の位置を特定する。そして、異常がある領域の位置を、表示用の内視鏡画像において表示する。 In recent years, as image analysis technology has advanced, objective information or quantitative information can be obtained from medical images by analyzing medical images. For this reason, medical devices that support discrimination, diagnosis, and the like are increasing by presenting analysis results of medical images to a doctor or the like. For example, the endoscope apparatus described in Patent Document 1 is abnormal using a fluorescence image taken using fluorescence or a narrow band light image taken using light having a specific narrow wavelength band (so-called narrow band light). Locate the area where And the position of the area | region which has abnormality is displayed on the endoscopic image for a display.
特開２００６－１９８１０６号公報Japanese Patent Application Publication No. 2006-198106
　従来の医療装置においては、医療画像を解析することにより病変等の異常が認められる部分（病変部分または病変の可能性がある部分）を１または複数含む注目すべき領域（いわゆる注目領域、関心領域、または、異常領域等と称する領域である。以下、単に異常領域という。）を検出し、その位置等を提示して診断等を支援する。 In a conventional medical device, a notable area (so-called attention area, area of interest) including one or more parts where abnormality such as a lesion is recognized by analyzing a medical image (lesion part or a part having a possibility of a lesion) Or, it is an area called an abnormal area etc. Hereinafter, it is simply referred to as an abnormal area, and the position etc. is presented to support diagnosis and the like.
　医師等は、医療装置が提示した異常領域にある病変等について、その種類及び進行度等を鑑別するが、病変等の種類及び進行度の鑑別は依然として負担が大きい。このため、近年では、さらに医師等の負担を低減すべく、病変等の種類及び進行度等について、鑑別の材料となる詳細な情報を提供することが求められている。 The doctor or the like distinguishes the type and the degree of progress of the lesion or the like in the abnormal area presented by the medical device, but the type and the degree of progression of the lesion or the like still bear a heavy burden. For this reason, in recent years, in order to further reduce the burden on a doctor or the like, it is required to provide detailed information as a material for discrimination about the type and the degree of progression of a lesion or the like.
　本発明は、病変等について従来よりも詳細かつ正確な情報を提示できる医療画像処理装置、及び、内視鏡装置を提供することを目的とする。 An object of the present invention is to provide a medical image processing apparatus and an endoscope apparatus capable of presenting more detailed and accurate information on a lesion or the like than ever.
　本発明の医療画像処理装置は、被写体像を含む医療画像を取得する医療画像取得部と、医療画像のうち、特定のスペクトルを有する第１照明光を使用して撮影した第１医療画像を用いて１または複数種類の第１異常領域を検出する第１鑑別処理を行う第１鑑別処理部と、医療画像のうち、第１照明光とはスペクトルが異なる第２照明光を使用して撮影した第２医療画像を用いて、各々の第１異常領域が含む異常の種類を特定する第２鑑別処理を行う第２鑑別処理部と、医療画像のうち、第１照明光及び第２照明光とはスペクトルが異なる第３照明光を使用して撮影した第３医療画像を用いて、第１異常領域が含む異常の進行度を特定する第３鑑別処理を行う第３鑑別処理部と、を備える。 A medical image processing apparatus according to the present invention uses a first medical image captured using a first illumination light having a specific spectrum among medical images, and a medical image acquisition unit for acquiring a medical image including a subject image. The first discrimination processing unit that performs a first discrimination process for detecting one or more types of first abnormal regions, and the second illumination light having a spectrum different from that of the first illumination light in the medical image A second discrimination processing unit for performing a second discrimination process of identifying the type of abnormality included in each of the first abnormal areas using the second medical image; first illumination light and second illumination light of the medical image And a third discrimination processing unit that performs a third discrimination process of identifying the degree of progression of the abnormality included in the first abnormal area using the third medical image captured using the third illumination light having different spectra. .
　第２鑑別処理部は、第１異常領域に対応する第２医療画像に含まれる第２異常領域に対して第２鑑別処理を行うことで、第１異常領域が含む異常の種類を特定することが好ましい。 The second discrimination processing unit identifies the type of abnormality included in the first abnormal area by performing the second discrimination processing on the second abnormal area included in the second medical image corresponding to the first abnormal area. Is preferred.
　第３鑑別処理部は、第１異常領域または第２異常領域の少なくとも一方に対応する第３医療画像に含まれる第３異常領域に対して第３鑑別処理を行うことで、第１異常領域が含む異常の進行度を特定することが好ましい。 The third discrimination processing unit performs the third discrimination processing on the third abnormal region included in the third medical image corresponding to at least one of the first abnormal region or the second abnormal region, whereby the first abnormal region is It is preferable to specify the degree of progression of the abnormality included.
　第３鑑別処理部は、第２鑑別処理の結果を用いて第３医療画像を選択することが好ましい。 The third discrimination processing unit preferably selects the third medical image using the result of the second discrimination processing.
　第３鑑別処理部は、第２鑑別処理の結果と対応付けられた第３照明光のスペクトルで取得された第３医療画像を選択することが好ましい。 It is preferable that a 3rd discrimination | determination process part selects the 3rd medical image acquired by the spectrum of 3rd illumination light matched with the result of a 2nd discrimination process.
　医療画像取得部は、第１医療画像、第２医療画像、及び、第３医療画像の他に、観察用医療画像を取得し、観察用医療画像を表示部に表示している間に、第１鑑別処理部は第１鑑別処理をし、第２鑑別処理部は第２鑑別処理をし、かつ、第３鑑別処理部は第３鑑別処理をすることが好ましい。 The medical image acquisition unit acquires a medical image for observation other than the first medical image, the second medical image, and the third medical image, and displays the medical image for observation on the display unit. The first discrimination processing unit preferably performs the first discrimination processing, the second discrimination processing unit performs the second discrimination processing, and the third discrimination processing unit preferably performs the third discrimination processing.
　医療画像取得部は、第１医療画像、第２医療画像、及び、第３医療画像のうちの何れかを観察用医療画像に設定し、観察用医療画像を表示部に表示している間に、第１鑑別処理部は第１鑑別処理をし、第２鑑別処理部は第２鑑別処理をし、かつ、第３鑑別処理部は第３鑑別処理をすることが好ましい。 The medical image acquisition unit sets any one of the first medical image, the second medical image, and the third medical image as a medical image for observation, and while displaying the medical image for observation on the display unit The first discrimination processing unit preferably performs the first discrimination processing, the second discrimination processing unit performs the second discrimination processing, and the third discrimination processing unit preferably performs the third discrimination processing.
　第２鑑別処理において特定する異常の種類、または、第３鑑別処理において特定する進行度の分類の設定を変更する設定部を備えることが好ましい。 It is preferable to include a setting unit that changes the type of the abnormality identified in the second discrimination process or the setting of the classification of the progress degree identified in the third discrimination process.
　設定部は、第１照明光、第２照明光、または、第３照明光の各スペクトルもしくは組み合わせの設定を変更することが好ましい。 Preferably, the setting unit changes settings of each spectrum or combination of the first illumination light, the second illumination light, or the third illumination light.
　カルテを取得するカルテ取得部を備え、設定部は、カルテが含む情報を用いて設定をすることが好ましい。 It is preferable that the medical chart acquisition unit includes a medical chart acquisition unit for acquiring a medical chart, and the setting unit sets the information using information included in the medical chart.
　設定部は、第２鑑別処理において特定する異常の種類に、カルテが含む情報によって定まる特定の病変を含めることが好ましい。 The setting unit preferably includes, in the type of the abnormality identified in the second discrimination process, a specific lesion determined by the information included in the medical record.
　第１鑑別処理の結果、第２鑑別処理の結果、または、第３鑑別処理の結果を修正する鑑別結果修正部を備えることが好ましい。 As a result of the first discrimination process, it is preferable to include a discrimination result correction unit that corrects the result of the second discrimination process or the result of the third discrimination process.
　第１鑑別処理の結果、第２鑑別処理の結果、または、第３鑑別処理の結果を報知する鑑別結果報知部を備えることが好ましい。 It is preferable to provide the discrimination result notification part which alert | reports the result of a 2nd discrimination process, or the result of a 3rd discrimination process as a result of a 1st discrimination process.
　本発明の内視鏡装置は、被写体像を含む内視鏡画像を取得する内視鏡画像取得部と、内視鏡画像のうち、特定のスペクトルを有する第１照明光を使用して撮影した第１内視鏡画像を用いて１または複数種類の第１異常領域を検出する第１鑑別処理を行う第１鑑別処理部と、内視鏡画像のうち、第１照明光とはスペクトルが異なる第２照明光を使用して撮影した第２内視鏡画像を用いて、各々の第１異常領域が含む異常の種類を特定する第２鑑別処理を行う第２鑑別処理部と、内視鏡画像のうち、第１照明光及び第２照明光とはスペクトルが異なる第３照明光を使用して撮影した第３医療画像を用いて、第１異常領域が含む異常の進行度を特定する第３鑑別処理部と、を備える。 The endoscope apparatus of the present invention is photographed using an endoscope image acquisition unit for acquiring an endoscope image including a subject image, and a first illumination light having a specific spectrum of the endoscope image. A first discrimination processing unit that performs a first discrimination process of detecting one or more types of first abnormal areas using the first endoscopic image, and a spectrum of the first illumination light in the endoscopic image have different spectra. A second discrimination processing unit that performs a second discrimination process of identifying the type of abnormality included in each of the first abnormal areas using a second endoscopic image captured using a second illumination light; and an endoscope A third medical image captured using a third illumination light having a spectrum different from that of the first illumination light and the second illumination light in the image is used to specify the progression degree of the anomaly included in the first anomaly region. And (3) a discrimination processing unit.
　第３鑑別処理部は、第２鑑別処理の結果を用いて第３医療画像を取得する際に用いる照明光のスペクトルを選択することが好ましい。 It is preferable that a 3rd discrimination | determination process part selects the spectrum of the illumination light used when acquiring a 3rd medical image using the result of a 2nd discrimination process.
　本発明の医療画像処理装置及び内視鏡装置は、病変等について従来よりも詳細かつ正確な情報を提供できる。 The medical image processing apparatus and the endoscope apparatus of the present invention can provide more detailed and accurate information on lesions and the like than ever before.
医療画像処理装置のブロック図である。It is a block diagram of a medical image processing device. 内視鏡装置のブロック図である。It is a block diagram of an endoscope apparatus. 光源装置が発光し得る照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light which a light source device can emit. 観察用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for observation. パターン１の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 1. FIG. パターン２の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 2. FIG. パターン３の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 3. FIG. パターン４の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 4. FIG. パターン５の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 5. FIG. パターン６の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 6. FIG. パターン７の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 7. FIG. パターン８の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 8. FIG. パターン９の鑑別用照明光のスペクトルを示すグラフである。It is a graph which shows the spectrum of the illumination light for discrimination of pattern 9. FIG. 医療画像解析処理部のブロック図である。It is a block diagram of a medical image analysis processing part. 第１内視鏡画像（第１医療画像）である。It is a 1st endoscopic image (1st medical image). 第２内視鏡画像（第２医療画像）である。It is a 2nd endoscopic image (2nd medical image). 第２鑑別処理部のブロック図である。It is a block diagram of a 2nd discrimination processing part. 第３内視鏡画像（第３医療画像）である。It is a 3rd endoscopic image (3rd medical image). 第３鑑別処理部のブロック図である。It is a block diagram of a 3rd discrimination processing part. 設定部における設定の内容を示す説明図である。It is an explanatory view showing the contents of setting in a setting part. 医療画像処理装置の作用を示すフローチャートである。It is a flowchart which shows an effect | action of a medical image processing apparatus. 鑑別結果を示す表示画面の例である。It is an example of the display screen which shows a discrimination result. カルテ取得部を設けた医療画像解析処理部のブロック図である。It is a block diagram of a medical image analysis processing unit provided with a chart acquisition unit. 鑑別結果修正部を設けた医療画像解析処理部のブロック図である。It is a block diagram of a medical image analysis processing unit provided with a discrimination result correction unit. 鑑別結果報知部を設けた医療画像解析処理部のブロック図である。It is a block diagram of a medical image analysis processing unit provided with a discrimination result notification unit. 医療画像処理装置を含む内視鏡装置のブロック図である。It is a block diagram of an endoscope apparatus containing a medical image processing device. 内視鏡装置においてリアルタイムに鑑別処理を行う場合のフローチャートである。It is a flowchart in the case of performing a discrimination | determination process in real time in an endoscope apparatus. 医療画像処理装置を含む内視鏡装置のブロック図である。It is a block diagram of an endoscope apparatus containing a medical image processing device. 観察条件と撮影の頻度を示す表である。It is a table | surface which shows observation conditions and the frequency of imaging | photography. 医療画像処理装置を含む診断支援装置の説明図である。It is an explanatory view of a diagnosis support device containing a medical image processing device. 医療画像処理装置を含む医療業務支援装置の説明図である。It is an explanatory view of a medical operation support device including a medical image processing device.
　［第１実施形態］
　図１に示すように、医療画像処理装置１０は、医療画像取得部１１、医療画像解析処理部１２、表示部１３、表示制御部１５、入力受信部１６、統括制御部１７、及び、保存部１８を備える。 First Embodiment
As shown in FIG. 1, the medical image processing apparatus 10 includes a medical image acquisition unit 11, a medical image analysis processing unit 12, a display unit 13, a display control unit 15, an input reception unit 16, an overall control unit 17, and a storage unit. It has eighteen.
　医療画像取得部１１は、医療装置である内視鏡装置２１等から直接に、または、ＰＡＣＳ（Picture Archiving and Communication System）２２等の管理システムもしくはその他情報システムを介して、被写体像を含む医療画像を取得する。医療画像は、静止画像または動画（いわゆる検査動画）である。医療画像が動画である場合、医療画像取得部１１は、検査後に、動画を構成するフレーム画像を静止画像として取得することができる。また、医療画像が動画である場合、医療画像の表示には、動画を構成する１つの代表フレームの静止画像を表示することのほか、動画を１または複数回、再生することを含む。また、医療画像取得部１１が取得する医療画像には、内視鏡装置２１等の医療装置を用いて医師が撮影した画像の他、内視鏡装置２１等の医療装置が医師の撮影指示に依らず自動的に撮影した画像を含む。 The medical image acquisition unit 11 is a medical image including a subject image directly from the endoscope apparatus 21 or the like which is a medical apparatus, or via a management system such as a PACS (Picture Archiving and Communication System) 22 or other information system. To get The medical image is a still image or a moving image (so-called test moving image). When the medical image is a moving image, the medical image acquiring unit 11 can acquire a frame image constituting the moving image as a still image after the examination. When the medical image is a moving image, displaying the medical image includes reproducing the moving image one or more times in addition to displaying a still image of one representative frame constituting the moving image. In addition, in the medical image acquired by the medical image acquisition unit 11, the medical device such as the endoscope device 21 or the like receives the imaging instruction of the doctor in addition to the image photographed by the doctor using the medical device such as the endoscope device 21 or the like. Includes images taken automatically regardless of
　医療画像取得部１１は、複数の医療画像を取得し得る場合、これらの医療画像のうち１または複数の医療画像を選択的に取得できる。また、医療画像取得部１１は、複数の互いに異なる検査において取得した複数の医療画像を取得できる。例えば、過去に行った検査で取得した医療画像と、最新の検査で取得した医療画像と、の一方または両方を取得できる。すなわち、医療画像取得部１１は、任意に医療画像を取得できる。 When the medical image acquisition unit 11 can acquire a plurality of medical images, it can selectively acquire one or more medical images among these medical images. Further, the medical image acquisition unit 11 can acquire a plurality of medical images acquired in a plurality of different examinations. For example, one or both of a medical image acquired by an examination performed in the past and a medical image acquired by the latest examination can be acquired. That is, the medical image acquisition unit 11 can arbitrarily acquire a medical image.
　本実施形態においては、医療画像処理装置１０は、内視鏡装置２１と接続し、内視鏡装置２１から医療画像を取得する。すなわち、本実施形態において医療画像は、内視鏡画像である。 In the present embodiment, the medical image processing apparatus 10 is connected to the endoscope apparatus 21 and acquires a medical image from the endoscope apparatus 21. That is, in the present embodiment, the medical image is an endoscopic image.
　また、異常領域１０２（図１５等参照）等の異常領域の有無の鑑別（異常領域１０２の検出）、異常領域１０２が含む病変等の種類の鑑別、及び、異常領域１０２が含む病変等の進行度の鑑別をするために、医療画像取得部１１は、少なくとも相互に撮影条件が異なる複数の内視鏡画像（医療画像）を取得する。本実施形態においては、医療画像取得部１１は、表示部１３に表示する観察用の内視鏡画像（以下、観察用内視鏡画像１０１（観察用医療画像）という。図２２参照。）と、異常領域１０２の有無の鑑別に用いる内視鏡画像（以下、第１内視鏡画像６１という。図１５参照。）と、異常領域１０２が含む病変等の種類の鑑別に用いる内視鏡画像（以下、第２内視鏡画像６３という。図１６参照。）と、異常領域１０２が含む病変等の進行度の鑑別に用いる内視鏡画像（以下、第３内視鏡画像６６という。図１８参照。）と、を取得する。観察用内視鏡画像１０１、第１内視鏡画像６１、第２内視鏡画像６３、及び、第３内視鏡画像６６は、各々の使用目的に合わせるために、相互に撮影条件が異なる。 Further, discrimination of presence / absence of abnormal area such as abnormal area 102 (see FIG. 15 etc.) (detection of abnormal area 102), discrimination of type of lesion etc. included in abnormal area 102, progression of lesions included in abnormal area 102 etc. In order to determine the degree, the medical image acquisition unit 11 acquires a plurality of endoscopic images (medical images) at least having mutually different imaging conditions. In the present embodiment, the medical image acquisition unit 11 displays an endoscopic image for observation displayed on the display unit 13 (hereinafter referred to as an endoscopic image for observation 101 (medical image for observation); see FIG. 22). , An endoscopic image (hereinafter referred to as the first endoscopic image 61; see FIG. 15) used to distinguish the presence or absence of the abnormal area 102 and an endoscopic image used to distinguish the type of lesion etc. included in the abnormal area 102 (Hereinafter referred to as the second endoscopic image 63; see FIG. 16) and an endoscopic image (hereinafter referred to as the third endoscopic image 66) used to distinguish the degree of progress of a lesion or the like included in the abnormal area 102. 18) and get. The observation endoscopic image 101, the first endoscopic image 61, the second endoscopic image 63, and the third endoscopic image 66 have different imaging conditions from one another in order to match the purpose of use. .
