CN115553764A - Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence - Google Patents
Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence Download PDFInfo
- Publication number
- CN115553764A CN115553764A CN202211029360.5A CN202211029360A CN115553764A CN 115553764 A CN115553764 A CN 115553764A CN 202211029360 A CN202211029360 A CN 202211029360A CN 115553764 A CN115553764 A CN 115553764A
- Authority
- CN
- China
- Prior art keywords
- image
- real
- light
- blood oxygen
- time
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 239000008280 blood Substances 0.000 title claims abstract description 45
- 210000004369 blood Anatomy 0.000 title claims abstract description 45
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 43
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 43
- 239000001301 oxygen Substances 0.000 title claims abstract description 43
- 238000003384 imaging method Methods 0.000 title claims abstract description 37
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 108010064719 Oxyhemoglobins Proteins 0.000 claims abstract description 26
- 108010054147 Hemoglobins Proteins 0.000 claims abstract description 13
- 102000001554 Hemoglobins Human genes 0.000 claims abstract description 13
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 11
- 238000002835 absorbance Methods 0.000 claims description 33
- 238000013507 mapping Methods 0.000 claims description 21
- 238000010521 absorption reaction Methods 0.000 claims description 15
- 230000003287 optical effect Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 230000003595 spectral effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 11
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 230000017531 blood circulation Effects 0.000 abstract description 6
- 210000000056 organ Anatomy 0.000 abstract description 6
- 238000002674 endoscopic surgery Methods 0.000 abstract description 4
- 238000012549 training Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 208000028867 ischemia Diseases 0.000 abstract description 3
- 206010061216 Infarction Diseases 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 230000007574 infarction Effects 0.000 abstract description 2
- 230000004089 microcirculation Effects 0.000 abstract description 2
- 230000035939 shock Effects 0.000 abstract description 2
- 238000001356 surgical procedure Methods 0.000 abstract description 2
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 238000005282 brightening Methods 0.000 abstract 1
- 230000031700 light absorption Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 11
- 210000001519 tissue Anatomy 0.000 description 5
- 210000003414 extremity Anatomy 0.000 description 4
- 206010021143 Hypoxia Diseases 0.000 description 3
- 239000002872 contrast media Substances 0.000 description 3
- 230000007954 hypoxia Effects 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000002583 angiography Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 208000001647 Renal Insufficiency Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 210000000624 ear auricle Anatomy 0.000 description 1
- 238000000799 fluorescence microscopy Methods 0.000 description 1
- 231100000086 high toxicity Toxicity 0.000 description 1
- MOFVSTNWEDAEEK-UHFFFAOYSA-M indocyanine green Chemical compound [Na+].[O-]S(=O)(=O)CCCCN1C2=CC=C3C=CC=CC3=C2C(C)(C)C1=CC=CC=CC=CC1=[N+](CCCCS([O-])(=O)=O)C2=CC=C(C=CC=C3)C3=C2C1(C)C MOFVSTNWEDAEEK-UHFFFAOYSA-M 0.000 description 1
- 229960004657 indocyanine green Drugs 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000000302 ischemic effect Effects 0.000 description 1
- 201000006370 kidney failure Diseases 0.000 description 1
- 238000002357 laparoscopic surgery Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000003333 near-infrared imaging Methods 0.000 description 1
- 238000002496 oximetry Methods 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 206010040560 shock Diseases 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and an imaging method based on artificial intelligence adopt a light absorption imaging brightening system and a two-dimensional real-time imaging system of oxyhemoglobin, and realize a high-precision reflective imaging oximeter which has noninvasive, real-time imaging and can eliminate light interference of an external environment. The method solves the problem of limitation of the monitoring range of the contact oximeter, and overcomes the defects of low precision and easy interference of an external light source of the non-contact reflection oximeter. And only need the narrowband filter in the training process, in case artificial intelligence model training is accomplished, can only realize blood oxygen formation of image with camera cooperation artificial intelligence model. The technical system can be expanded to scenes with more light source interference such as endoscopic surgery and the like, and can be used for monitoring the blood flow state of important organs in real time, not only for noninvasive blood vessel imaging, but also for monitoring microcirculation extravasated blood shock, organ ischemia infarction state evaluation in surgery and the like. Moreover, the mobile phone can be carried on the mobile phone to realize home health monitoring. The application range of the hemoglobin measurement system is further expanded, and the hemoglobin measurement system has great significance in real-time evaluation of the blood flow state of a human body, clinical operation and home health monitoring.