　撮影条件とは、医療画像の撮影に係る条件であって、例えば、照明光のスペクトル、または、医療画像を生成する際の画像処理の有無もしくは強度、等である。照明光のスペクトルとは、波長ごとの強度分布であり、波長帯域及び中心波長の概念を含む。医療画像を生成する際の画像処理とは、例えば、特定の組織または病変等を強調する色彩等の調節に係る処理等である。 The imaging condition is a condition relating to imaging of a medical image, and is, for example, the spectrum of illumination light or the presence or absence or intensity of image processing at the time of generating a medical image. The spectrum of illumination light is an intensity distribution for each wavelength, and includes the concepts of wavelength band and central wavelength. The image processing at the time of generating a medical image is, for example, processing relating to adjustment of a color or the like that emphasizes a specific tissue or a lesion.
　図２に示すように、本実施形態において医療画像処理装置１０が接続する内視鏡装置２１は、白色の波長帯域の光もしくは特定の波長帯域の光の少なくともいずれかを照射して被写体を撮影する内視鏡３１、内視鏡３１を介して被写体内に照明光を照射する光源装置３２、プロセッサ装置３３、及び、内視鏡３１を用いて撮影した内視鏡画像等を表示するモニタ３４を有する。 As shown in FIG. 2, in the present embodiment, the endoscope apparatus 21 to which the medical image processing apparatus 10 is connected shoots a subject by irradiating at least one of light of a white wavelength band or light of a specific wavelength band. Endoscope 31, a light source device 32 for emitting illumination light into a subject through the endoscope 31, a processor device 33, and a monitor 34 for displaying an endoscopic image or the like captured using the endoscope 31. Have.
　内視鏡３１は、被写体が反射または散乱した照明光、または、被写体もしくは被写体に投与した薬剤等が発光する蛍光、等を用いて被写体を撮影するイメージセンサ４１を備える。イメージセンサ４１は、例えば、ＣＭＯＳ（Complementary Metal-Oxide-Semiconductor）のカラーセンサ（カラーフィルタを有するセンサ）である。 The endoscope 31 includes an image sensor 41 for imaging a subject using illumination light in which the subject is reflected or scattered, or fluorescence from which the subject or a drug or the like administered to the subject emits light. The image sensor 41 is, for example, a complementary metal-oxide-semiconductor (CMOS) color sensor (a sensor having a color filter).
　光源装置３２は、光源部４２と、光源制御部４７と、を含む。光源部４２は、スペクトルが異なる複数種類の照明光を発光する。光源部４２は、例えば、ＬＥＤ（Light Emitting Diode）、ＬＤ（Laser Diode）、またはキセノンランプ等の発光デバイスを備える。また、光源部４２は、プリズム、ミラー、光ファイバ、または、波長帯域もしくは光量等を調節する光学フィルタ等、を必要に応じて備える。本実施形態においては、光源部４２は、中心波長が約４０５ｎｍの紫色光を発光するＶ－ＬＥＤ４３と、中心波長が約４５０ｎｍの青色光を発光するＢ－ＬＥＤ４４と、中心波長が約５４０ｎｍの緑色光を発光するＧ－ＬＥＤ４５と、中心波長が約６３０ｎｍのＲ－ＬＥＤ４６と、を備える。 The light source device 32 includes a light source unit 42 and a light source control unit 47. The light source unit 42 emits a plurality of types of illumination light having different spectra. The light source unit 42 includes, for example, a light emitting device such as a light emitting diode (LED), a laser diode (LD), or a xenon lamp. In addition, the light source unit 42 is provided with a prism, a mirror, an optical fiber, an optical filter for adjusting a wavelength band, a light amount, and the like as needed. In the present embodiment, the light source unit 42 includes a V-LED 43 that emits violet light with a center wavelength of about 405 nm, a B-LED 44 that emits blue light with a center wavelength of about 450 nm, and a green light with a center wavelength of about 540 nm. It comprises a G-LED 45 emitting light and an R-LED 46 with a center wavelength of about 630 nm.
　光源制御部４７は、光源部４２が含む発光源を制御し、内視鏡３１が被写体の撮影に使用する照明光を発生する。また、光源制御部４７は、光源部４２が複数の発光デバイスを含む場合、各発光デバイスの発光のタイミング及び発光量をそれぞれに制御することができる。したがって、光源装置３２は、スペクトルが異なる複数種類の照明光を、任意のタイミング及び任意の強度で内視鏡３１に供給できる。すなわち、本実施形態においては、光源装置３２は、光源制御部４７が行う制御により、白色光の他、紫色光、青色光、緑色光、赤色光、または、これら各色の光のうち２以上を任意の強度比で混合した光等を、任意のタイミング及び任意の強度で照明光として発光できる。 The light source control unit 47 controls the light emission source included in the light source unit 42, and generates illumination light used by the endoscope 31 for photographing an object. Further, when the light source unit 42 includes a plurality of light emitting devices, the light source control unit 47 can control the light emission timing and the light emission amount of each light emitting device. Therefore, the light source device 32 can supply the endoscope 31 with a plurality of types of illumination light having different spectra, at any timing and at any intensity. That is, in the present embodiment, the light source device 32 controls two or more of purple light, blue light, green light, red light or light of each color other than white light under the control of the light source control unit 47. Light mixed at an arbitrary intensity ratio can be emitted as illumination light at an arbitrary timing and an arbitrary intensity.
　例えば、本実施形態においては、光源装置３２は、図３に示すように、Ｖ－ＬＥＤ４３が発光する紫色光（符号「Ｖ」で表す。以下同じ。）と、Ｂ－ＬＥＤ４４が発光する青色光（符号「Ｂ」で表す。以下同じ。）と、Ｇ－ＬＥＤ４５が発光する緑色光（符号「Ｇ」で表す。以下同じ。）と、Ｒ－ＬＥＤ４６が発光する赤色光（符号「Ｒ」で表す。以下同じ。）と、を含む照明光を発光できる。光源制御部４７は、上記照明光が含む、紫色光Ｖ、青色光Ｂ、緑色光Ｇ、及び、赤色光Ｒの各色光の光量を、撮影の目的等に応じて任意に制御する。 For example, in the present embodiment, as shown in FIG. 3, the light source device 32 emits violet light (represented by a symbol “V”. The same applies hereinafter) emitted by the V-LED 43 and blue light emitted by the B-LED 44. The green light emitted by the G-LED 45 (represented by the code “G”. The same applies hereinafter) and the red light emitted by the R-LED 46 (indicated by the code “R”) And the same.) And can emit light. The light source control unit 47 arbitrarily controls the light amount of each color light of purple light V, blue light B, green light G, and red light R included in the illumination light according to the purpose of photographing.
　例えば、観察用内視鏡画像１０１を得る場合、光源装置３２は、図４に示す観察用スペクトルを有する照明光（以下、観察用照明光という）を発光する。観察用照明光は、いわゆる白色光である。また、各種鑑別処理用の第１内視鏡画像６１、第２内視鏡画像６３、または第３内視鏡画像６６を得る場合、光源装置３２は、例えば、図５に示すスペクトルを有する照明光（以下、パターン１の鑑別用照明光という）、図６に示すスペクトルを有する照明光（以下、パターン２の鑑別用照明光という）、図７に示すスペクトルを有する照明光（以下、パターン３の鑑別用照明光という）、図８に示すスペクトルを有する照明光（以下、パターン４の鑑別用照明光という）、図９に示すスペクトルを有する照明光（以下、パターン５の鑑別用照明光という）、図１０に示すスペクトルを有する照明光（以下、パターン６の鑑別用照明光という）、図１１に示すスペクトルを有する照明光（以下、パターン７の鑑別用照明光という）、図１２に示すスペクトルを有する照明光、または、図１３に示すスペクトルを有する照明光（以下、パターン９の鑑別用照明光という）を適宜切り替えて発光する。 For example, when obtaining the observation endoscope image 101, the light source device 32 emits illumination light (hereinafter, referred to as observation illumination light) having the observation spectrum shown in FIG. The observation illumination light is so-called white light. In addition, in the case of obtaining the first endoscopic image 61, the second endoscopic image 63, or the third endoscopic image 66 for various discrimination processing, the light source device 32 has, for example, illumination having a spectrum shown in FIG. Light (hereinafter referred to as discrimination illumination light of pattern 1), illumination light having a spectrum shown in FIG. 6 (hereinafter referred to as discrimination illumination light of pattern 2), illumination light having a spectrum shown in FIG. 7 (hereinafter pattern 3) Illumination light having a spectrum shown in FIG. 8 (hereinafter referred to as discrimination illumination light for pattern 4), illumination light having a spectrum shown in FIG. 9 (hereinafter referred to as discrimination illumination light for pattern 5) 10), illumination light having the spectrum shown in FIG. 10 (hereinafter referred to as discrimination illumination light for pattern 6), illumination light having the spectrum shown in FIG. 11 (hereinafter referred to as discrimination illumination light for pattern 7), Illumination light having to the spectral or the illumination light having a spectrum shown in FIG. 13 (hereinafter, referred to as differential illumination light pattern 9) emits light switched appropriately.
　パターン１の鑑別用照明光（図５参照）は第１内視鏡画像６１を取得する際に使用する。パターン２の鑑別用照明光（図６参照）は第２内視鏡画像６３を取得する際に使用する。パターン６の鑑別用照明光（図１０参照）、パターン３の鑑別用照明光（図７参照）、及び、パターン４の鑑別用照明光（図４参照）は、第３内視鏡画像６６を取得する際に使用する。より具体的には、パターン６の鑑別用照明光は、ポリープの進行度を鑑別するための第３内視鏡画像６６を取得する際に使用し、パターン３の鑑別用照明光は、潰瘍性大腸炎の進行度を鑑別するための第３内視鏡画像６６を取得する際に使用し、かつ、パターン４の鑑別用照明光はクローン病の進行度を鑑別するための第３内視鏡画像６６を取得する際に使用する。 The identification illumination light for pattern 1 (see FIG. 5) is used when acquiring the first endoscopic image 61. The identification illumination light for pattern 2 (see FIG. 6) is used when acquiring the second endoscopic image 63. The illumination light for discrimination of pattern 6 (see FIG. 10), the illumination light for discrimination of pattern 3 (see FIG. 7), and the illumination light for discrimination of pattern 4 (see FIG. 4) form the third endoscopic image 66 Used when acquiring. More specifically, the discrimination illumination light of pattern 6 is used when acquiring the third endoscopic image 66 for discriminating the degree of progression of the polyp, and the differentiation illumination light of pattern 3 is ulcerative It is used when acquiring the 3rd endoscopic image 66 for discriminating the degree of progression of colitis, and the illumination light for discrimination of pattern 4 is the 3rd endoscope for differentiating the degree of progression of Crohn's disease It is used when acquiring the image 66.
　この他、光源装置３２は、発光デバイスの特性により、または、光学フィルタの使用により、特定の狭い波長帯域を有する光（いわゆる狭帯域光）を照明光として発光できる。例えば、緑色波長帯域よりも短波長帯域の光、特に可視域の青色帯域または紫色帯域の光を発光できる。 In addition to this, the light source device 32 can emit light having a specific narrow wavelength band (so-called narrow band light) as illumination light according to the characteristics of the light emitting device or the use of an optical filter. For example, it is possible to emit light in a wavelength band shorter than the green wavelength band, in particular, light in the blue band or purple band in the visible range.
　プロセッサ装置３３は、イメージセンサ４１から内視鏡画像を取得し、または、イメージセンサ４１から取得した内視鏡画像に画像処理を施した内視鏡画像を生成する内視鏡画像生成部４８を備える。イメージセンサ４１及び内視鏡画像生成部４８は、内視鏡装置２１において「内視鏡画像取得部」を構成する。内視鏡画像取得部は、照明光を使用して被写体を撮影することにより、被写体像を含む内視鏡画像を取得する。医療画像処理装置１０は上記プロセッサ装置３３と接続する。そして、医療画像取得部１１は、内視鏡装置２１の内視鏡画像生成部４８から直接に内視鏡画像を取得する。 The processor device 33 acquires an endoscopic image from the image sensor 41, or generates an endoscopic image by performing image processing on the endoscopic image acquired from the image sensor 41. Prepare. The image sensor 41 and the endoscope image generation unit 48 constitute an “endoscope image acquisition unit” in the endoscope apparatus 21. The endoscopic image acquisition unit acquires an endoscopic image including an object image by photographing the object using the illumination light. The medical image processing apparatus 10 is connected to the processor 33. Then, the medical image acquisition unit 11 acquires an endoscope image directly from the endoscope image generation unit 48 of the endoscope apparatus 21.
　医療画像解析処理部１２は、医療画像取得部１１が取得した医療画像である内視鏡画像を用いて解析処理をする。具体的には、図１４に示すように、第１鑑別処理部５１と、第２鑑別処理部５２と、第３鑑別処理部５３と、設定部５６と、を含む。 The medical image analysis processing unit 12 performs analysis processing using an endoscopic image which is a medical image acquired by the medical image acquisition unit 11. Specifically, as shown in FIG. 14, it includes a first discrimination processing unit 51, a second discrimination processing unit 52, a third discrimination processing unit 53, and a setting unit 56.
　第１鑑別処理部５１は、医療画像を用いて異常領域１０２の有無を鑑別する。具体的には、第１鑑別処理部５１は、医療画像取得部１１が取得した医療画像のうち、特定のスペクトルを有する第１照明光を使用して撮影した第１医療画像を用いて１または複数種類の異常領域１０２を検出する第１鑑別処理を行う。本実施形態において、「特定のスペクトルを有する第１照明光」とはパターン１の鑑別用照明光であり、かつ、図１５に示すように、第１医療画像は第１内視鏡画像６１である。以下、他の医療画像における異常領域１０２との区別が必要な場合には、第１内視鏡画像６１（第１医療画像）における異常領域１０２は「第１異常領域」という。第１鑑別処理部５１は、例えば、第１内視鏡画像６１を用いて１または複数の所定の特徴量を算出し、算出した特徴量を用いて異常領域１０２を検出する。所定の特徴量とは、例えば、色もしくは明るさ、血管等の特定の組織または構造の形状、長さ、太さ、粘膜表面からの深さ、密度、大きさ、分布等の範囲、分岐数、複雑度、規則性の乱れ、または、その他の特徴に係る数量である。第１鑑別処理部５１は、特徴量を使用する代わりに、例えば、テクスチャ解析または規則形状を用いたパターンマッチングにより、第１鑑別処理を行うことができる。 The first discrimination processing unit 51 discriminates the presence or absence of the abnormal area 102 using the medical image. Specifically, of the medical images acquired by the medical image acquisition unit 11, the first discrimination processing unit 51 uses one or more of the first medical images captured using the first illumination light having a specific spectrum. A first discrimination process of detecting a plurality of types of abnormal areas 102 is performed. In the present embodiment, “first illumination light having a specific spectrum” is illumination light for discrimination of pattern 1 and, as shown in FIG. 15, the first medical image is the first endoscopic image 61. is there. Hereinafter, when it is necessary to distinguish from the abnormal area 102 in another medical image, the abnormal area 102 in the first endoscopic image 61 (first medical image) is referred to as a “first abnormal area”. For example, the first discrimination processing unit 51 calculates one or a plurality of predetermined feature amounts using the first endoscopic image 61, and detects the abnormal area 102 using the calculated feature amounts. The predetermined feature amount is, for example, color or brightness, shape of a specific tissue or structure such as a blood vessel, length, thickness, depth from a mucosal surface, density, size, distribution, etc., number of branches, etc. , Complexity, disorder of regularity, or other characteristic quantities. The first discrimination processing unit 51 can perform the first discrimination processing by, for example, texture analysis or pattern matching using a regular shape, instead of using the feature amount.
　医療画像取得部１１が内視鏡画像を取得する場合、第１鑑別処理部５１が異常領域１０２として検出する対象は、１または複数の病変、周辺の組織等と相違する色もしくは形状の特徴を有する領域、薬剤を散布等した領域、または、処置（生検、内視鏡的粘膜切除術（ＥＭＲ（Endoscopic Mucosal Resection））、または、内視鏡的粘膜下層剥離術（ＥＳＤ（Endoscopic Submucosal Dissection））等）を実施した領域、等の対象を含む領域である。医療画像が内視鏡画像である場合、病変等とは、例えば、潰瘍性大腸炎等の炎症性疾患に係る炎症、クローン病、または、ポリープ（***性病変）等である。ポリープとは、より具体的には、過形成ポリープ（ＨＰ：hyperplastic polyp）、ＳＳＡ／Ｐ（sessile serrated adenoma/polyp）、腺腫、癌、等である。また、周辺の組織等と相違する色もしくは形状の特徴を有する領域とは、被写体の発赤、萎縮、憩室、または、治療痕、等である。 When the medical image acquisition unit 11 acquires an endoscopic image, a target detected by the first discrimination processing unit 51 as the abnormal area 102 is a feature of a color or shape different from one or more lesions, surrounding tissues, etc. Area, drug-applied area, or treatment (biopsy, endoscopic mucosal resection (EMR), or endoscopic submucosal dissection (ESD) Etc.) is an area including the target of the area etc.). When the medical image is an endoscopic image, the lesion or the like is, for example, inflammation associated with an inflammatory disease such as ulcerative colitis, Crohn's disease, or a polyp (raised lesion) or the like. More specifically, polyps are hyperplastic polyp (HP), sessile serrated adenoma / polyp (SSA), adenoma, cancer, etc. In addition, the area having characteristics of color or shape different from the surrounding tissue or the like is, for example, the subject's redness, atrophy, diverticulum, or a treatment scar.
　第１鑑別処理部５１は、医療画像の一部または全部について、異常領域１０２を検出する。すなわち、第１鑑別処理部５１は、第１鑑別処理を、画素ごとに、内視鏡画像を小領域に分ける場合にはその小領域ごとに、または、内視鏡画像の全体に対して、行うことができる。本実施形態においては、第１鑑別処理部５１は、所定数の画素からなる小領域ごとに、異常領域１０２か否かを判断する。したがって、第１鑑別処理部５１は、医療画像の１箇所または複数箇所において異常領域１０２を検出することができる。第１鑑別処理部５１は、処理結果の確からしさを表す「確度」と、を第１鑑別処理の結果に含めることができる。 The first discrimination processing unit 51 detects the abnormal area 102 for a part or all of the medical image. That is, the first discrimination processing unit 51 performs the first discrimination processing on a pixel-by-pixel basis, in a case where the endoscope image is divided into small regions, for each small region, or with respect to the entire endoscope image, It can be carried out. In the present embodiment, the first discrimination processing unit 51 determines, for each small area including a predetermined number of pixels, whether the area is the abnormal area 102 or not. Therefore, the first discrimination processing unit 51 can detect the abnormal area 102 at one or more places of the medical image. The first discrimination processing unit 51 can include, in the result of the first discrimination processing, “probability” indicating the certainty of the processing result.