Description
Technical Field
The invention relates to the technical field of biological image processing, in particular to a noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and an imaging method based on artificial intelligence.
Background
Blood oxygen content is a physiological parameter commonly used in clinic, and is commonly used for evaluating the degree of hypoxia and ischemia of limb organs. With the development of electronic technology, blood oxygen content detection is no longer limited to invasive blood drawing detection, and portable oximeters based on the concept of "non-invasive" are also increasingly used for daily blood oxygen detection to assess the physiological condition of an individual. At present, transmission oximeters and reflection oximeters are relatively mature in development and widely applied in clinical practice.
The traditional invasive blood oxygen detection method needs arterial puncture, the process is painful and complex, the analysis is time-consuming, and the blood oxygen saturation cannot be detected in real time. Although such methods possess high accuracy, invasive detection may cause complications, and detection cannot be performed continuously in real time, and clinical application thereof is limited.
Although the transmission-type oximeter successfully avoids trauma and realizes real-time detection, the detection of the transmission-type oximeter is limited to the measurement site, the measurement range is small, the error under hypoxia is large, and the measurement of the blood oxygen saturation of large or thick local tissues or organs, such as forehead, abdomen, cerebral vessels, muscle vessels and the like, can only be performed at the extremity of the limb, such as fingers or earlobes, where incident light is conveniently transmitted. Meanwhile, the perspective oximeter is easily limited by the movement of the limbs of the human body, and the system consumes much energy, so that the perspective oximeter cannot be used for real-time detection of people in a large range.
Although the reflection oximeter also realizes non-invasive and real-time detection. However, the contact reflection oximeter is limited to detect flat parts of human skin, such as forehead, wrist, etc., and has a large error under low oxygen. The non-contact reflection type oximeter solves the physical limitation between a patient and the oximeter to a certain extent, and enlarges the detection range. However, the non-contact reflective oximeter is still not fully developed, the reflective oximeter probe can only receive reflected light, and most of the reflected light carrying physiological signals is easily interfered by external light, motion artifacts, power frequency noise and the like, the signal amplitude is small, the fluctuation is large, and the actually received useful signals are very weak. Therefore, the non-contact reflective blood oxygen detection method has low accuracy and poor real-time performance, and cannot perform effective blood oxygen detection under the action of external light and other interference factors, and the technical method needs to be further improved.
Moreover, most of the existing reflective blood oxygen detection devices need to shield ambient light interference when in use, and need to use special light sources, such as red light or near-infrared light. This means that in laparoscopic surgery, existing blood oxygen imaging systems require that the surgical lights be turned off while the red or near infrared imaging is turned on. It is imperative for the surgeon to pause the surgical procedure. Such oximetry imaging systems not only increase operational complexity, but also increase unpredictable risks while extending the time of the procedure.
In addition, in an endoscopic surgery scene, an indocyanine green contrast agent is a common angiography contrast agent currently used for near-infrared fluorescence imaging, but the contrast agent has relatively high toxicity and large side effects, and is easy to cause allergy, renal failure and even shock symptoms of a patient. The invasive nature and large side effects of angiographic agents limit their clinical practice. Meanwhile, the application of the reflective oximeter is also greatly limited under the illumination condition of the endoscopic surgery.
Therefore, it is of far-reaching significance to develop a non-contact reflective oximeter with high accuracy, which can perform non-invasive and real-time imaging and eliminate the interference of external ambient light.
Disclosure of Invention
In order to realize the technical problem of how to carry out noninvasive real-time accurate blood oxygen imaging on a human body and avoid the interference of an external light source, the invention provides an artificial intelligence-based noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and an imaging method, which can accurately position oxygenated hemoglobin and distinguish blood vessels from surrounding background tissues or be used for judging the degree of ischemia and hypoxia of the tissues.
The technical solution adopted by the invention is as follows: noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system based on artificial intelligence comprises the following modules:
the light source emission and image acquisition module: emitting light with specific intensity and containing specific wavelength, and respectively collecting light with specific wavelength related to oxyhemoglobin and background light images without any absorption peak wave band of oxyhemoglobin by the filtering function of the image collecting element;
an absorbance image processing and imaging module:
the light source emission and image acquisition module is connected with the light source emission and background light image processing module, and the hemoglobin absorbance image and the background light image are subjected to image processing based on artificial intelligence to obtain imaging of oxyhemoglobin in spatial distribution;
an image output module: the resulting spatial distribution image of absorbance is brightened by computer processing and overlaid in real time as a thermal map or pseudo-colour onto the image output of the scope.
The light source emission and image acquisition module comprises a 660nm narrow-band filter with the bandwidth of 10nm and a CCD or CMOS element without a Bayer array, the 660nm narrow-band filter with the bandwidth of 10nm filters specific wavelength, and an image with high hemoglobin absorbance and a background light image under the specific wavelength are obtained through the CCD or CMOS element without the Bayer array.
The light source emission and image acquisition module comprises a CCD or CMOS element containing a Bayer array, and an oxyhemoglobin absorbance image and a background light image are obtained by using the same CCD or CMOS element containing the Bayer array according to the mapping relation between the constructed full-color RGB pixel value and the absorbance image at 660 nm.
A non-invasive real-time non-contact anti-interference blood oxygen real-time imaging method comprises the following steps:
(1) Mapping construction of RGB pixel values under specific light wavelength and common illumination conditions: the RGB pixel values presented by the CCD/CMOS are presented under the irradiation of a light source containing an absorption peak, a full-color image is obtained, meanwhile, the RGB pixel values presented by the CCD/CMOS under the light with the wavelengths of 660nm and 600nm are measured, an image with high oxyhemoglobin absorbance is obtained, the image is input into a computer to construct an artificial intelligence model, and the mapping relation from the full-color image to the images with the wavelengths of 660nm and 600nm is respectively obtained. The artificial intelligence model is essentially a filter realized by software in the process and is a model for realizing the mapping from the supervised picture to the picture;
(2) When in use, the oxyhemoglobin absorption peak and the background light image are obtained according to the mapping relation: under the same light source used in model building, obtaining an oxyhemoglobin absorbance image by using the same CCD or CMOS element according to the mapping relation between full-color RGB pixel values built in advance and the absorbance image at 660nm, and under the same light source used in model building, obtaining a background light image by using the same CCD or CMOS element according to the mapping relation between full-color RGB pixel values built in advance and the absorbance image at 600nm to obtain a surrounding tissue background image;
(3) And (3) obtaining an absorption degree spatial distribution image through computer comparison: and (3) calculating the pixel values of the oxyhemoglobin absorbance image and the background light image according to the Lambert-beer law to obtain an absorbance spatial distribution image. Lambert-beer's law refers to the calculation of oxyhemoglobin (HbO) 2 ) And reducing the absorption difference of hemoglobin (Hb) to different wavelengths of light, collecting images of multiple wavelengths, and calculating to obtain blood oxygen value through image processing. The calculation of blood oxygen content is directly related to Optical Density (OD), which is defined as: OD = log (I) 0 I), OD represents the intensity of emergent light I relative to the intensity of incident light I 0 The attenuation of (2).
In the optical density calculation, the emergent light intensity I is the pixel value of the corresponding channel, and the incident light intensity I 0 The incident light intensity for the corresponding color wavelength range. The blood oxygen saturation is approximately in a linear relationship with the blood vessel Optical Density Ratio (ODR) at different wavelengths, as shown in the formula.
In the above formula, satO2 represents the blood oxygen saturation, ODR represents the optical density ratio of blood vessels at different wavelengths, I0|660nm is the intensity of incident light in the 660nm spectral range, I0|600nm is the intensity of incident light in the 600nm spectral range, and the intensity of incident light can be obtained by a light source spectrum measured in advance. I is 660 The nm is the emergent light absorbed by blood vessel in the spectral range of 660nm, I 600 The nm is emergent light under the spectral range of 600nm, and a and b are parameters used for linear fitting of the blood oxygen value and the ODR, and can be calibrated and measured through experiments.
(4) And (3) image output: the obtained blood oxygen saturation degree space distribution image is brightened through computer processing and is covered on the image output of the endoscope in a form of heat map or pseudo color in real time.