　第２鑑別処理部５２は、第１異常領域（図１５における異常領域１０２）が含む異常の種類を鑑別する。具体的には、第２鑑別処理部５２は、医療画像取得部１１が取得した医療画像のうち、第１照明光とはスペクトルが異なる第２照明光を使用して撮影した第２医療画像を用いて、各々の第１異常領域が含む異常の種類を特定する第２鑑別処理を行う。本実施形態において、「第１照明光とはスペクトルが異なる第２照明光」とは、パターン２の鑑別用照明光であり、かつ、図１６に示すように、第２医療画像は第２内視鏡画像６３である。第２鑑別処理部５２は、少なくとも、第１異常領域に対応する「第２医療画像に含まれる第２異常領域」に対して第２鑑別処理を行うことで、第１異常領域が含む異常の種類を特定する。第２異常領域とは、第２内視鏡画像６３（第２医療画像）における異常領域１０２である。第２異常領域（図１６の異常領域１０２）は、被写体中の位置その他の特徴等が第１異常領域に対応する。なお、第２鑑別処理の対象に第２異常領域が含まれていれば良いので、第２鑑別処理部５２は、例えば、第２異常領域を位置等を特定せずに、第２内視鏡画像６３の全体に対して第２鑑別処理を行って第１異常領域が含む異常の種類を特定できる。 The second discrimination processing unit 52 discriminates the type of abnormality included in the first abnormal area (the abnormal area 102 in FIG. 15). Specifically, in the medical image acquired by the medical image acquisition unit 11, the second discrimination processing unit 52 captures a second medical image captured using a second illumination light having a spectrum different from that of the first illumination light. A second discrimination process is performed to identify the type of abnormality included in each first abnormality area. In the present embodiment, the “second illumination light having a spectrum different from that of the first illumination light” is the illumination light for discrimination of pattern 2 and, as shown in FIG. It is an endoscopic image 63. The second discrimination processing unit 52 performs the second discrimination processing on at least the “second abnormal area included in the second medical image” corresponding to the first abnormal area, whereby the abnormality included in the first abnormal area is Identify the type. The second abnormal area is the abnormal area 102 in the second endoscopic image 63 (second medical image). The second abnormal area (abnormal area 102 in FIG. 16) corresponds to the first abnormal area in the position and the like in the subject. In addition, since it is sufficient that the target of the second discrimination processing includes the second abnormal area, for example, the second discrimination processing unit 52 does not specify the position or the like of the second abnormal area, and the second endoscope The second discrimination process can be performed on the entire image 63 to identify the type of abnormality included in the first abnormal area.
　第２鑑別処理部５２は、鑑別対象とする「異常の種類」の数に応じて１または複数の種類鑑別部を備える。種類鑑別部は、異常領域１０２が含む異常が特定の病変か否かを鑑別する。本実施形態においては、図１７に示すように、第２鑑別処理部５２は、第１種類鑑別部７１、第２種類鑑別部７２、第３種類鑑別部７３、及び、その他の種類鑑別部（図示しない）を備える。第１種類鑑別部７１は、第１鑑別処理において検出した異常領域１０２（複数の異常領域１０２を検出した場合にはそれらのうちの特定の異常領域１０２である。以下、同じ。）が含む異常が「ポリープ」か否かを鑑別する。第２種類鑑別部７２は、第１鑑別処理において検出した異常領域１０２が含む異常が「潰瘍性大腸炎」か否かを鑑別する。第３種類鑑別部７３は、第１鑑別処理において検出した異常領域１０２が含む異常が「クローン病」か否かを鑑別する。その他の種類鑑別部も同様に、異常領域１０２が含む異常が特定の病変であるか否かを鑑別する。 The second discrimination processing unit 52 includes one or more type discrimination units according to the number of “types of abnormality” to be discriminated. The type identification unit identifies whether the abnormality included in the abnormal area 102 is a specific lesion. In the present embodiment, as shown in FIG. 17, the second discrimination processing unit 52 includes a first type discrimination unit 71, a second type discrimination unit 72, a third type discrimination unit 73, and other type discrimination units ( Not shown). The first type discrimination unit 71 is an abnormality included in the abnormal area 102 detected in the first identification process (in the case where a plurality of abnormal areas 102 are detected, the abnormal area 102 is a specific abnormal area 102 among them. The same applies hereinafter). To determine if it is a "polyp". The second type identification unit 72 identifies whether the abnormality included in the abnormal area 102 detected in the first identification process is “ulcerative colitis”. The third type discrimination unit 73 discriminates whether or not the abnormality included in the abnormal area 102 detected in the first discrimination process is "Crohn's disease". Similarly, the other type identification unit identifies whether the abnormality included in the abnormal area 102 is a specific lesion.
　第２鑑別処理の結果は、少なくとも異常領域１０２が含む異常の種類を示す情報（「ポリープ」、「潰瘍性大腸炎」、または、「クローン病」等）を含む。なお、第２鑑別処理の結果は、必ずしも異常の種類を１つに確定的に特定するものではなく、「潰瘍性大腸炎である確率４０％、かつ、クローン病である確率４０％」というように、各々の種類鑑別部における鑑別結果の確からしさを表す確度（確率）と合わせて、もっともらしい異常の種類を絞り込み得る情報である。したがって、第２鑑別処理において「異常の種類を特定する」とは、異常の種類を絞り込み得る情報を得ることをいう。 The result of the second discrimination process includes information ("polyp", "ulcerative colitis", "Crohn's disease", etc.) indicating at least the type of abnormality included in the abnormal area 102. In addition, the result of the second discrimination process does not necessarily identify the type of abnormality definitely as one, and says "40% probability that it is ulcerative colitis and 40% probability that it is Crohn's disease" In addition, it is the information which can narrow down the kind of plausible abnormality together with the probability (probability) showing the certainty of the discrimination result in each kind discrimination part. Therefore, “specifying the type of abnormality” in the second discrimination process means obtaining information that can narrow down the type of abnormality.
　第３鑑別処理部５３は、第１異常領域（図１５における異常領域１０２）が含む異常の進行度を鑑別する。具体的には、第３鑑別処理部５３は、医療画像取得部１１が取得した医療画像のうち、第１照明光及び第２照明光とはスペクトルが異なる第３照明光を使用して撮影した第３医療画像を用いて、異常領域１０２が含む異常の進行度を特定する第３鑑別処理を行う。本実施形態において、「第１照明光及び第２照明光とはスペクトルが異なる第３照明光」とはパターン３からパターン９のいずれかの鑑別用照明光であり、かつ、図１８に示すように、第３医療画像は第３内視鏡画像６６である。また、第３鑑別処理部５３は、第１異常領域または第２異常領域の少なくとも一方に対応する「第３医療画像に含まれる第３異常領域」に対して第３鑑別処理を行うことで、第１異常領域が含む異常の進行度を特定する。第３異常領域とは、第３内視鏡画像６６（第３医療画像）における異常領域１０２である。第３異常領域（図１８の異常領域１０２）は、被写体中の位置その他の特徴等が第１異常領域または第２異常領域に対応する。なお、第３鑑別処理の対象に第３異常領域が含まれていれば良いので、第３鑑別処理部５３は、例えば、第３異常領域を位置等を特定せずに、第３内視鏡画像６６の全体に対して第３鑑別処理を行って第１異常領域が含む異常の種類を特定できる。 The third discrimination processing unit 53 discriminates the degree of progression of the abnormality included in the first abnormal area (the abnormal area 102 in FIG. 15). Specifically, in the medical image acquired by the medical image acquisition unit 11, the third discrimination processing unit 53 is photographed using the third illumination light having a spectrum different from that of the first illumination light and the second illumination light. A third discrimination process is performed to specify the degree of progression of the abnormality included in the abnormal area 102 using the third medical image. In the present embodiment, the “third illumination light having a different spectrum from the first illumination light and the second illumination light” is any of the discrimination illumination light of the patterns 3 to 9, and as shown in FIG. The third medical image is the third endoscopic image 66. Further, the third discrimination processing unit 53 performs the third discrimination processing on the “third abnormal area included in the third medical image” corresponding to at least one of the first abnormal area or the second abnormal area. Identify the degree of progression of the anomaly included in the first anomaly region. The third abnormal area is the abnormal area 102 in the third endoscopic image 66 (third medical image). The third abnormal area (abnormal area 102 in FIG. 18) corresponds to the first abnormal area or the second abnormal area in the position and the like in the subject. The third discrimination processing unit 53 may, for example, determine the position of the third abnormal area, for example, without specifying the position of the third abnormal area. The third discrimination process can be performed on the entire image 66 to identify the type of abnormality included in the first abnormal area.
　第３鑑別処理部５３は、鑑別対象とする「異常の種類」の数に応じて１または複数の進行度鑑別部を備える。進行度鑑別部は、特定種類の異常について、その進行度を鑑別する。本実施形態においては、図１９に示すように、第３鑑別処理部５３は、第１進行度鑑別部８１、第２進行度鑑別部８２、第３進行度鑑別部８３、及び、その他の進行度鑑別部（図示しない）を備える。第１進行度鑑別部８１は、ポリープの進行度を鑑別する。第２進行度鑑別部８２は、潰瘍性大腸炎の進行度を鑑別する。第３進行度鑑別部８３は、クローン病の進行度を鑑別する。その他の進行度鑑別部も同様である。 The third discrimination processing unit 53 includes one or more progress degree discrimination units in accordance with the number of “types of abnormality” to be discriminated. The progress discrimination unit discriminates the progress of a specific type of abnormality. In the present embodiment, as shown in FIG. 19, the third discrimination processing unit 53 includes a first progression discrimination unit 81, a second progression discrimination unit 82, a third progression discrimination unit 83, and other progressions. A degree discrimination unit (not shown) is provided. The first progression discrimination unit 81 discriminates the progression of the polyp. The second progression discrimination unit 82 discriminates the progression of ulcerative colitis. The third progression discrimination unit 83 discriminates the progression degree of Crohn's disease. The same applies to the other progress discrimination units.
　第３鑑別処理の結果は、病変等の進行度である。医療画像が内視鏡画像である場合、進行度はいわゆる内視鏡所見分類にしたがって鑑別する。ポリープ（癌を含む）を対象病変とする場合の内視鏡所見分類には、例えば、ＮＩＣＥ（The Narrow-band imaging International Colorectal Endoscopic）分類、またはＪＮＥＴ(The Japan NBI(Narrow Band Imaging) Expert Team)分類等がある。本実施形態においては、第３鑑別処理においてポリープの進行度を鑑別する場合、ＮＩＣＥ分類にしたがって、「ＮＩＣＥ　Ｔｙｐｅ１」、「ＮＩＣＥ　Ｔｙｐｅ２」、または、「ＮＩＣＥ　Ｔｙｐｅ３」に分類する。「ＮＩＣＥ　Ｔｙｐｅ１」は過形成病変を表し、「ＮＩＣＥ　Ｔｙｐｅ２」は腺腫（アデノーマ）から粘膜内癌（いわゆるＭ癌）を表し、かつ、「ＮＩＣＥ　Ｔｙｐｅ３」は粘膜下層浸潤癌（いわゆるＳＭ癌）を表す。 The result of the third discrimination process is the degree of progression of a lesion or the like. When the medical image is an endoscopic image, the degree of progression is discriminated according to a so-called endoscopic findings classification. Endoscopic classification when targeting polyps (including cancer) is, for example, NICE (The Narrow-band imaging International Colorectal Endoscopic) classification, or JNET (The Japan NBI (Narrow Band Imaging) Expert Team) classification. There are classification etc. In the present embodiment, when differentiating the degree of progression of polyps in the third discrimination process, classification is made into “NICE Type 1”, “NICE Type 2”, or “NICE Type 3” according to the NICE classification. “NICE Type 1” represents hyperplastic lesion, “NICE Type 2” represents adenoma (adenoma) to intramucosal cancer (so-called M cancer), and “NICE Type 3” represents submucosal invasion cancer (so-called SM cancer) .
　潰瘍性大腸炎の内視鏡所見分類には、例えば、Ｍａｙｏ分類、Ｍａｔｔｓ分類、ＵＣＥＩＳ（Ulcerative Colitis Endoscopic. Index of Severity）分類等である。これら内視鏡所見分類のうち、本実施形態においては、潰瘍性大腸炎の進行度をＭａｙｏ分類にしたがって分類する。Ｍａｙｏ分類にはＭａｙｏ０（グレード０）、Ｍａｙｏ１（グレード１）、Ｍａｙｏ２（グレード２）、及び、Ｍａｙｏ３（グレード３）の４段階のグレードがある。Ｍａｙｏ０は、正常または非活動性（寛解期を含む）を表すグレードである。Ｍａｙｏ１は、軽症を表すグレードであり、一般に、発赤、血管像不明瞭、または、軽度の易出血性が認められる状態である。Ｍａｙｏ２は、中等症を表すグレードであり、一般に、顕著な発赤、血管像の消失、易出血性、膿性分泌物の付着、粘膜粗造、糜爛、または、部分的な潰瘍等が認められる状態である。Ｍａｙｏ３は重症（活動期）を表すグレードであり、一般に、明らかな自然出血、浮腫、潰瘍（広範な潰瘍を含む）等が認められる状態である。また、第３鑑別処理においては、潰瘍性大腸炎にともなう異形成（dysplasia）を鑑別する。 The endoscopic findings classification of ulcerative colitis includes, for example, Mayo classification, Matts classification, UCEIS (Ulcerative Colitis Endoscopic. Index of Severity) classification, and the like. Among these endoscopic findings classifications, in the present embodiment, the degree of progression of ulcerative colitis is classified according to the Mayo classification. The Mayo classification has four grades of Mayo 0 (grade 0), Mayo 1 (grade 1), Mayo 2 (grade 2), and Mayo 3 (grade 3). Mayo0 is a grade that represents normal or inactive (including remission). Mayo 1 is a grade that indicates mildness, and is generally in a state in which redness, blood vessel image obscurity, or mild bleeding tendency is observed. Mayo 2 is a grade that represents moderate disease, and in general, conditions such as marked redness, disappearance of angiogram, hemorrhage, adherence of purulent secretions, mucous membrane prostheses, wrinkles, or partial ulcers etc. It is. Mayo 3 is a grade representing severe (active stage), and in general, it is a state in which obvious spontaneous bleeding, edema, ulcer (including extensive ulcer) and the like are recognized. In the third differential treatment, dysplasia associated with ulcerative colitis is differentiated.
　クローン病の内視鏡所見分類には、例えばＳＥＳＣＤ（Simple Endoscopic Score for Crohn's Disease）等がある。本実施形態においては、クローン病の進行度をＳＥＳＣＤにしたがって、「ＳＥＳＣＤ　０」、「ＳＥＳＣＤ　１」、「ＳＥＳＣＤ　２」、または「ＳＥＳＣＤ　３」に分類する。 The endoscopic findings classification of Crohn's disease includes, for example, SESCD (Simple Endoscopic Score for Crohn's Disease). In this embodiment, the degree of progression of Crohn's disease is classified into "SESCD 0", "SESCD 1", "SESCD 2", or "SESCD 3" according to SESCD.
　第２鑑別処理の結果が、病変の種類を複数に絞り込んだ結果である場合、第３鑑別処理においては、各種類の病変についてそれぞれ進行度を鑑別し、１または複数の病変についての進行度を第３鑑別処理の結果として出力する。例えば、第２鑑別処理の結果が「潰瘍性大腸炎である確率４０％、かつ、クローン病である確率４０％」である場合、第３鑑別処理においては、潰瘍性大腸炎の進行度と、クローン病の進行度と、を鑑別する。そして、第２鑑別処理において絞り込んだ各病変の進行度が、例えば、「潰瘍性大腸炎である場合Ｍａｙｏ１である確率が２０％」かつ「クローン病である場合、ＳＥＳＣＤ１である確率が９５％」であれば、これらの結果のうち、後者のクローン病に係る結果を第３鑑別処理の結果として出力する。 If the result of the second discrimination process is a result of narrowing down the types of lesions, in the third discrimination process, the degree of progression for each type of lesion is differentiated, and the degree of progression for one or more lesions is Output as the result of the third discrimination process. For example, when the result of the second discrimination process is "probability 40% for ulcerative colitis and 40% probability for Crohn's disease", the degree of progression of ulcerative colitis in the third discrimination process, Differentiate the degree of progression of Crohn's disease. Then, for example, the degree of progression of each lesion narrowed down in the second differentiation process is "20% of the probability that Mayo 1 is ulcerative colitis" and "95% of the probability that SESCD 1 is Crohn's disease" Among these results, the result relating to the latter Crohn's disease is output as the result of the third discrimination process.
　なお、第３鑑別処理部５３は、第２鑑別処理の結果を用いて１または複数の第３医療画像を選択する。また、第３鑑別処理部５３は、第２鑑別処理の結果と対応付けられた第３照明光のスペクトルで取得された第３医療画像を選択する。例えば、第２鑑別処理の結果が「ポリープ」を含む場合、パターン６の鑑別用照明光を用いて撮影した内視鏡画像を第３内視鏡画像６６として選択及び取得する。同様に、第２鑑別処理の結果が「潰瘍性大腸炎」を含む場合、パターン３の鑑別用照明光を用いて撮影した内視鏡画像を第３内視鏡画像６６として選択及び取得し、かつ、第２鑑別処理の結果が「クローン病」を含む場合、パターン４の鑑別用照明光を用いて撮影した内視鏡画像を第３内視鏡画像６６として選択及び取得する。 The third discrimination processing unit 53 selects one or more third medical images using the result of the second discrimination processing. Further, the third discrimination processing unit 53 selects the third medical image acquired in the spectrum of the third illumination light associated with the result of the second discrimination processing. For example, when the result of the second discrimination process includes “polyp”, an endoscopic image captured using the discrimination illumination light of pattern 6 is selected and acquired as the third endoscopic image 66. Similarly, when the result of the second discrimination process includes “ulcerative colitis”, an endoscopic image taken using the illumination light for discrimination of pattern 3 is selected and acquired as a third endoscopic image 66, And, when the result of the second discrimination processing includes “Crohn's disease”, an endoscopic image captured using the discrimination illumination light of pattern 4 is selected and acquired as a third endoscopic image 66.
　医療画像取得部１１は、第２鑑別処理部５２及び第３鑑別処理部５３が要求する可能性がある医療画像を予め取得することができる。また、医療画像取得部１１は、第２鑑別処理部５２または第３鑑別処理部５３が要求した医療画像を未取得である場合、第２鑑別処理部５２または第３鑑別処理部５３の要求にしたがって、第２鑑別処理または第３鑑別処理に使用する医療画像を取得することができる。 The medical image acquisition part 11 can acquire the medical image which the 2nd discrimination process part 52 and the 3rd discrimination process part 53 may request | require beforehand. Further, when the medical image acquired by the second discrimination processing unit 52 or the third discrimination processing unit 53 is not acquired, the medical image acquisition unit 11 requests the second discrimination processing unit 52 or the third discrimination processing unit 53. Therefore, the medical image used for the 2nd distinction processing or the 3rd distinction processing can be acquired.
　また、第１鑑別処理、第２鑑別処理、及び第３鑑別処理は、表示部１３に観察用医療画像を表示しつつ、そのバックグラウンドで実施する。すなわち、観察用医療画像（本実施形態においては観察用内視鏡画像１０１）を表示部１３に表示している間に、第１鑑別処理部５１は第１鑑別処理をし、第２鑑別処理部５２は第２鑑別処理をし、かつ、第３鑑別処理部５３は第３鑑別処理をする。本実施形態においては、医療画像取得部１１は、第１医療画像、第２医療画像、及び、第３医療画像の他に、観察用医療画像を取得するが、医療画像取得部１１が、第１医療画像、第２医療画像、及び、第３医療画像のうちの何れかを観察用医療画像に設定する場合（第１医療画像、第２医療画像、または第３医療画像を観察用医療画像としても利用する場合）も同様である。なお、表示制御部１５は、第１鑑別処理、第２鑑別処理、または第３鑑別処理を行っている途中で、表示部１３に表示する観察用内視鏡画像１０１を適宜更新できる。 Further, the first discrimination process, the second discrimination process, and the third discrimination process are performed in the background while displaying the medical image for observation on the display unit 13. That is, while the medical image for observation (in the present embodiment, the endoscopic image for observation 101) is displayed on the display unit 13, the first discrimination processing unit 51 performs the first discrimination processing, and the second discrimination processing The part 52 performs a second discrimination process, and the third discrimination processing unit 53 performs a third discrimination process. In the present embodiment, the medical image acquisition unit 11 acquires a medical image for observation other than the first medical image, the second medical image, and the third medical image, but the medical image acquisition unit 11 When one of the first medical image, the second medical image, and the third medical image is set as the medical image for observation (the first medical image, the second medical image, or the third medical image for medical observation And also when it is used. The display control unit 15 can appropriately update the observation endoscope image 101 displayed on the display unit 13 while performing the first discrimination process, the second discrimination process, or the third discrimination process.