The invention has the beneficial effects that: the invention provides a noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and an imaging method based on artificial intelligence. The method solves the problem of limitation of the monitoring range of the contact oximeter, and overcomes the defects of low precision and easy interference of an external light source of the non-contact reflection oximeter. The technical system can be expanded to scenes with more light source interference, such as endoscopic surgery and the like, and can be used for monitoring the blood flow state of important organs in real time, so as to prevent the further deterioration of microcirculation extravasated blood shock and organ ischemic infarction. The application range of the hemoglobin measurement system is further improved, and the hemoglobin measurement system has important significance for real-time evaluation of the blood flow state of a human body and clinical operation.
Drawings
FIG. 1 is a flow chart of example 1 of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following embodiments and the accompanying drawings, it being understood that the drawings and the following embodiments are illustrative of the invention only and are not limiting thereof.
Example 1:
bayer array oxyhemoglobin absorbance based imaging without narrow band filters
Bayer array is one of the main technologies that realize CCD or CMOS sensors to capture color images. It is a 4 x 4 array, which is composed of 8 green, 4 blue and 4 red pixels, and when converting the gray pattern into color picture, it will use 2 x 2 matrix to do 9 operations, and finally generate a color pattern. A color pattern can be viewed as comprising the sum of the various visible wavelength bands, so that the narrow band filters can be replaced by bayer arrays having different transmittances for different wavelength bands. Alternatively, the acquisition of the specific wavelength band absorbance image may be performed by a pre-established mapping from the full-color image to the specific wavelength image, also under surgical light. Compared with the original scheme, the scheme only needs the narrow-band filter when the mapping is established, has the characteristic that special equipment does not need to be replaced when in use, and can even realize blood oxygen imaging by using a mobile phone camera theoretically.
The method comprises the following steps: the mapping of the specific light wavelength and the RGB pixel value under the common illumination condition is constructed to show the RGB pixel value shown by the CCD/CMOS under the illumination of a light source containing an absorption peak, a full-color image is obtained, the RGB pixel values shown by the CCD/CMOS under the light with the wavelength of 660nm and 600nm are measured at the same time, an image with high oxyhemoglobin absorbance is obtained, the image is input into a computer to construct an artificial intelligence model, and the mapping relation from the full-color image to the images with the wavelength of 660nm and 600nm is obtained respectively. The artificial intelligence model is essentially a filter realized by software in the process, and a supervised image-to-image mapping model is realized.
And step two, obtaining an oxyhemoglobin absorption peak and a background light image according to the mapping relation during use.
1, obtaining an oxyhemoglobin absorbance image using the same CCD or CMOS device according to the mapping relationship between the full color RGB pixel values constructed in advance and the absorbance image thereof at 660nm under the same light source used in constructing the model.
2. Under the same light source used in model building, a background light image is obtained by using the same CCD or CMOS element according to the mapping relation of full-color RGB pixel values built in advance and the absorbance image at 600nm, so as to obtain the background image of the surrounding tissues.
Step three, obtaining an absorption degree space distribution image by computer contrast
And obtaining an absorbance space distribution image according to the pixel values of the oxyhemoglobin absorbance image and the background light image according to the Lambert-beer law. Lambert-beer's law refers to the calculation of oxyhemoglobin (HbO) 2 ) And reducing the absorption difference of hemoglobin (Hb) to different wavelengths of light, collecting images of multiple wavelengths, and calculating to obtain blood oxygen value through image processing. The calculation of blood oxygen content is directly related to Optical Density (OD), which is defined as: OD = log (I) 0 I), OD represents the intensity of emergent light I relative to the intensity of incident light I 0 The attenuation of (2).
In the calculation of optical density, the emergent light intensity I is the pixel value of the corresponding channel, and the incident light intensity I 0 The intensity of the incident light for the corresponding color wavelength range.The blood oxygen saturation is approximately in a linear relationship with the blood vessel Optical Density Ratio (ODR) at different wavelengths, as shown in the formula.
In the above formula, satO2 represents the blood oxygen saturation, ODR represents the optical density ratio of blood vessels at different wavelengths, I0|660nm is the intensity of incident light in the 660nm spectral range, I0|600nm is the intensity of incident light in the 600nm spectral range, and the intensity of incident light can be obtained by a light source spectrum measured in advance. I is 660 The nm is the emergent light absorbed by blood vessel in the spectral range of 660nm, I 600 The nm is emergent light under the spectral range of 600nm, and a and b are parameters used for linear fitting of the blood oxygen value and the ODR, and can be calibrated and measured through experiments.
Step four, image output
The resulting spatial distribution image of absorbance is brightened by computer processing and overlaid in real time as a thermal map or pseudo-colour onto the image output of the scope.
Conclusion
The innovative point of the application realizes a brand-new blood oxygen imaging system capable of avoiding the interference of an external light source, and can display the distribution information of oxygenated hemoglobin in the space to image the blood flow in real time.
The invention is characterized in that the real-time imaging aiming at the blood flow space distribution can be realized by comparing and processing the image with higher oxyhemoglobin absorbance and the background image through a computer. And special hardware is needed only in the training process, once the artificial intelligence model training is completed, blood oxygen imaging can be realized by using a common camera. The angiography is realized in a non-invasive and non-side-effect mode, and the problem that the existing reflection type oximeter and the existing perspective type oximeter are easily interfered by an external light source is solved.
The skilled person should understand that: although the invention has been described in terms of the above specific embodiments, the inventive concept is not limited thereto and any modification applying the inventive concept is intended to be included within the scope of the patent claims.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (4)
1. The noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system based on artificial intelligence is characterized by comprising the following modules:
the light source emission and image acquisition module: emitting light with specific intensity and specific wavelength, and respectively collecting light with specific wavelength related to oxyhemoglobin and background light images without any absorption peak wave band of oxyhemoglobin by the filtering function of an image collecting element;
the absorption image processing and imaging module comprises: the light source emission and image acquisition module is connected with the light source emission and background light image processing module, and the hemoglobin absorbance image and the background light image are subjected to image processing based on artificial intelligence to obtain imaging of oxyhemoglobin in spatial distribution;
an image output module: the resulting absorbance spatial distribution image is brightened by computer processing and overlaid in real time onto the image output of the scope in the form of a thermal map or pseudo-colour.
2. The artificial intelligence based non-invasive real-time non-contact anti-interference blood oxygen real-time imaging system according to claim 1, wherein the light source emission and image collection module comprises a 660nm narrow band filter with a bandwidth of 10nm and a CCD or CMOS device without bayer array, the 660nm narrow band filter with a bandwidth of 10nm filters a specific wavelength, and an image with high hemoglobin absorbance at the specific wavelength and a background light image are obtained by the CCD or CMOS device without bayer array.
3. The artificial intelligence based non-invasive real-time non-contact anti-interference blood oxygen real-time imaging system according to claim 1, wherein the light source emission and image acquisition module comprises a CCD or CMOS element comprising bayer array, and the same CCD or CMOS element comprising bayer array is used to obtain the oxyhemoglobin absorbance image and the background light image according to the mapping relationship between the constructed full-color RGB pixel values and the absorbance image at 660 nm.