　設定部５６は、第２鑑別処理において特定する異常の種類（鑑別対象）、または、第３鑑別処理において特定する進行度の分類（鑑別内容）の設定を記憶し、かつ、変更することができる。例えば、設定部５６は、図２０に示す設定変更用メニューウィンドウを表示部１３に表示する。医師等がマウス等を用いてチェックボックス９１にチェック（「レ」）を入れることにより、該当する鑑別対象及び鑑別内容を有効化することができる。図１７においては、鑑別対象として「ポリープ」と「潰瘍性大腸炎」を有効化し、ポリープについては「ＮＩＣＥ　Ｔｙｐｅ１」、「ＮＩＣＥ　Ｔｙｐｅ２」、及び、「ＮＩＣＥ　Ｔｙｐｅ３」を有効化しており、かつ、潰瘍性大腸炎については、「Ｍａｙｏ０」、「Ｍａｙｏ１」、及び、「Ｍａｙｏ２」を有効化している。この設定の場合、第２鑑別処理部５２は、異常領域１０２が含む異常がポリープであるか否か、及び、潰瘍性大腸炎であるか否かを鑑別する。また、第３鑑別処理部５３は、異常領域１０２が含む異常がポリープである場合に、その進行度を、「ＮＩＣＥ　Ｔｙｐｅ１」、「ＮＩＣＥ　Ｔｙｐｅ２」、または、「ＮＩＣＥ　Ｔｙｐｅ３」に鑑別する。同様に、第３鑑別処理部５３は、異常領域１０２が含む異常が潰瘍性大腸炎である場合に、その進行度を、「Ｍａｙｏ０」、「Ｍａｙｏ１」、または、「Ｍａｙｏ２」に鑑別する。 The setting unit 56 can store and change the setting of the type of abnormality (discrimination target) identified in the second discrimination processing or the classification (discrimination content) of the progress degree identified in the third discrimination processing. . For example, the setting unit 56 causes the display unit 13 to display a setting change menu window shown in FIG. When a doctor or the like puts a check (“RE”) in the check box 91 using a mouse or the like, the corresponding discrimination target and the discrimination content can be validated. In FIG. 17, “polyp” and “ulcerative colitis” are activated as discrimination targets, and “NICE Type 1”, “NICE Type 2”, and “NICE Type 3” are activated for polyps, and ulcers are detected. For sexually transmitted colitis, "Mayo 0", "Mayo 1" and "Mayo 2" are activated. In this setting, the second discrimination processing unit 52 discriminates whether the abnormality included in the abnormal area 102 is a polyp and whether it is ulcerative colitis. Further, when the abnormality included in the abnormal area 102 is a polyp, the third discrimination processing unit 53 discriminates the progress degree of the abnormality into “NICE Type 1”, “NICE Type 2”, or “NICE Type 3”. Similarly, when the abnormality included in the abnormal area 102 is ulcerative colitis, the third discrimination processing unit 53 discriminates the progress degree to “Mayo 0”, “Mayo 1”, or “Mayo 2”.
　なお、第２鑑別処理において特定する異常の種類（鑑別対象）、または、第３鑑別処理において特定する進行度の分類（鑑別内容）を設定し、もしくはこれら設定の変更をする代わりに、設定部５６は、第１照明光、第２照明光、または、第３照明光の各スペクトルもしくは組み合わせの設定をし、もしくはこれらの設定を変更することができる。第２鑑別処理において特定する異常の種類（鑑別対象）、または、第３鑑別処理において特定する進行度の分類（鑑別内容）を設定することと、第１照明光、第２照明光、または、第３照明光の各スペクトルもしくは組み合わせの設定をすることは、第１鑑別処理、第２鑑別処理、及び、第３鑑別処理に関して実質的に同じ設定の効果を発揮する。 In addition, instead of setting the classification (discrimination content) of the type of abnormality (discrimination target) to specify in the second discrimination processing or the progress degree to specify in the third discrimination processing, or instead of changing these settings, the setting unit 56 can set or change each spectrum or combination of the first illumination light, the second illumination light, or the third illumination light. Setting the type of abnormality (differentiation target) to be identified in the second discrimination process, or the classification (discrimination content) of the progress degree to be identified in the third discrimination process, and the first illumination light, the second illumination light, or Setting each spectrum or combination of the third illumination light exerts substantially the same setting effect with respect to the first discrimination process, the second discrimination process, and the third discrimination process.
　表示部１３は、医療画像取得部１１が取得した医療画像を表示するディスプレイである。表示部１３は、少なくとも観察用医療画像を表示する。また、表示部１３は、第１鑑別処理の結果、第２鑑別処理の結果、及び、第３鑑別処理の結果のうち１または複数を表示することができる。医療画像処理装置１０が接続するデバイス等が含むモニタまたはディスプレイを共用し、医療画像処理装置１０の表示部１３として使用できる。 The display unit 13 is a display that displays the medical image acquired by the medical image acquisition unit 11. The display unit 13 displays at least a medical image for observation. In addition, the display unit 13 can display one or more of the result of the first discrimination process, the result of the second discrimination process, and the result of the third discrimination process. A monitor or display included in a device or the like connected to the medical image processing apparatus 10 can be shared and used as the display unit 13 of the medical image processing apparatus 10.
　表示制御部１５は、表示部１３における観察用医療画像等の表示態様を制御する。本実施形態においては、第１鑑別処理部５１が検出した異常領域１０２（第１異常領域）を観察用内視鏡画像１０１に重畳して表示する。また、表示制御部１５は、異常領域１０２が含む異常の種類、及び、異常領域１０２が含む異常の進行度を表す文字（文字列もしくはメッセージ）等を表示部１３に表示する。なお、設定によっては、表示制御部１５は、音（音声を含む）、光（観察用内視鏡画像１０１の部分的な点滅等）、座標の表示等、その他の任意の方法で、異常領域１０２の位置、異常領域１０２が含む異常の種類、及び、異常領域１０２が含む異常の進行度を示すことができる。 The display control unit 15 controls the display mode of the medical image for observation or the like on the display unit 13. In the present embodiment, the abnormal area 102 (first abnormal area) detected by the first discrimination processing unit 51 is superimposed on the observation endoscope image 101 and displayed. Further, the display control unit 15 displays on the display unit 13 the type of abnormality included in the abnormal area 102, characters (character string or message) indicating the progress of abnormality included in the abnormal area 102, and the like. Depending on the setting, the display control unit 15 may use the sound (including sound), light (partial blinking of the observation endoscope image 101, etc.), display of coordinates, or any other appropriate method, such as an abnormal area. The position of 102, the type of abnormality included in the abnormal area 102, and the degree of progression of abnormality included in the abnormal area 102 can be indicated.
　入力受信部１６は、医療画像処理装置１０に接続するマウス、キーボード、その他操作デバイスからの入力を受け付ける。医療画像処理装置１０の各部の動作はこれらの操作デバイスを用いて制御できる。 The input reception unit 16 receives input from a mouse, a keyboard, and other operation devices connected to the medical image processing apparatus 10. The operation of each part of the medical image processing apparatus 10 can be controlled using these operation devices.
　統括制御部１７は、医療画像処理装置１０の各部の動作を統括的に制御する。入力受信部１６が操作デバイスを用いた操作入力を受信した場合には、統括制御部１７は、その操作入力にしたがって医療画像処理装置１０の各部を制御する。 The integrated control unit 17 integrally controls the operation of each unit of the medical image processing apparatus 10. When the input reception unit 16 receives an operation input using the operation device, the overall control unit 17 controls each unit of the medical image processing apparatus 10 according to the operation input.
　保存部１８は、医療画像処理装置１０が含むメモリ等の記憶デバイス（図示しない）、または、内視鏡装置２１等の医療装置もしくはＰＡＣＳ２２が含む記憶デバイス（図示しない）に、必要に応じて、異常領域１０２の位置、異常領域１０２が含む異常の種類、または、異常領域１０２が含む異常の進行度等を保存する。 The storage unit 18 is a storage device (not shown) such as a memory included in the medical image processing apparatus 10 or a medical device such as the endoscope apparatus 21 or a storage device (not shown) included in the PACS 22 as needed. The position of the abnormal area 102, the type of abnormality included in the abnormal area 102, the degree of progress of abnormality included in the abnormal area 102, and the like are stored.
　以下、医療画像処理装置１０の動作の流れを説明する。図２１に示すように、医療画像取得部１１は、観察用医療画像である観察用内視鏡画像１０１を適宜取得し（ステップＳ１１０）、かつ、表示制御部１５は観察用内視鏡画像１０１を表示部１３に適宜表示する（ステップＳ１１１）。こうして表示部１３に観察用内視鏡画像１０１を表示する処理のバックグラウンドにおいては、医療画像取得部１１が第1鑑別処理用の医療画像である第１内視鏡画像６１を取得し（ステップＳ１１２）、かつ、第1鑑別処理部５１が第１内視鏡画像６１を用いて異常領域１０２の有無を鑑別する第１鑑別処理を実行する（ステップＳ１１３）。 The flow of the operation of the medical image processing apparatus 10 will be described below. As shown in FIG. 21, the medical image acquisition unit 11 appropriately acquires the observation endoscopic image 101 which is a medical image for observation (step S110), and the display control unit 15 acquires the endoscopic image 101 for observation. Are appropriately displayed on the display unit 13 (step S111). Thus, in the background of the process of displaying the endoscopic image 101 for observation on the display unit 13, the medical image acquisition unit 11 acquires the first endoscopic image 61, which is a medical image for the first discrimination process (step In step S112, the first discrimination processing unit 51 executes the first discrimination process of discriminating the presence or absence of the abnormal area 102 using the first endoscopic image 61 (step S113).
　第１鑑別処理において異常領域１０２を検出すると、医療画像取得部１１は第２鑑別処理用の医療画像である第２内視鏡画像６３を取得し（ステップＳ１１４）、かつ、第２鑑別処理部５２が第２内視鏡画像６３を用いて異常領域１０２が含む異常の種類を鑑別する第２鑑別処理を実行する（ステップＳ１１５）。その後、医療画像取得部１１は第３鑑別処理用の医療画像である第３内視鏡画像６６を取得し（ステップＳ１１６）、かつ、第３鑑別処理部５３が第３内視鏡画像６６を用いて異常領域１０２が含む異常の進行度を鑑別する第３鑑別処理を実行する（ステップＳ１１７）。 When the abnormal area 102 is detected in the first discrimination process, the medical image acquisition unit 11 acquires the second endoscopic image 63 which is a medical image for the second discrimination process (step S114), and the second discrimination processing unit A second discrimination process is performed to discriminate the type of abnormality included in the abnormal area 102 using the second endoscopic image 63 (step S115). Thereafter, the medical image acquisition unit 11 acquires the third endoscopic image 66 which is a medical image for the third discrimination process (step S116), and the third discrimination processing unit 53 obtains the third endoscopic image 66. A third discrimination process of discriminating the degree of progression of the abnormality included in the abnormal area 102 is executed (step S117).
　こうして第１鑑別処理、第２鑑別処理、及び第３鑑別処理を実行すると、表示制御部１５は、表示部１３にこれらの結果を表示する（ステップＳ１１８）。例えば、図２２に示すように、表示制御部１５は、観察用内視鏡画像１０１において異常領域１０２の輪郭を示す等して異常領域１０２の位置を表示する。また、表示制御部１５は、第２鑑別処理の結果を示すための特定の表示欄１０３に異常領域１０２が含む異常が例えば「潰瘍性大腸炎」であることを表示し、かつ、第３鑑別処理の結果を示すための特定の表示欄１０４に、進行度が例えば「Ｍａｙｏ１」であることを表示する。 When the first discrimination process, the second discrimination process, and the third discrimination process are thus performed, the display control unit 15 displays these results on the display unit 13 (step S118). For example, as shown in FIG. 22, the display control unit 15 displays the position of the abnormal area 102 by indicating the outline of the abnormal area 102 in the observation endoscope image 101 or the like. Further, the display control unit 15 displays that the abnormality included in the abnormal area 102 is, for example, “ulcerative colitis” in the specific display column 103 for indicating the result of the second discrimination processing, and the third discrimination In the specific display field 104 for indicating the result of the process, it is displayed that the progress degree is, for example, "Mayo 1".
　上記のように、医療画像処理装置１０は、異常領域１０２を検出し、検出した異常領域１０２が含む異常の種類及び進行度を鑑別する際に、これら各々の鑑別に適した照明光で撮影した医療画像を使用している。具体的には、第１鑑別処理においては、異常領域１０２の有無の鑑別に適した第１内視鏡画像６１を使用し、第２鑑別処理においては異常領域１０２が含む異常の種類の鑑別に適した第２内視鏡画像６３を使用し、かつ、第３鑑別処理においては進行度の鑑別に適した第３内視鏡画像６６を使用する。このため、医療画像処理装置１０は、異常領域１０２の位置に加え、さらに、異常領域１０２が含む異常の種類、及び、異常領域１０２が含む異常の進行度についての正確な情報を提供できる。すなわち、医療画像処理装置１０は、病変等について従来よりも詳細な情報を提供して、診断等をより効果的に支援することができる。 As described above, when the medical image processing apparatus 10 detects the abnormal area 102 and discriminates the type and the degree of progress of the abnormality included in the detected abnormal area 102, the medical image processing apparatus 10 captures an image with illumination light suitable for each of the discrimination. I use medical images. Specifically, in the first discrimination process, the first endoscopic image 61 suitable for discrimination of the presence or absence of the abnormal area 102 is used, and in the second discrimination process, for discrimination of the type of abnormality included in the abnormal area 102 A suitable second endoscopic image 63 is used, and a third endoscopic image 66 suitable for differentiation of the degree of progression is used in the third discrimination process. Therefore, in addition to the position of the abnormal area 102, the medical image processing apparatus 10 can further provide the type of abnormality included in the abnormal area 102 and accurate information on the progression of the abnormality included in the abnormal area 102. That is, the medical image processing apparatus 10 can provide more detailed information on lesions and the like than in the past, and can support diagnosis and the like more effectively.
　なお、第１実施形態における第１鑑別処理部５１、第２鑑別処理部５２、及び、第３鑑別処理部５３は、機械学習またはディープラーニング等により学習した、いわゆるＡＩ（Artificial Intelligence）プログラムを用いて構成することができる。 The first discrimination processing unit 51, the second discrimination processing unit 52, and the third discrimination processing unit 53 in the first embodiment use a so-called AI (Artificial Intelligence) program learned by machine learning or deep learning. Can be configured.
　なお、第２鑑別処理において、異常の種類を複数の種類に絞り込んだ場合、医療画像取得部１１は、各々の異常の種類について、それぞれ第３鑑別処理に適した第３内視鏡画像６６を取得し、かつ、第３鑑別処理部５３は、各種類の異常の進行度を鑑別する。例えば、第２鑑別処理において「潰瘍性大腸炎である確率４０％、かつ、クローン病である確率４０％」と特定した場合、医療画像取得部１１は、潰瘍性大腸炎の進行度の鑑別に必要な第３内視鏡画像６６と、クローン病の進行度の鑑別に必要な第３内視鏡画像６６を取得し、かつ、第３鑑別処理部５３は各第３内視鏡画像６６を用いて、潰瘍性大腸炎の進行度（異常の種類が潰瘍性大腸炎であるとした場合の進行度）と、クローン病の進行度（異常の種類がクローン病であるとした場合の進行度）と、を特定する。 In the second discrimination process, when the types of abnormalities are narrowed down to a plurality of types, the medical image acquiring unit 11 respectively obtains the third endoscopic image 66 suitable for the third discrimination process for each type of abnormality. The third discrimination processing unit 53 acquires and discriminates the degree of progress of each type of abnormality. For example, when it is specified that “probability 40% is ulcerative colitis and probability 40% is Crohn's disease” in the second discrimination processing, medical image acquisition unit 11 discriminates the progression degree of ulcerative colitis. The third endoscopic image 66 required and the third endoscopic image 66 necessary for discrimination of the degree of progression of Crohn's disease are obtained, and the third discrimination processing unit 53 calculates each third endoscopic image 66 The degree of progression of ulcerative colitis (the degree of progression when the type of abnormality is ulcerative colitis) and the degree of progression when Crohn's disease is the type of abnormality ) And.
　また、第２鑑別処理において異常の種類を複数の種類に絞り込み、かつ、第３鑑別処理において各々の進行度を特定した場合、表示制御部１５は、少なくとも、最も確度が高い鑑別結果を表示する。例えば、第２鑑別処理において「潰瘍性大腸炎である確率４０％、かつ、クローン病である確率４０％」と特定し、第３鑑別処理において「潰瘍性大腸炎の進行度がＭａｙｏ１である確率２０％」、かつ、「クローン病の進行度がＳＥＳＣＤ１である確率９５％」と特定した場合、表示制御部１５は、少なくとも、異常の種類「クローン病」及び進行度「ＳＥＳＣＥ１」を表示する。 In addition, when the types of abnormalities are narrowed down to a plurality of types in the second discrimination process, and each progress degree is specified in the third discrimination process, the display control unit 15 displays at least the discrimination result with the highest accuracy. . For example, in the second differentiation process, it is specified as “probability 40% for ulcerative colitis and 40% probability for Crohn's disease”, and in the third differentiation process, “probability for progression of ulcerative colitis is Mayo 1 If it is specified that “20%” and “probability of progression of Crohn's disease is SESCD1 are 95%”, the display control unit 15 displays at least the type “Aberrant type“ Crohn's disease ”and the progression“ SESCE1 ”.
　図２３に示すように、医療画像解析処理部１２は、第１鑑別処理部５１、第２鑑別処理部５２、第３鑑別処理部５３、及び、設定部５６に加えて、カルテ取得部１２１を備えても良い。カルテ取得部１２１は、内視鏡装置２１等の医療装置、または、ＰＡＣＳ２２等から、検査対象である患者のカルテを取得する。カルテとは、患者に関して診療または検査の経過等を記録した情報であり、例えば、患者の氏名、性別及び年齢、病名、主要な症状、処方もしくは処置の内容、または、既往歴等の記録を含む。 As shown in FIG. 23, the medical image analysis processing unit 12 includes the chart acquisition unit 121 in addition to the first discrimination processing unit 51, the second discrimination processing unit 52, the third discrimination processing unit 53, and the setting unit 56. You may have. The chart acquisition unit 121 acquires the chart of the patient to be examined from the medical device such as the endoscope apparatus 21 or the PACS 22 or the like. A medical record is information that records the progress of medical treatment or examination about a patient, and includes, for example, the patient's name, sex and age, disease name, major symptoms, contents of prescription or treatment, or records of medical history etc. .
　上記のように、カルテ取得部１２１を備える場合、設定部５６は、カルテが含む情報を用いて、第２鑑別処理において特定する異常の種類（鑑別対象）、または、第３鑑別処理において特定する進行度の分類（鑑別内容）の設定をすることができる。例えば、設定部５６は、第２鑑別処理において特定する異常の種類に、カルテが含む情報によって定まる特定の病変を含めることができる。具体的には、潰瘍性大腸炎の既往歴があれば、潰瘍性大腸炎が検査の主な対象である主病変でなくても、設定部５６が、潰瘍性大腸炎を副病変として、鑑別対象に設定する等である。 As described above, when the medical record acquisition unit 121 is provided, the setting unit 56 specifies the type of abnormality (differentiation target) specified in the second discrimination process or the third discrimination process using information included in the medical chart. It is possible to set classification (differentiated content) of the degree of progress. For example, the setting unit 56 can include, in the type of abnormality identified in the second discrimination process, a specific lesion determined by the information included in the medical record. Specifically, if there is a history of ulcerative colitis, even if ulcerative colitis is not the main lesion that is the main target of the examination, setting unit 56 differentiates ulcerative colitis as a secondary lesion. It is set as an object.
　図２４に示すように、医療画像解析処理部１２は、第１鑑別処理部５１、第２鑑別処理部５２、第３鑑別処理部５３、及び、設定部５６に加えて、鑑別結果修正部１３１を備えても良い。鑑別結果修正部１３１は、医師等の入力受信部１６を用いた操作入力に基づいて、第１鑑別処理の結果、第２鑑別処理の結果、または、第３鑑別処理の結果を修正する。鑑別結果修正部１３１を設けておくことにより、第１鑑別処理、第２鑑別処理、または、第３鑑別処理における誤鑑別を修正できる。具体的には、医師等は、第１鑑別処理において検出した異常領域１０２の位置、大きさ、範囲、または、個数等を任意に修正することができる。また、第２鑑別処理において特定した異常の種類を任意に選択し直すことができ、または、第３鑑別処理において特定する進行度についても、医師等は任意に鑑別し直すことができる。 As shown in FIG. 24, in addition to the first discrimination processing unit 51, the second discrimination processing unit 52, the third discrimination processing unit 53, and the setting unit 56, the medical image analysis processing unit 12 has a discrimination result correction unit 131. May be provided. The discrimination result correction unit 131 corrects the result of the first discrimination process, the result of the second discrimination process, or the result of the third discrimination process based on the operation input using the input reception unit 16 such as a doctor. By providing the discrimination result correction unit 131, it is possible to correct erroneous discrimination in the first discrimination process, the second discrimination process, or the third discrimination process. Specifically, a doctor or the like can arbitrarily correct the position, size, range, number, etc., of the abnormal area 102 detected in the first discrimination process. Further, the type of the abnormality identified in the second discrimination process can be arbitrarily selected again, or the doctor or the like can arbitrarily discriminate the degree of progress specified in the third discrimination process.
　鑑別結果修正部１３１が第１鑑別処理の結果を修正した場合、第２鑑別処理部５２は修正後の第１鑑別処理の結果を反映して第２鑑別処理を実行し、かつ、第３鑑別処理部５３は、修正後の第１鑑別処理の結果を反映した第２鑑別処理の結果を反映して第３鑑別処理を実行する。鑑別結果修正部１３１が第１鑑別処理の結果を修正した際に、既に、第２鑑別処理、第３鑑別処理、またはこれらの両方が完了している場合、自動的にまたは医師等の操作入力等による指示に基づいて、第２鑑別処理部５２は修正後の第１鑑別処理の結果を反映して第２鑑別処理をやり直すことができ、かつ、第３鑑別処理部５３は、修正後の第１鑑別処理の結果を反映した第２鑑別処理の結果を反映して第３鑑別処理をやり直すことができる。 When the discrimination result correction unit 131 corrects the result of the first discrimination process, the second discrimination processing unit 52 executes the second discrimination process reflecting the result of the first discrimination process after correction, and the third discrimination The processing unit 53 executes the third discrimination process by reflecting the result of the second discrimination process that reflects the result of the first discrimination process after correction. When the discrimination result correction unit 131 corrects the result of the first discrimination process, if the second discrimination process, the third discrimination process, or both of them are already completed, the operation input by the doctor or the like automatically or automatically The second discrimination processing unit 52 can redo the second discrimination processing reflecting the result of the first discrimination processing after the correction based on the instruction by the etc., and the third discrimination processing unit 53 performs the correction after the modification. It is possible to redo the third discrimination process by reflecting the result of the second discrimination process reflecting the result of the first discrimination process.
　鑑別結果修正部１３１が第２鑑別処理の結果を修正した場合、第３鑑別処理部５３は、修正後の第２鑑別処理の結果を反映して第３鑑別処理を実行する。鑑別結果修正部１３１が第２鑑別処理の結果を修正した際に、既に、第３鑑別処理が完了している場合、自動的にまたは医師等の操作入力等による指示に基づいて、第３鑑別処理部５３は修正後の第２鑑別処理の結果を反映して第３鑑別処理をやり直すことができる。 When the discrimination result correction unit 131 corrects the result of the second discrimination process, the third discrimination processing unit 53 executes the third discrimination process, reflecting the result of the second discrimination process after the correction. When the discrimination result correction unit 131 corrects the result of the second discrimination process, if the third discrimination process is already completed, the third discrimination is automatically performed or based on an instruction by a doctor etc. The processing unit 53 can redo the third discrimination process by reflecting the result of the second discrimination process after the correction.
　図２５に示すように、医療画像解析処理部１２は、第１鑑別処理部５１、第２鑑別処理部５２、第３鑑別処理部５３、及び、設定部５６に加えて、鑑別結果報知部１４１を備えても良い。鑑別結果報知部１４１は、第１鑑別処理の結果、第２鑑別処理の結果、または、第３鑑別処理の結果を、任意のタイミングで報知する。上記第１実施形態においては、第３鑑別処理が完了したタイミングで、第１鑑別処理の結果、第２鑑別処理の結果、及び、第３鑑別処理の結果を表示部１３に表示することで報知しているが、鑑別結果報知部１４１は、例えば、第１鑑別処理の完了後、第１鑑別処理の結果をリアルタイムに報知し、第２鑑別処理の完了後、第２鑑別処理の結果をリアルタイムに報知する。鑑別結果報知部１４１は、表示制御部１５及び表示部１３を用いて上記第１実施形態と同様に各鑑別結果を表示できるほか、音（音声を含む）、光（観察用内視鏡画像１０１の部分的な点滅等）、座標の表示等、その他の任意の方法で、第１鑑別処理の結果、第２鑑別処理の結果、及び、第３鑑別処理の結果を報知できる。 As shown in FIG. 25, in addition to the first discrimination processing unit 51, the second discrimination processing unit 52, the third discrimination processing unit 53, and the setting unit 56, the medical image analysis processing unit 12 has a discrimination result notification unit 141. May be provided. The discrimination result notifying unit 141 reports the result of the first discrimination process, the result of the second discrimination process, or the result of the third discrimination process at an arbitrary timing. In the first embodiment, at the timing when the third discrimination process is completed, notification is made by displaying the result of the first discrimination process, the result of the second discrimination process, and the result of the third discrimination process on the display unit 13 Although the discrimination result notifying unit 141 reports the result of the first discrimination process in real time after the completion of the first discrimination process, for example, the result of the second discrimination process is real time after the completion of the second discrimination process Alert to The discrimination result notifying unit 141 can display the respective discrimination results as in the first embodiment using the display control unit 15 and the display unit 13, and can also use sound (including sound), light (observation endoscope image 101). The result of the first discrimination process, the result of the second discrimination process, and the result of the third discrimination process can be reported by any other method such as the partial blinking of the character of the symbol, the display of coordinates, and the like.
　［第２実施形態］
　上記第１実施形態及び変形例においては、医療画像処理装置１０と内視鏡装置２１は別個の装置であるが、内視鏡装置２１は、医療画像処理装置１０を含むことができる。この場合、図２６に示す内視鏡装置５１０のように、医療画像処理装置１０を構成する各部５２０は、プロセッサ装置３３に設ける。但し、表示部１３は、内視鏡装置２１のモニタ３４を共用できる。また、医療画像取得部１１は、イメージセンサ４１及び内視鏡画像生成部４８が形成する「内視鏡画像取得部」に相当する。このため、プロセッサ装置３３には医療画像取得部１１及び表示部１３以外の各部を設ければ足りる。その他の各部の構成は、第１実施形態と同様である。また、上記各実施形態及びその他変形例の医療画像処理装置１０と、図２の内視鏡装置２１と、の全体で新たな内視鏡装置を構成できる。 Second Embodiment
In the first embodiment and the modification, the medical image processing apparatus 10 and the endoscope apparatus 21 are separate apparatuses, but the endoscope apparatus 21 can include the medical image processing apparatus 10. In this case, as in the endoscope apparatus 510 shown in FIG. 26, each unit 520 constituting the medical image processing apparatus 10 is provided in the processor apparatus 33. However, the display unit 13 can share the monitor 34 of the endoscope apparatus 21. Moreover, the medical image acquisition part 11 is corresponded to the "endoscope image acquisition part" which the image sensor 41 and the endoscope image generation part 48 form. For this reason, it is sufficient to provide the processor 33 with components other than the medical image acquisition unit 11 and the display unit 13. The configuration of the other components is the same as that of the first embodiment. In addition, a new endoscope apparatus can be configured as a whole of the medical image processing apparatus 10 of each of the above-described embodiments and the other modifications and the endoscope apparatus 21 of FIG. 2.
　医療画像処理装置１０を含む内視鏡装置５１０は、基本的にリアルタイムに被写体を観察する装置である。このため、内視鏡装置５１０は、医療画像である内視鏡画像の取得、第１鑑別処理、第２鑑別処理、第３鑑別処理、及び、これらの結果の表示処理等は、内視鏡画像を撮影しながらリアルタイムで、または、各種操作部等の操作に起因した任意のタイミングで実行できる。 An endoscope apparatus 510 including the medical image processing apparatus 10 is basically an apparatus for observing a subject in real time. For this reason, the endoscope apparatus 510 can obtain an endoscope image which is a medical image, a first discrimination process, a second discrimination process, a third discrimination process, and a display process of these results, etc. It can be performed in real time while capturing an image, or at any timing caused by the operation of various operation units and the like.
　以下、医療画像処理装置１０を含む内視鏡装置５１０がリアルタイムに病変等の検出及び進行度の鑑別をする場合の動作の流れを説明する。図２７に示すように、内視鏡装置５１０は、観察用照明光を用いて被写体を撮影し、観察用内視鏡画像１０１を適宜取得し（ステップＳ２１０）、かつ、表示制御部１５は観察用内視鏡画像１０１をモニタ３４に適宜表示する（ステップＳ２１１）。 The flow of operation when the endoscope apparatus 510 including the medical image processing apparatus 10 detects a lesion or the like and discriminates the progress degree in real time will be described below. As shown in FIG. 27, the endoscope apparatus 510 captures an object using the observation illumination light, appropriately acquires the observation endoscope image 101 (step S210), and the display control unit 15 performs observation The endoscopic image 101 for endoscope is suitably displayed on the monitor 34 (step S211).
　また、モニタ３４に観察用内視鏡画像１０１を表示する処理のバックグラウンドにおいて、統括制御部１７は、一連の観察用内視鏡画像１０１の撮影の間に、観察用内視鏡画像１０１の連続した表示に支障がない所定のタイミングで、間欠的に、第１鑑別処理用の撮影を割り込ませる。すなわち、内視鏡装置５１０は、イメージセンサ４１の撮影のタイミングに合わせて照明光をパターン１の鑑別用照明光に適宜切り替え（ステップＳ２１２）、観察用内視鏡画像１０１を撮影するフレームの合間に、パターン１の鑑別用照明光を用いて被写体を撮影するフレームを適宜挿入する。これにより、内視鏡装置５１０は、第１鑑別処理用の第１内視鏡画像６１を取得し（ステップＳ２１３）、かつ、第１鑑別処理部５１は第１内視鏡画像６１を用いて第１鑑別処理を実行する（ステップＳ２１４）。 Further, in the background of the process of displaying the observation endoscope image 101 on the monitor 34, the integrated control unit 17 sets the observation endoscope image 101 during the series of imaging of the observation endoscope image 101. The imaging for the first discrimination process is intermittently interrupted at a predetermined timing that does not affect continuous display. That is, the endoscope apparatus 510 appropriately switches the illumination light to the discrimination illumination light of pattern 1 in accordance with the timing of imaging of the image sensor 41 (step S212), and the interval between the frames for imaging the endoscopic image 101 for observation Then, a frame for photographing a subject using the discrimination illumination light of pattern 1 is inserted as appropriate. Thereby, the endoscope apparatus 510 acquires the first endoscopic image 61 for the first discrimination process (step S213), and the first discrimination processing unit 51 uses the first endoscopic image 61. The first discrimination process is executed (step S214).
　第１鑑別処理において異常領域１０２を検出すると、統括制御部１７は、一連の観察用内視鏡画像１０１の撮影の間に、観察用内視鏡画像１０１の連続した表示に支障がない所定のタイミングで、間欠的に、第２鑑別処理用の撮影を割り込ませる。すなわち、内視鏡装置５１０は、イメージセンサ４１の撮影のタイミングに合わせて照明光をパターン２の鑑別用照明光に適宜切り替え（ステップＳ２１５）、観察用内視鏡画像１０１を撮影するフレームの合間に、パターン２の鑑別用照明光を用いて被写体を撮影するフレームを適宜挿入する。これにより、内視鏡装置５１０は、第２鑑別処理用の第２内視鏡画像６３を取得し（ステップＳ２１６）、かつ、第２鑑別処理部５２は、第２内視鏡画像６３を用いて第２鑑別処理を実行する（ステップＳ２１７）。 When the abnormal area 102 is detected in the first discrimination process, the general control unit 17 determines that the continuous display of the observation endoscope image 101 is not interrupted during the imaging of the series of observation endoscope images 101. At the timing, the imaging for the second discrimination process is intermittently interrupted. That is, the endoscope apparatus 510 appropriately switches the illumination light to the discrimination illumination light of pattern 2 in accordance with the timing of imaging of the image sensor 41 (step S215), and the interval between the frames for imaging the endoscopic image 101 for observation Then, a frame for photographing a subject using the discrimination illumination light of pattern 2 is inserted as appropriate. Thereby, the endoscope apparatus 510 acquires the second endoscopic image 63 for the second discrimination process (step S216), and the second discrimination processing unit 52 uses the second endoscopic image 63. The second discrimination process is executed (step S217).
　その後、統括制御部１７は、一連の観察用内視鏡画像１０１の撮影の間に、観察用内視鏡画像１０１の連続した表示に支障がない所定のタイミングで、間欠的に、第３鑑別処理用の撮影を割り込ませる。すなわち、内視鏡装置５１０は、第２鑑別処理の結果にしたがって第３鑑別処理に適したスペクトルを有する特定のパターンの鑑別用照明光に適宜切り替える（ステップＳ２１８）。この際、第３鑑別処理部５３は、第２鑑別処理の結果を用いて第３医療画像を取得する際に用いる照明光のスペクトルを選択する。この照明光を切り替えの結果、観察用内視鏡画像１０１を撮影するフレームの合間に、第３鑑別処理用の照明光を用いて被写体を撮影するフレームを適宜挿入する。例えば、第２鑑別処理の結果、異常領域１０２が含む異常が「ポリープ」であればパターン６の鑑別用照明光を用いて被写体を撮影するフレームを挿入し、異常領域１０２が含む異常が「潰瘍性大腸炎」であればパターン３の鑑別用照明光を用いて被写体を撮影するフレームを挿入し、かつ、異常領域１０２が含む異常が「クローン病」であればパターン４の鑑別用照明光を用いて被写体を撮影するフレームを挿入する。これにより、内視鏡装置５１０は、第３鑑別処理用の第３内視鏡画像６６を取得し（ステップＳ２１９）、かつ、第３鑑別処理部５３は、第３内視鏡画像６６を用いて第３鑑別処理を実行する（ステップＳ２２０）。第３鑑別処理が完了すると、表示制御部１５は、表示部１３に少なくとも第３鑑別処理の結果を表示する（ステップＳ２２１） Thereafter, the integrated control unit 17 intermittently performs the third identification at predetermined timing that does not affect continuous display of the observation endoscope image 101 during capturing of the series of observation endoscope images 101. Interrupt the shooting for processing. That is, the endoscope apparatus 510 appropriately switches to the identification illumination light for a specific pattern having a spectrum suitable for the third identification processing according to the result of the second identification processing (step S218). At this time, the third discrimination processing unit 53 selects the spectrum of the illumination light used when acquiring the third medical image, using the result of the second discrimination processing. As a result of switching the illumination light, a frame for photographing a subject using the illumination light for the third discrimination process is inserted as needed between the frames for photographing the observation endoscope image 101. For example, if the abnormality included in the abnormal area 102 is "polyp" as a result of the second discrimination processing, a frame for photographing the subject is inserted using the discrimination illumination light of pattern 6, and the abnormality included in the abnormal area 102 is "ulcer If the disease is "colonitis", insert a frame that shoots the subject using the discrimination illumination light of pattern 3, and if the abnormality included in the abnormal area 102 is "Crohn's disease", the discrimination illumination light of pattern 4 Insert a frame to shoot a subject using. Thereby, the endoscope apparatus 510 acquires the third endoscopic image 66 for the third discrimination process (step S219), and the third discrimination processing unit 53 uses the third endoscopic image 66. And execute the third discrimination process (step S220). When the third discrimination process is completed, the display control unit 15 displays at least the result of the third discrimination process on the display unit 13 (step S221).
　上記のように、医療画像処理装置１０を含む内視鏡装置５１０は、リアルタイムに第１鑑別処理、第２鑑別処理、及び、第３鑑別処理を行って、リアルタイムに診断等を支援することができる。 As described above, the endoscope apparatus 510 including the medical image processing apparatus 10 may perform the first discrimination process, the second discrimination process, and the third discrimination process in real time to support diagnosis etc. in real time. it can.
　図２８に示すように、医療画像処理装置１０を含む内視鏡装置５１０は、さらにズーム機構５３１、ズーム制御部５４１、光量制御部５４２、動き検出部５４３、及び、撮影制御部５４５等を備えることが好ましい。 As shown in FIG. 28, the endoscope apparatus 510 including the medical image processing apparatus 10 further includes a zoom mechanism 531, a zoom control unit 541, a light amount control unit 542, a motion detection unit 543, an imaging control unit 545, and the like. Is preferred.
　ズーム機構５３１は、撮影倍率を変更する機械的機構または電子的機構である。機械的機構とはいわゆる光学ズームであり、電子的機構とはいわゆる電子ズームである。ズーム制御部５４１は、ズーム機構５３１を制御して撮影倍率を設定する。内視鏡装置５１０は、ズーム制御部５４１を用いて撮影倍率を取得できる。 The zoom mechanism 531 is a mechanical mechanism or an electronic mechanism that changes the imaging magnification. The mechanical mechanism is a so-called optical zoom, and the electronic mechanism is a so-called electronic zoom. The zoom control unit 541 controls the zoom mechanism 531 to set an imaging magnification. The endoscope apparatus 510 can obtain the imaging magnification using the zoom control unit 541.
　光量制御部５４２は、観察距離（内視鏡３１の先端と被写体との距離である。撮影倍率の変更による実質的な内視鏡３１の先端と被写体との距離を含む。）に応じて適正な照明光の光量を設定する。光源制御部４７は、光源部４２を用いて、光量制御部５４２が設定した光量で、観察用照明光、及び、各パターンの鑑別用照明光を発光する。 The light amount control unit 542 is appropriate according to the observation distance (the distance between the tip of the endoscope 31 and the subject, including the substantial distance between the tip of the endoscope 31 and the subject due to the change of the imaging magnification). Set the amount of illumination light. The light source control unit 47 uses the light source unit 42 to emit observation illumination light and discrimination illumination light of each pattern with the light amount set by the light amount control unit 542.
　動き検出部５４３は、観察用内視鏡画像１０１等の内視鏡画像を用いて被写体の動き、または、被写体と内視鏡３１との相対的な動き（以下、単に「動き」という）の方向、速度、もしくは移動量等を検出する。 The motion detection unit 543 uses the endoscope image such as the observation endoscope image 101 or the like to perform the motion of the subject or the relative motion of the subject and the endoscope 31 (hereinafter simply referred to as “motion”). It detects the direction, speed or movement amount.
　撮影制御部５４５は、観察条件にしたがって、第１鑑別処理用の撮影の頻度、第２鑑別処理用の撮影の頻度、または、第３鑑別処理用の撮影の頻度を制御する。観察条件とは、内視鏡画像を撮影する際の撮影倍率、照明光の光量、または、動きに関する状況である。撮影制御部５４５は、撮影倍率をズーム制御部５４１から取得でき、照明光の光量を光量制御部５４２から取得でき、かつ、動きを動き検出部５４３から取得できる。本変形例においては、撮影制御部５４５は、撮影倍率、照明光の光量、及び、動きを複合した観察条件にしたがって、第１鑑別処理用の撮影の頻度と、第２鑑別処理用の撮影及び第３鑑別処理用の撮影の頻度と、を制御する。 The imaging control unit 545 controls the frequency of imaging for the first discrimination process, the frequency of imaging for the second discrimination process, or the frequency of imaging for the third discrimination process according to the observation condition. The observation conditions are the imaging magnification at the time of imaging an endoscopic image, the light amount of illumination light, or the situation regarding movement. The shooting control unit 545 can obtain the shooting magnification from the zoom control unit 541, can obtain the light quantity of the illumination light from the light quantity control unit 542, and can obtain the movement from the movement detection unit 543. In the present modification, the photographing control unit 545 sets the photographing frequency for the first discrimination process, the photographing for the second discrimination process, and the photographing condition for the first discrimination process according to the photographing condition, the light amount of the illumination light, and the observation condition combining the motion. Control the frequency of imaging for the third discrimination process.
　図２９に示すように、撮影倍率が比較的小さく、照明光の光量が比較的大きく、かつ、動きが比較的大きい「観察条件Ｘ１」は、いわゆるスクリーニングをしている状況において発生頻度が高い観察条件である。このため、撮影制御部５４５は、観察用内視鏡画像１０１の撮影の頻度と、第１鑑別処理用の撮影の頻度と、を相対的に多くし、かつ、第２鑑別処理用及び第３鑑別処理用の撮影の頻度を相対的に少なくする。スクリーニングは、一般的に、被写体の全体的な観察、または、異常領域１０２の検出を主な目的とするからである。 As shown in FIG. 29, “observation condition X1” having a relatively small imaging magnification, a relatively large amount of illumination light, and a relatively large movement is observed with a high frequency of occurrence in a so-called screening situation. It is a condition. Therefore, the imaging control unit 545 relatively increases the frequency of imaging of the observation endoscope image 101 and the frequency of imaging for the first discrimination process, and for the second discrimination process and the third discrimination process. Reduce the frequency of imaging for discrimination processing relatively. This is because, in general, screening mainly aims at general observation of an object or detection of an abnormal area 102.
　一方、撮影倍率が比較的大きく、照明光の光量が比較的小さく、かつ、動きが比較的小さい「観察条件Ｘ２」は、診断等のために被写体を詳細に観察する状況において発生頻度が高い観察条件である。このため、撮影制御部５４５は、観察用内視鏡画像１０１の撮影頻度と、第１鑑別処理用の撮影の頻度を相対的に少なくし、かつ、第２鑑別処理用及び第３鑑別処理用の撮影の頻度を相対的に多くする。診断等のために被写体を詳細に観察する状況においては、被写体の僅かな見え方の変化等に追従して、迅速かつ正確に第２鑑別処理及び第３鑑別処理の結果を提示することが求められるからである。 On the other hand, “observation condition X2” in which the imaging magnification is relatively large, the amount of illumination light is relatively small, and the movement is relatively small is an observation that occurs frequently when the object is observed in detail for diagnosis etc. It is a condition. For this reason, the imaging control unit 545 relatively reduces the imaging frequency of the observation endoscope image 101 and the imaging frequency for the first discrimination process, and for the second discrimination process and the third discrimination process. Relatively increase the frequency of shooting. In a situation where the subject is observed in detail for diagnosis etc., it is required that the results of the second discrimination process and the third discrimination process be presented promptly and accurately, following the slight change in appearance of the subject, etc. Because
　上記のように、観察条件を用いて、観察用内視鏡画像１０１の撮影の頻度、第１鑑別処理用の撮影の頻度、第２鑑別処理用の撮影の頻度、及び、第３鑑別処理用の撮影の頻度を変更すれば、撮影の状況（撮影の目的）に応じて適切な更新頻度で第３鑑別処理の結果等の鑑別結果を提示できる。 As described above, using the observation conditions, the frequency of imaging of the observation endoscope image 101, the frequency of imaging for the first discrimination process, the frequency of imaging for the second discrimination process, and for the third discrimination process If the frequency of photographing is changed, discrimination results such as the result of the third discrimination processing can be presented at an appropriate updating frequency according to the situation of photographing (the purpose of photographing).
　なお、比較的小さいとは例えば所定の閾値よりも小さいことをいい、比較的大きいとは例えば所定の閾値以上であることをいう。また、撮影の頻度を相対的に多くまたは少なくするとは、観察条件Ｘ１、観察条件Ｘ２、または、その他の観察条件における特定の撮影の頻度を基準として、撮影の頻度を多くまたは少なくすることをいう。本変形例においては、観察条件Ｘ１における撮影の頻度と観察条件Ｘ２における撮影の頻度の相互比較である。 Note that “relatively small” means, for example, smaller than a predetermined threshold, and “relatively large” means, for example, greater than or equal to the predetermined threshold. Also, to relatively increase or decrease the frequency of imaging means to increase or decrease the frequency of imaging based on the frequency of specific imaging under the observation condition X1, the observation condition X2, or other observation conditions. . In this modification, the frequency of imaging under observation condition X1 is compared with the frequency of imaging under observation condition X2.
　上記第２実施形態においては、内視鏡装置５１０が医療画像処理装置１０を含んでいるが、図３０に示すように、内視鏡装置２１その他モダリティと組み合わせて使用する診断支援装置６１０は、上記実施形態及びその他変形例の医療画像処理装置１０を含むことができる。また、図３１に示すように、例えば内視鏡装置２１を含む、第１検査装置６２１、第２検査装置６２２、…、第Ｎ検査装置６２３等の各種検査装置と任意のネットワーク６２６を介して接続する医療業務支援装置６３０は、上記実施形態及びその他変形例の医療画像処理装置１０を含むことができる。 In the second embodiment, the endoscope apparatus 510 includes the medical image processing apparatus 10. However, as shown in FIG. 30, the diagnostic support apparatus 610 used in combination with the endoscope apparatus 21 and other modality is The medical image processing apparatus 10 of the said embodiment and the other modification can be included. Also, as shown in FIG. 31, various inspection devices such as the first inspection device 621, the second inspection device 622, ..., the N-th inspection device 623, etc., including the endoscope device 21, for example, via the arbitrary network 626 The medical service support device 630 to be connected can include the medical image processing device 10 of the above-described embodiment and other modified examples.
　この他、医療画像処理装置１０、及び、医療画像処理装置１０を含む各種装置、及び、医療画像処理装置１０の機能を内包する各種装置またはシステムは、以下の種々の変更等をして使用できる。 In addition, the medical image processing apparatus 10, various apparatuses including the medical image processing apparatus 10, and various apparatuses or systems including the functions of the medical image processing apparatus 10 can be used with various modifications described below. .
　医療画像としては、白色帯域の光、または白色帯域の光として複数の波長帯域の光を照射して得る通常光画像を用いることができる。 As a medical image, a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band can be used.
　医療画像としては、特定の波長帯域の光を照射して得た画像を使用する場合、特定の波長帯域は、白色の波長帯域よりも狭い帯域を用いることができる。 When an image obtained by irradiating light of a specific wavelength band is used as a medical image, a specific wavelength band can use a band narrower than the white wavelength band.
　特定の波長帯域は、例えば、可視域の青色帯域または緑色帯域である。 The specific wavelength band is, for example, a blue band or a green band in the visible range.
　特定の波長帯域が可視域の青色帯域または緑色帯域である場合、特定の波長帯域は、３９０ｎｍ以上４５０ｎｍ以下または５３０ｎｍ以上５５０ｎｍ以下の波長帯域を含み、かつ、特定の波長帯域の光は、３９０ｎｍ以上４５０ｎｍ以下または５３０ｎｍ以上５５０ｎｍ以下の波長帯域内にピーク波長を有することが好ましい。 When the specific wavelength band is a blue band or a green band in the visible range, the specific wavelength band includes a wavelength band of 390 nm to 450 nm or 530 nm to 550 nm, and light of the specific wavelength band is 390 nm or more It is preferable to have a peak wavelength within a wavelength band of 450 nm or less or 530 nm or more and 550 nm or less.
　特定の波長帯域は、例えば、可視域の赤色帯域である。 The specific wavelength band is, for example, a red band in the visible range.
　特定の波長帯域が可視域の赤色帯域である場合、特定の波長帯域は、５８５ｎｍ以上６１５ｎｍまたは６１０ｎｍ以上７３０ｎｍ以下の波長帯域を含み、かつ、特定の波長帯域の光は、５８５ｎｍ以上６１５ｎｍ以下または６１０ｎｍ以上７３０ｎｍ以下の波長帯域内にピーク波長を有することが好ましい。 When the specific wavelength band is a red band in the visible range, the specific wavelength band includes a wavelength band of 585 nm to 615 nm or 610 nm to 730 nm, and light of the specific wavelength band is 585 nm to 615 nm or 610 nm It is preferable to have a peak wavelength within the wavelength band of not less than 730 nm.
　特定の波長帯域は、例えば、酸化ヘモグロビンと還元ヘモグロビンとで吸光係数が異なる波長帯域を含み、かつ、特定の波長帯域の光は、酸化ヘモグロビンと還元ヘモグロビンとで吸光係数が異なる波長帯域にピーク波長を有することができる。 The specific wavelength band includes, for example, wavelength bands in which the absorption coefficient is different between oxygenated hemoglobin and reduced hemoglobin, and light of a specific wavelength band is a peak wavelength in the wavelength band where absorption coefficients are different between oxygenated hemoglobin and reduced hemoglobin You can have
　特定の波長帯域が、酸化ヘモグロビンと還元ヘモグロビンとで吸光係数が異なる波長帯域を含み、かつ、特定の波長帯域の光は、酸化ヘモグロビンと還元ヘモグロビンとで吸光係数が異なる波長帯域にピーク波長を有する場合、特定の波長帯域は、４００±１０ｎｍ、４４０±１０ｎｍ、４７０±１０ｎｍ、または、６００ｎｍ以上７５０ｎｍ以下の波長帯域を含み、かつ、特定の波長帯域の光は、４００±１０ｎｍ、４４０±１０ｎｍ、４７０±１０ｎｍ、または、６００ｎｍ以上７５０ｎｍ以下の波長帯域にピーク波長を有することが好ましい。 A specific wavelength band includes wavelength bands whose absorption coefficients are different between oxyhemoglobin and reduced hemoglobin, and light of a specific wavelength band has peak wavelengths in wavelength bands whose absorption coefficients are different between oxyhemoglobin and reduced hemoglobin In the case, the specific wavelength band includes the wavelength bands of 400 ± 10 nm, 440 ± 10 nm, 470 ± 10 nm, or 600 nm to 750 nm, and the light of the specific wavelength band is 400 ± 10 nm, 440 ± 10 nm, It is preferable to have a peak wavelength in a wavelength band of 470 ± 10 nm, or 600 nm to 750 nm.
　医療画像が生体内を写した生体内画像である場合、この生体内画像は、生体内の蛍光物質が発する蛍光の情報を有することができる。 When the medical image is an in-vivo image obtained by copying the inside of a living body, this in-vivo image can have information of fluorescence emitted from a fluorescent substance in the living body.
　また、蛍光は、ピーク波長が３９０ｎｍ以上４７０ｎｍ以下である励起光を生体内に照射して得る蛍光を利用できる。 Further, as fluorescence, fluorescence obtained by irradiating excitation light having a peak wavelength of 390 nm or more and 470 nm or less into a living body can be used.
　医療画像が生体内を写した生体内画像である場合、前述の特定の波長帯域は、赤外光の波長帯域を利用することができる。 When the medical image is an in-vivo image obtained by copying the inside of a living body, the above-mentioned specific wavelength band can utilize the wavelength band of infrared light.
　医療画像が生体内を写した生体内画像であり、前述の特定の波長帯域として、赤外光の波長帯域を利用する場合、特定の波長帯域は、７９０ｎｍ以上８２０ｎｍまたは９０５ｎｍ以上９７０ｎｍ以下の波長帯域を含み、かつ、特定の波長帯域の光は、７９０ｎｍ以上８２０ｎｍ以下または９０５ｎｍ以上９７０ｎｍ以下の波長帯域にピーク波長を有することが好ましい。 When the medical image is an in-vivo image obtained by copying the inside of a living body and a wavelength band of infrared light is used as the above-mentioned specific wavelength band, the specific wavelength band is a wavelength band of 790 nm to 820 nm or 905 nm to 970 nm And light of a specific wavelength band preferably has a peak wavelength in a wavelength band of 790 nm or more and 820 nm or less or 905 nm or more and 970 nm or less.
　医療画像取得部１１は、白色帯域の光、または白色帯域の光として複数の波長帯域の光を照射して得る通常光画像に基づいて、特定の波長帯域の信号を有する特殊光画像を取得する特殊光画像取得部を有することができる。この場合、医療画像として特殊光画像を利用できる。 The medical image acquisition unit 11 acquires a special light image having a signal of a specific wavelength band based on a normal light image obtained by irradiating light of a plurality of wavelength bands as light of the white band or light of the white band. It can have a special light image acquisition unit. In this case, a special light image can be used as a medical image.
　特定の波長帯域の信号は、通常光画像に含むＲＧＢまたはＣＭＹの色情報に基づく演算により得ることができる。 A signal of a specific wavelength band can be obtained by an operation based on RGB or CMY color information included in a normal light image.
　白色帯域の光、または白色帯域の光として複数の波長帯域の光を照射して得る通常光画像と、特定の波長帯域の光を照射して得る特殊光画像との少なくとも一方に基づく演算によって、特徴量画像を生成する特徴量画像生成部を備えることができる。この場合、医療画像として特徴量画像を利用できる。 By an operation based on at least one of a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band, and a special light image obtained by irradiating light of a specific wavelength band A feature amount image generation unit that generates a feature amount image can be provided. In this case, the feature amount image can be used as a medical image.
　内視鏡装置２１については、内視鏡３１としてカプセル内視鏡を使用できる。この場合、光源装置３２と、プロセッサ装置３３の一部と、はカプセル内視鏡に搭載できる。 For the endoscope apparatus 21, a capsule endoscope can be used as the endoscope 31. In this case, the light source device 32 and part of the processor device 33 can be mounted on the capsule endoscope.
　上記各実施形態及び変形例において、医療画像取得部１１、医療画像解析処理部１２（医療画像解析処理部１２を構成する各部）、表示制御部１５、入力受信部１６、統括制御部１７、並びに、内視鏡装置２１の内視鏡画像生成部４８等といった各種の処理を実行する処理部（processing unit)のハードウェア的な構造は、次に示すような各種のプロセッサ（processor）である。各種のプロセッサには、ソフトウエア（プログラム）を実行して各種の処理部として機能する汎用的なプロセッサであるＣＰＵ（Central Processing Unit)、ＦＰＧＡ (Field Programmable Gate Array)などの製造後に回路構成を変更可能なプロセッサであるプログラマブルロジックデバイス（Programmable Logic Device:ＰＬＤ）、各種の処理を実行するために専用に設計された回路構成を有するプロセッサである専用電気回路などが含まれる。 In each of the above-described embodiments and modifications, the medical image acquisition unit 11, the medical image analysis processing unit 12 (each unit constituting the medical image analysis processing unit 12), the display control unit 15, the input reception unit 16, the general control unit 17, and The hardware-like structure of a processing unit that executes various processes such as the endoscope image generation unit 48 of the endoscope apparatus 21 is various processors as shown below. For various processors, change the circuit configuration after manufacturing CPU (Central Processing Unit), which is a general-purpose processor that executes software (program) and functions as various processing units, FPGA (Field Programmable Gate Array), etc. A programmable logic device (Programmable Logic Device: PLD), which is a possible processor, and a dedicated electric circuit, which is a processor having a circuit configuration specially designed to execute various processes, are included.
　１つの処理部は、これら各種のプロセッサのうちの１つで構成されてもよいし、同種または異種の２つ以上のプロセッサの組み合せ（例えば、複数のＦＰＧＡや、ＣＰＵとＦＰＧＡの組み合わせ）で構成されてもよい。また、複数の処理部を１つのプロセッサで構成してもよい。複数の処理部を１つのプロセッサで構成する例としては、第１に、クライアントやサーバなどのコンピュータに代表されるように、１つ以上のＣＰＵとソフトウエアの組み合わせで１つのプロセッサを構成し、このプロセッサが複数の処理部として機能する形態がある。第２に、システムオンチップ（System On Chip:ＳｏＣ）などに代表されるように、複数の処理部を含むシステム全体の機能を１つのＩＣ（Integrated Circuit）チップで実現するプロセッサを使用する形態がある。このように、各種の処理部は、ハードウェア的な構造として、上記各種のプロセッサを１つ以上用いて構成される。 One processing unit may be configured of one of these various processors, or configured of a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs or a combination of a CPU and an FPGA) It may be done. In addition, a plurality of processing units may be configured by one processor. As an example in which a plurality of processing units are configured by one processor, first, one processor is configured by a combination of one or more CPUs and software as represented by computers such as clients and servers; There is a form in which this processor functions as a plurality of processing units. Second, as typified by a system on chip (SoC) or the like, there is a form using a processor that realizes the functions of the entire system including a plurality of processing units in one integrated circuit (IC) chip. is there. Thus, the various processing units are configured using one or more of the above-described various processors as a hardware structure.
　さらに、これらの各種のプロセッサのハードウェア的な構造は、より具体的には、半導体素子などの回路素子を組み合わせた形態の電気回路（circuitry）である。 Furthermore, the hardware-like structure of these various processors is, more specifically, an electrical circuit (circuitry) in the form in which circuit elements such as semiconductor elements are combined.
　１０　医療画像処理装置
　１１　医療画像取得部
　１２　医療画像解析処理部
　１３　表示部
　１５　表示制御部
　１６　入力受信部
　１７　統括制御部
　１８　保存部
　２１，５１０　内視鏡装置
　２２　ＰＡＣＳ
　３１　内視鏡
　３２　光源装置
　３３　プロセッサ装置
　３４　モニタ
　４１　イメージセンサ
　４２　光源部
　４３　Ｖ－ＬＥＤ
　４４　Ｂ－ＬＥＤ
　４５　Ｇ－ＬＥＤ
　４６　Ｒ－ＬＥＤ
　４７　光源制御部
　４８　内視鏡画像生成部
　５１　第１鑑別処理部
　５２　第２鑑別処理部
　５３　第３鑑別処理部
　５６　設定部
　６１　第１内視鏡画像（第１医療画像）
　６３　第２内視鏡画像（第２医療画像）
　６６　第３内視鏡画像（第３医療画像）
　７１　第１種類鑑別部
　７２　第２種類鑑別部
　７３　第３種類鑑別部
　８１　第１進行度鑑別部
　８２　第２進行度鑑別部
　８３　第３進行度鑑別部
　９１　チェックボックス
　１０１　観察用内視鏡画像
　１０２　異常領域
　１０３　第２鑑別処理の結果を示す表示欄
　１０４　第３鑑別処理の結果を示す表示欄
　１２１　カルテ取得部
　１３１　鑑別結果修正部
　１４１　鑑別結果報知部
　５２０　医療画像処理装置を構成する各部
　５３１　ズーム機構
　５４１　ズーム制御部
　５４２　光量制御部
　５４３　動き検出部
　５４５　撮影制御部
　６１０　診断支援装置
　６２１　第１検査装置
　６２２　第２検査装置
　６２３　第Ｎ検査装置
　６２６　ネットワーク
　６３０　医療業務支援装置
　Ｓ１１０～Ｓ１１８、Ｓ２１０～Ｓ２２１　動作のステップ
　Ｘ１、Ｘ２　観察条件 Reference Signs List 10 medical image processing apparatus 11 medical image acquisition unit 12 medical image analysis processing unit 13 display unit 15 display control unit 16 input reception unit 17 general control unit 18 storage unit 21, 510 endoscope apparatus 22 PACS
Reference Signs List 31 endoscope 32 light source device 33 processor device 34 monitor 41 image sensor 42 light source portion 43 V-LED
44 B-LED
45 G-LED
46 R-LED
47 light source control unit 48 endoscope image generation unit 51 first discrimination processing unit 52 second discrimination processing unit 53 third discrimination processing unit 56 setting unit 61 first endoscopic image (first medical image)
63 Second endoscopic image (second medical image)
66 Third endoscopic image (third medical image)
71 first type discrimination unit 72 second type discrimination unit 73 third type discrimination unit 81 first progress discrimination unit 82 second progression discrimination unit 83 third progression discrimination unit 91 check box 101 endoscopic image for observation 102 Abnormal area 103 Display field indicating the result of the second discrimination process 104 Display field indicating the result of the third discrimination process 121 medical record acquisition unit 131 discrimination result correction unit 141 discrimination result notification unit 520 each unit constituting the medical image processing apparatus 531 zoom mechanism 541 zoom control unit 542 light amount control unit 543 motion detection unit 545 imaging control unit 610 diagnosis support device 621 first inspection device 622 second inspection device 623 Nth inspection device 626 network 630 medical service support device S110 to S118, S210 to S221 operation Step X1, X2 observation conditions of