4. An imaging method using the imaging system of claim 1, comprising the steps of:
(1) Mapping construction of RGB pixel values under specific light wavelength and common illumination conditions: displaying RGB pixel values displayed by a CCD/CMOS under the irradiation of a light source containing an absorption peak to obtain a full-color image, simultaneously measuring the RGB pixel values displayed by the CCD/CMOS under 660nm and 600nm wavelength light to obtain an image with higher oxyhemoglobin absorbance, inputting the image into a computer to construct an artificial intelligence model, and respectively obtaining the mapping relation from the full-color image to 660nm and 600nm wavelength images;
(2) When in use, the oxyhemoglobin absorption peak and the background light image are obtained according to the mapping relation: under the same light source used in model building, obtaining an oxyhemoglobin absorbance image by using the same CCD or CMOS element according to the mapping relation between full-color RGB pixel values built in advance and the absorbance image at 660nm, and under the same light source used in model building, obtaining a background light image by using the same CCD or CMOS element according to the mapping relation between full-color RGB pixel values built in advance and the absorbance image at 600nm to obtain a surrounding tissue background image;
(3) And (3) obtaining an absorption degree spatial distribution image through computer comparison: calculating the pixel values of the oxyhemoglobin absorbance image and the background light image according to Lambert-beer's law, which is to calculate oxyhemoglobin (HbO) 2 ) And reducing the absorption difference of hemoglobin (Hb) to different wavelengths, collecting multiple wavelength images, calculating blood oxygen value, calculating blood oxygen content and optical densityThe values (Optical Density, OD) are directly related, the Optical Density value OD being defined as: OD = log (I) 0 I), OD represents the intensity of emergent light I relative to the intensity of incident light I 0 The attenuation of (2);
in the optical density calculation, the emergent light intensity I is the pixel value of the corresponding channel, and the incident light intensity I 0 For the incident light intensity corresponding to the color wavelength range, the blood oxygen saturation and the blood vessel optical density ratio under different wavelengths are approximately in a negative correlation linear relationship, as shown in the formula:
in the above formula, satO2 represents the blood oxygen saturation, ODR represents the optical density ratio of blood vessels at different wavelengths, I0|660nm is the incident light intensity under the 660nm spectral range, I0|600nm is the incident light intensity under the 600nm spectral range, the incident light intensity can be obtained by the light source spectrum measured in advance, I0|600nm is the light intensity of the light source spectrum measured in advance, and 660 the nm is the emergent light absorbed by blood vessel in the spectral range of 660nm, I 600 The nm is emergent light in a spectral range of 600nm, a and b are parameters used for linear fitting of a blood oxygen value and an ODR (optical Density rating) and can be calibrated and measured through experiments;
(4) And (3) image output: the resulting spatial distribution image of absorbance is brightened by computer processing and overlaid in real time as a thermal map or pseudo-colour onto the image output of the scope.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211029360.5A CN115553764A (en) | 2022-08-23 | 2022-08-23 | Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211029360.5A CN115553764A (en) | 2022-08-23 | 2022-08-23 | Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115553764A true CN115553764A (en) | 2023-01-03 |
Family
ID=84739420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211029360.5A Pending CN115553764A (en) | 2022-08-23 | 2022-08-23 | Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115553764A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2281504A1 (en) * | 2009-08-04 | 2011-02-09 | Pulsion Medical Systems AG | Apparatus and method for determining a physiological parameter |
| US20110275932A1 (en) * | 2009-01-20 | 2011-11-10 | Frederic Leblond | Method And Apparatus For Depth-Resolved Fluorescence, Chromophore, and Oximetry Imaging For Lesion Identification During Surgery |
| CN104856691A (en) * | 2014-02-21 | 2015-08-26 | 谢亚男 | Retina blood oxygen saturation measurement method based on fundus cameras |
| CN105395184A (en) * | 2015-12-04 | 2016-03-16 | 华中科技大学 | Biological tissue blood flow, blood oxygen and blood volume multi-parameter detection method and device |
| CN107205701A (en) * | 2014-11-14 | 2017-09-26 | 张文瀚 | Device and method to detect blood oxygen concentration and/or cephalophyma |
| CN110755090A (en) * | 2019-11-15 | 2020-02-07 | 合肥师范学院 | Human body blood oxygen saturation measuring method based on network camera |