Claims (15)

  1. 　被写体像を含む医療画像を取得する医療画像取得部と、
    　前記医療画像のうち、特定のスペクトルを有する第１照明光を使用して撮影した第１医療画像を用いて１または複数種類の第１異常領域を検出する第１鑑別処理を行う第１鑑別処理部と、
    　前記医療画像のうち、前記第１照明光とはスペクトルが異なる第２照明光を使用して撮影した第２医療画像を用いて、各々の前記第１異常領域が含む異常の種類を特定する第２鑑別処理を行う第２鑑別処理部と、
    　前記医療画像のうち、前記第１照明光及び前記第２照明光とはスペクトルが異なる第３照明光を使用して撮影した第３医療画像を用いて、前記第１異常領域が含む異常の進行度を特定する第３鑑別処理を行う第３鑑別処理部と、
    　を備える医療画像処理装置。     A medical image acquisition unit for acquiring a medical image including a subject image;
    First discrimination processing for performing first discrimination processing of detecting one or more types of first abnormal regions using the first medical image captured using the first illumination light having a specific spectrum among the medical images Department,
    In the medical image, a second medical image captured using a second illumination light having a spectrum different from that of the first illumination light is used to identify a type of abnormality included in each of the first abnormal areas. 2) a second discrimination processing unit that performs discrimination processing;
    Of the medical images, using the third medical image captured using the third illumination light different in spectrum from the first illumination light and the second illumination light, the progression of the abnormality included in the first abnormal area A third discrimination processing unit that performs a third discrimination process that specifies the degree of
    Medical image processing apparatus comprising:
  2. 　前記第２鑑別処理部は、前記第１異常領域に対応する前記第２医療画像に含まれる第２異常領域に対して前記第２鑑別処理を行うことで、前記第１異常領域が含む異常の種類を特定する請求項１の医療画像処理装置。 The second discrimination processing unit performs the second discrimination process on a second abnormal area included in the second medical image corresponding to the first abnormal area, whereby an abnormality included in the first abnormal area is generated. The medical image processing apparatus of claim 1, wherein the type is identified.
  3. 　前記第３鑑別処理部は、前記第１異常領域または前記第２異常領域の少なくとも一方に対応する前記第３医療画像に含まれる第３異常領域に対して前記第３鑑別処理を行うことで、前記第１異常領域が含む異常の進行度を特定する請求項１または２に記載の医療画像処理装置。 The third discrimination processing unit performs the third discrimination process on a third abnormal area included in the third medical image corresponding to at least one of the first abnormal area or the second abnormal area. The medical image processing apparatus according to claim 1, wherein the degree of progression of the abnormality included in the first abnormal area is specified.
  4. 　前記第３鑑別処理部は、前記第２鑑別処理の結果を用いて前記第３医療画像を選択する請求項１～３のいずれか１項に記載の医療画像処理装置。 The medical image processing apparatus according to any one of claims 1 to 3, wherein the third discrimination processing unit selects the third medical image using a result of the second discrimination processing.
  5. 　前記第３鑑別処理部は、前記第２鑑別処理の結果と対応付けられた前記第３照明光のスペクトルで取得された前記第３医療画像を選択する請求項４に記載の医療画像処理装置。 The medical image processing apparatus according to claim 4, wherein the third discrimination processing unit selects the third medical image acquired in the spectrum of the third illumination light associated with the result of the second discrimination processing.
  6. 　前記医療画像取得部は、前記第１医療画像、前記第２医療画像、及び、前記第３医療画像の他に、観察用医療画像を取得し、
    　前記観察用医療画像を表示部に表示している間に、前記第１鑑別処理部は前記第１鑑別処理をし、前記第２鑑別処理部は前記第２鑑別処理をし、かつ、前記第３鑑別処理部は前記第３鑑別処理をする請求項１～５のいずれか１項に記載の医療画像処理装置。     The medical image acquisition unit acquires a medical image for observation in addition to the first medical image, the second medical image, and the third medical image.
    While the medical image for observation is displayed on the display unit, the first discrimination processing unit performs the first discrimination processing, the second discrimination processing unit performs the second discrimination processing, and The medical image processing apparatus according to any one of claims 1 to 5, wherein the 3 discrimination processing unit performs the third discrimination processing.
  7. 　前記医療画像取得部は、前記第１医療画像、前記第２医療画像、及び、前記第３医療画像のうちの何れかを観察用医療画像に設定し、
    　前記観察用医療画像を表示部に表示している間に、前記第１鑑別処理部は前記第１鑑別処理をし、前記第２鑑別処理部は前記第２鑑別処理をし、かつ、前記第３鑑別処理部は前記第３鑑別処理をする請求項１～５のいずれか１項に記載の医療画像処理装置。     The medical image acquisition unit sets any one of the first medical image, the second medical image, and the third medical image as a medical image for observation.
    While the medical image for observation is displayed on the display unit, the first discrimination processing unit performs the first discrimination processing, the second discrimination processing unit performs the second discrimination processing, and The medical image processing apparatus according to any one of claims 1 to 5, wherein the 3 discrimination processing unit performs the third discrimination processing.
  8. 　前記第２鑑別処理において特定する異常の種類、または、前記第３鑑別処理において特定する進行度の分類の設定を変更する設定部を備える請求項１～７のいずれか１項に記載の医療画像処理装置。 The medical image according to any one of claims 1 to 7, further comprising: a setting unit configured to change the setting of the type of the abnormality identified in the second discrimination process or the classification of the progress degree identified in the third discrimination process. Processing unit.
  9. 　前記設定部は、前記第１照明光、前記第２照明光、または、前記第３照明光の各スペクトルもしくは組み合わせの設定を変更する請求項８に記載の医療画像処理装置。 The medical image processing apparatus according to claim 8, wherein the setting unit changes settings of each spectrum or combination of the first illumination light, the second illumination light, or the third illumination light.
  10. 　カルテを取得するカルテ取得部を備え、
    　前記設定部は、前記カルテが含む情報を用いて前記設定をする請求項８または９に記載の医療画像処理装置。     Equipped with a medical chart acquisition unit to acquire medical charts,
    The medical image processing apparatus according to claim 8, wherein the setting unit performs the setting using information included in the medical chart.
  11. 　前記設定部は、前記第２鑑別処理において特定する異常の種類に、前記カルテが含む情報によって定まる特定の病変を含める請求項８～１０のいずれか１項に記載の医療画像処理装置。 The medical image processing apparatus according to any one of claims 8 to 10, wherein the setting unit includes a specific lesion determined by information included in the medical chart in the type of abnormality specified in the second discrimination process.
  12. 　前記第１鑑別処理の結果、前記第２鑑別処理の結果、または、前記第３鑑別処理の結果を修正する鑑別結果修正部を備える請求項１～１１のいずれか１項に記載の医療画像処理装置。 The medical image processing according to any one of claims 1 to 11, further comprising: a discrimination result correction unit configured to correct the result of the second discrimination process or the result of the third discrimination process as a result of the first discrimination process. apparatus.
  13. 　前記第１鑑別処理の結果、前記第２鑑別処理の結果、または、前記第３鑑別処理の結果を報知する鑑別結果報知部を備える請求項１～１２のいずれか１項に記載の医療画像処理装置。 The medical image processing according to any one of claims 1 to 12, further comprising: a discrimination result notifying unit for notifying of a result of the first discrimination processing, a result of the second discrimination processing, or a result of the third discrimination processing. apparatus.
  14. 　被写体像を含む内視鏡画像を取得する内視鏡画像取得部と、
    　前記内視鏡画像のうち、特定のスペクトルを有する第１照明光を使用して撮影した第１内視鏡画像を用いて１または複数種類の第１異常領域を検出する第１鑑別処理を行う第１鑑別処理部と、
    　前記内視鏡画像のうち、前記第１照明光とはスペクトルが異なる第２照明光を使用して撮影した第２内視鏡画像を用いて、各々の前記第１異常領域が含む異常の種類を特定する第２鑑別処理を行う第２鑑別処理部と、
    　前記内視鏡画像のうち、前記第１照明光及び前記第２照明光とはスペクトルが異なる第３照明光を使用して撮影した第３医療画像を用いて、前記第１異常領域が含む異常の進行度を特定する第３鑑別処理部と、
    　を備える内視鏡装置。     An endoscopic image acquisition unit for acquiring an endoscopic image including a subject image;
    Performing a first discrimination process of detecting one or more types of first abnormal areas using a first endoscope image taken using the first illumination light having a specific spectrum among the endoscope images The first discrimination processing unit,
    Among the endoscopic images, types of abnormalities included in each of the first abnormal areas using a second endoscopic image taken using a second illumination light having a spectrum different from that of the first illumination light A second discrimination processing unit that performs a second discrimination process to identify
    An abnormality included in the first abnormal region using a third medical image captured using a third illumination light having a spectrum different from that of the first illumination light and the second illumination light among the endoscopic images A third discrimination processing unit that specifies the degree of progression of
    Endoscope apparatus provided with.
  15. 　前記第３鑑別処理部は、前記第２鑑別処理の結果を用いて前記第３医療画像を取得する際に用いる照明光のスペクトルを選択する請求項１４に記載の内視鏡装置。 The endoscope apparatus according to claim 14, wherein the third discrimination processing unit selects a spectrum of illumination light used when acquiring the third medical image using a result of the second discrimination processing.
PCT/JP2018/039920 2017-10-30 2018-10-26 Medical image processing device and endoscope device WO2019087971A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2019550327A JP6834019B2 (en) 2017-10-30 2018-10-26 Medical image processing equipment and endoscopic equipment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017209802 2017-10-30
JP2017-209802 2017-10-30

Publications (1)

Publication Number Publication Date
WO2019087971A1 true WO2019087971A1 (en) 2019-05-09

Family

ID=66333077

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/039920 WO2019087971A1 (en) 2017-10-30 2018-10-26 Medical image processing device and endoscope device

Country Status (2)

Country Link
JP (1) JP6834019B2 (en)
WO (1) WO2019087971A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020089710A (en) * 2018-12-04 2020-06-11 Hoya株式会社 Information processing device, processor for endoscope, information processing method, and program
WO2020116115A1 (en) * 2018-12-04 2020-06-11 Hoya株式会社 Information processing device and model generation method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006068488A (en) * 2004-08-31 2006-03-16 Olympus Corp Capsule type endoscope
JP2012016545A (en) * 2010-07-09 2012-01-26 Fujifilm Corp Endoscope apparatus
WO2015045576A1 (en) * 2013-09-26 2015-04-02 富士フイルム株式会社 Endoscope system, processor device for endoscope system, operation method for endoscope system, and operation method for processor device
JP2016077756A (en) * 2014-10-21 2016-05-16 富士フイルム株式会社 Endoscope system, processor device, operation method of endoscope system, and operation method of processor device

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010184057A (en) * 2009-02-13 2010-08-26 Fujifilm Corp Image processing method and device
JP5541914B2 (en) * 2009-12-28 2014-07-09 オリンパス株式会社 Image processing apparatus, electronic apparatus, program, and operation method of endoscope apparatus
JP2011250926A (en) * 2010-06-01 2011-12-15 Fujifilm Corp Electronic endoscope system
JP5502812B2 (en) * 2011-07-14 2014-05-28 富士フイルム株式会社 Biological information acquisition system and method of operating biological information acquisition system
JPWO2013136664A1 (en) * 2012-03-13 2015-08-03 コニカミノルタ株式会社 probe
US20150245769A1 (en) * 2012-09-24 2015-09-03 Konica Minolta, Inc. Optical Measurement Device And Probe System
CN108024689B (en) * 2015-09-24 2020-03-20 奥林巴斯株式会社 Endoscope device
JP6581923B2 (en) * 2016-03-03 2019-09-25 富士フイルム株式会社 Image processing apparatus, operating method thereof and operating program
JP6201095B1 (en) * 2016-04-27 2017-09-20 雫石　誠 Imaging module and imaging apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006068488A (en) * 2004-08-31 2006-03-16 Olympus Corp Capsule type endoscope
JP2012016545A (en) * 2010-07-09 2012-01-26 Fujifilm Corp Endoscope apparatus
WO2015045576A1 (en) * 2013-09-26 2015-04-02 富士フイルム株式会社 Endoscope system, processor device for endoscope system, operation method for endoscope system, and operation method for processor device
JP2016077756A (en) * 2014-10-21 2016-05-16 富士フイルム株式会社 Endoscope system, processor device, operation method of endoscope system, and operation method of processor device

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020089710A (en) * 2018-12-04 2020-06-11 Hoya株式会社 Information processing device, processor for endoscope, information processing method, and program
WO2020116115A1 (en) * 2018-12-04 2020-06-11 Hoya株式会社 Information processing device and model generation method
JP2020089711A (en) * 2018-12-04 2020-06-11 Hoya株式会社 Model generation method and program
JP2020089712A (en) * 2018-12-04 2020-06-11 Hoya株式会社 Information processing device, processor for endoscope, information processing method, and program
JP7015275B2 (en) 2018-12-04 2022-02-02 Hoya株式会社 Model generation method, teacher data generation method, and program

Also Published As

Publication number Publication date
JPWO2019087971A1 (en) 2020-10-22
JP6834019B2 (en) 2021-02-24

Similar Documents

Publication Publication Date Title
JP7296498B2 (en) Medical image processing device and endoscope device
US11132795B2 (en) Medical image processing apparatus
JPWO2018159363A1 (en) Endoscope system and operation method thereof
JP6920931B2 (en) Medical image processing equipment, endoscopy equipment, diagnostic support equipment, and medical business support equipment
JP7009636B2 (en) Endoscope system
US11449988B2 (en) Medical image processing apparatus
JP6785990B2 (en) Medical image processing equipment and endoscopic equipment
US20210158528A1 (en) Medical image processing system
WO2019087971A1 (en) Medical image processing device and endoscope device
JP6866497B2 (en) Medical image processing equipment and endoscopic equipment
US11830185B2 (en) Medical image processing system and learning method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18873162

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019550327

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18873162

Country of ref document: EP

Kind code of ref document: A1