| CN111387992A (en) * | 2020-02-14 | 2020-07-10 | 河南大学 | Thin-layer tissue blood oxygen imaging method and device based on Lambert beer law |
| CN211094138U (en) * | 2019-07-08 | 2020-07-28 | 北京大学 | Retina blood oxygen saturation measurement system based on single-lens reflective camera |
| CN111956234A (en) * | 2020-08-19 | 2020-11-20 | 英诺激光科技股份有限公司 | Accurate blood oxygen saturation measuring method and device based on photoacoustic technology |
| CN112168180A (en) * | 2020-09-24 | 2021-01-05 | 上海交通大学 | Tissue blood oxygen imaging detection method based on two-stage space mapping |
-
2022
- 2022-08-23 CN CN202211029360.5A patent/CN115553764A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110275932A1 (en) * | 2009-01-20 | 2011-11-10 | Frederic Leblond | Method And Apparatus For Depth-Resolved Fluorescence, Chromophore, and Oximetry Imaging For Lesion Identification During Surgery |
| EP2281504A1 (en) * | 2009-08-04 | 2011-02-09 | Pulsion Medical Systems AG | Apparatus and method for determining a physiological parameter |
| CN104856691A (en) * | 2014-02-21 | 2015-08-26 | 谢亚男 | Retina blood oxygen saturation measurement method based on fundus cameras |
| CN107205701A (en) * | 2014-11-14 | 2017-09-26 | 张文瀚 | Device and method to detect blood oxygen concentration and/or cephalophyma |
| CN105395184A (en) * | 2015-12-04 | 2016-03-16 | 华中科技大学 | Biological tissue blood flow, blood oxygen and blood volume multi-parameter detection method and device |
| CN211094138U (en) * | 2019-07-08 | 2020-07-28 | 北京大学 | Retina blood oxygen saturation measurement system based on single-lens reflective camera |
| CN110755090A (en) * | 2019-11-15 | 2020-02-07 | 合肥师范学院 | Human body blood oxygen saturation measuring method based on network camera |
| CN111387992A (en) * | 2020-02-14 | 2020-07-10 | 河南大学 | Thin-layer tissue blood oxygen imaging method and device based on Lambert beer law |
| CN111956234A (en) * | 2020-08-19 | 2020-11-20 | 英诺激光科技股份有限公司 | Accurate blood oxygen saturation measuring method and device based on photoacoustic technology |
| CN112168180A (en) * | 2020-09-24 | 2021-01-05 | 上海交通大学 | Tissue blood oxygen imaging detection method based on two-stage space mapping |
Non-Patent Citations (1)
| Title |
|---|
| 郑田莉;罗春华;朱海龙;付威威;: "双波长视网膜血氧饱和度测量仪光学***设计与仿真", 长春理工大学学报(自然科学版), no. 06, 15 December 2018 (2018-12-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5408998A (en) | Video based tissue oximetry | |
| US10709342B2 (en) | System and method for spatial cardiovascular monitoring | |
| US8398556B2 (en) | Systems and methods for non-invasive continuous blood pressure determination | |
| Martinez et al. | Optimal wavelength selection for noncontact reflection photoplethysmography | |
| RU2677765C2 (en) | System for screening of state of oxygenation of subject | |
| CN104968259B (en) | System and method for the vital sign information for determining object | |
| CN105813564A (en) | Device and method for determining vital signs of a subject | |
| US20070024946A1 (en) | Hyperspectral/multispectral imaging in determination, assessment and monitoring of systemic physiology and shock | |
| CN108471989A (en) | The equipment, system and method for the photo-plethysmographic image of vital sign information for generating carrying object | |
| US20130274610A1 (en) | Method and a system for visualization of cardiovascular pulsation waves | |
| EP2346387A1 (en) | Blood analysis | |
| US20200352487A1 (en) | Trans-abdominal fetal pulse oximetry and/or uterine tone determination devices and systems with adjustable components and methods of use thereof | |
| Hu et al. | Opto‐Physiological Modeling Applied to Photoplethysmographic Cardiovascular Assessment | |
| Spigulis | Biophotonic technologies for non-invasive assessment of skin condition and blood microcirculation | |
| CN115770027A (en) | Blood pressure detection method and device based on artificial intelligence | |
| Sinhal et al. | Estimating vital signs through non-contact video-based approaches: A survey | |
| Allen | Photoplethysmography for the assessment of peripheral vascular disease | |
| CN115553764A (en) | Noninvasive real-time non-contact anti-interference blood oxygen real-time imaging system and imaging method based on artificial intelligence | |
| CN116250815A (en) | Non-contact blood pressure monitoring method and device based on multispectral pulse wave | |
| CN109009050B (en) | Anti-motion interference reflective pulse rate signal detection device based on optical method | |
| Zhu et al. | Non-contact detection of cardiac rate based on visible light imaging device | |
| JP7520023B2 (en) | Apparatus, system and method for determining physiological information - Patents.com | |
| AU2013202796B2 (en) | Hyperspectral/multispectral imaging in determination, assessment and monitoring of systemic physiology and shock | |
| Clancy et al. | Registration and analysis of multispectral images acquired during uterine transplantation surgery | |
| Xiao et al. | Combination of denoising algorithms for video-based non-contact heart rate measurement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |