CN113689355A - Image processing method, image processing device, storage medium and computer equipment - Google Patents
Image processing method, image processing device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113689355A CN113689355A CN202111059740.9A CN202111059740A CN113689355A CN 113689355 A CN113689355 A CN 113689355A CN 202111059740 A CN202111059740 A CN 202111059740A CN 113689355 A CN113689355 A CN 113689355A
- Authority
- CN
- China
- Prior art keywords
- medical image
- strengthened
- enhanced
- contour region
- image
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 101
- 238000003672 processing method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 34
- 230000002787 reinforcement Effects 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 12
- 230000007547 defect Effects 0.000 claims description 44
- 238000005728 strengthening Methods 0.000 claims description 20
- 210000000056 organ Anatomy 0.000 claims description 18
- 239000000654 additive Substances 0.000 claims description 16
- 230000000996 additive effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 abstract description 10
- 201000010099 disease Diseases 0.000 abstract description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 6
- 210000004204 blood vessel Anatomy 0.000 description 42
- 230000003902 lesion Effects 0.000 description 28
- 208000024891 symptom Diseases 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000002107 myocardial effect Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 230000009469 supplementation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 208000007536 Thrombosis Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G06T2207/10072—Tomographic images
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application discloses an image processing method, an image processing device, a storage medium and computer equipment, wherein the method in the embodiment of the application comprises the following steps: acquiring a medical image to be processed; in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed; acquiring the associated information of the object to be strengthened; and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a reinforced medical image. Therefore, the medical image to be processed is subjected to enhancement processing, so that the processed medical image is convenient to identify and disease diagnosis is convenient to carry out according to the processed medical image.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, a storage medium, and a computer device.
Background
At present, medical images are usually identified and analyzed through AI identification, but because the accuracy of an identification algorithm is low, the identified image information is incomplete or unclear, that is, whether a focus exists in the medical image or not can not be determined according to the image information, or the type of the focus can not be determined, so that medical staff can not diagnose diseases according to the medical images.
Disclosure of Invention
The embodiment of the application provides an image processing method, an image processing device, a storage medium and computer equipment, which can perform strengthening processing on a medical image to obtain a clear medical image and perform disease diagnosis according to the processed medical image.
In a first aspect, an embodiment of the present application provides an image processing method, including:
acquiring a medical image to be processed;
in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed;
acquiring the associated information of an object to be strengthened;
and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
In a second aspect, an embodiment of the present application further provides an image processing apparatus, including:
the image acquisition module is used for acquiring a medical image to be processed;
the instruction processing module is used for responding to the received instruction to be enhanced and determining an object to be enhanced from the medical image to be enhanced;
the relevant information acquisition module is used for acquiring relevant information of an object to be strengthened;
and the image processing module is used for carrying out reinforcement processing on the object to be reinforced according to the associated information to obtain the medical image after the reinforcement processing.
In a third aspect, embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute an image processing method as provided in any embodiment of the present application.
In a fourth aspect, an embodiment of the present application further provides a computer device, including a processor and a memory, where the memory has a computer program, and the processor is configured to execute the image processing method according to any embodiment of the present application by calling the computer program.
According to the technical scheme provided by the embodiment of the application, the medical image to be processed is obtained; in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed; acquiring the associated information of an object to be strengthened; and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing. Based on the scheme, the medical image is subjected to strengthening treatment, so that the treated medical image is easy to identify, medical workers can conveniently diagnose diseases according to the medical image, and the defect of low AI identification accuracy is overcome.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a first image processing method according to an embodiment of the present application.
Fig. 2 is a schematic flowchart of a second image processing method according to an embodiment of the present application.
Fig. 3 is a schematic flowchart of a third image processing method according to an embodiment of the present application.
Fig. 4 is a fourth flowchart illustrating an image processing method according to an embodiment of the present application.
Fig. 5 is a schematic structural diagram of a myocardial bridge according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The embodiment of the present application provides an image processing method, and an execution subject of the image processing method may be the image processing apparatus provided in the embodiment of the present application, or a computer device integrated with the image processing apparatus, where the image processing apparatus may be implemented in a hardware or software manner. The computer device may be a smart phone, a tablet computer, a palm computer, a notebook computer, or a desktop computer.
Referring to fig. 1, fig. 1 is a first flowchart illustrating an image processing method according to an embodiment of the present disclosure. The specific flow of the image processing method provided by the embodiment of the application can be as follows:
101. acquiring a medical image to be processed.
The computer equipment can acquire the medical image to be processed from other storage media storing the medical image to be processed; the computer equipment can also have a medical image shooting function, and automatically identifies the medical image after the medical image is shot; the computer device can also be connected with a scanning instrument, and when the scanning instrument scans data, the image is presented in the computer device.
Since there are many ways in which the computer device can acquire the medical image to be processed, it is not described in detail here.
Optionally, in an embodiment, acquiring the medical image to be processed includes:
acquiring an original medical image;
and determining an image comprising the organ area from the original medical image, and taking the image comprising the organ area as a medical image to be processed.
The original medical image may be a scanned image such as a CT image, an MR image, an ultrasound image, or the like.
For example, if the computer device acquires a scanned image such as a CT image, an MR image, an ultrasound image, etc., the scanned image may be segmented by using a deep learning neural network algorithm such as a binary algorithm, a U-net network model, etc., so as to obtain an organ image in the scanned image, and the segmented organ image may be used as a medical image to be processed.
For another example, if the computer device acquires an image obtained by segmenting the scanned image, the image may be directly used as the medical image to be processed.
In another embodiment, the medical image to be processed may also be a medical image reconstructed by an AI algorithm.
After the original medical image is reconstructed through the AI algorithm, the processed medical image still has defects, and the processed medical image needs to be enhanced through the scheme of the application, so that the defects of AI reconstruction processing are complemented.
102. In response to the received instruction to be enhanced, an object to be enhanced is determined from the medical image to be processed.
After the medical image to be processed is acquired, the medical staff can issue the instruction to be enhanced to the computer equipment by operating the computer equipment, and the computer equipment responds to the instruction to be enhanced after receiving the instruction to be enhanced and executes the operation corresponding to the instruction to be enhanced. After the medical staff issues the instruction to be enhanced, the computer equipment responds to the instruction to be enhanced and can select the object to be enhanced in the medical image to be processed.
For example, a user may click or touch the contour of the suspected lesion in the medical image to be processed by a mouse, and then issue a command to be enhanced to the computer device in a click manner, and the computer device responds to the command to be enhanced and synchronously clicks the contour of the suspected lesion in the medical image to be processed, and then takes the contour as an object to be enhanced.
For another example, the user may select an image area of a suspected lesion by operating a mouse frame of the computer device, and then issue a command to be enhanced to the computer device in a frame selection manner, and the computer device responds to the command to be enhanced and synchronizes frame selection operations of the suspected lesion area in the medical image to be processed, and then takes the image area selected by the frame as an object to be enhanced.
Based on the above, the determination of the object to be strengthened is based on the selection of the user, and the selection mode is various, such as clicking, frame selection, etc., and the selection mode is based on the instruction to be strengthened issued by the user.
103. And acquiring the associated information of the object to be strengthened.
The method comprises the steps of identifying an object to be strengthened, obtaining associated information with high relevance around the object to be strengthened, and strengthening the object to be strengthened through the associated information. The related information may be a shape complementary to the object to be strengthened, or may have a similar characteristic to the object to be strengthened, so long as the related information has a relationship with the object to be strengthened to some extent.
In some embodiments, obtaining the association information of the object to be strengthened includes:
1031. and determining the defect type of the object to be strengthened according to the original image of the object to be strengthened.
The object to be enhanced may have a plurality of different types of defects, for example, if the object to be enhanced is an organ region, and the organ region is compared with the original image thereof, the types of defects that may exist are: the original image is blurred, the organ area has the problem of incomplete contour compared with the original image, the organ area has unclear contour line overlapping compared with the original image, and the like.
1032. Determining a contour region of an object to be strengthened, and enlarging the contour region along a direction far away from the contour region according to a first preset threshold value to obtain a strengthened region.
In this embodiment, a reinforced area is selected based on a contour area of an object to be reinforced, wherein the expansion direction may be a contour peripheral area, and by expanding the range of the contour area, information supplementation can be conveniently performed on the contour area subsequently, so as to supplement information missing from the object to be reinforced.
The first preset threshold refers to an outward extending distance, and the distance may be determined according to a contour region range of the object to be strengthened, for example, if the contour region is large, the first preset threshold is increased, and if the contour region is small, the first preset threshold is decreased; or the first preset threshold is set by a user in a self-defined way.
Therefore, the first preset threshold is not numerically limited in this embodiment, as long as a reasonable reinforced area can be obtained.
1033. And determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
In this embodiment, each voxel point of the medical image to be processed has an identification probability value, and different organs are distinguished by the identification probability values.
The voxel is an abbreviation of Volume element (Volume Pixel), and is the minimum unit of digital data in three-dimensional space segmentation.
Based on the identification probability value of the voxel point of the object to be strengthened, a related voxel point can be determined from the strengthened region according to the defect type, wherein the related voxel point is close to the identification probability value of the object to be strengthened.
104. And performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
The information complement can be carried out on the object to be strengthened through the associated information, so that the defect of the object to be strengthened is overcome, and the object to be strengthened is clearer and more complete.
If the object to be enhanced is a medical image reconstructed by an AI algorithm, the object to be enhanced is enhanced in order to repair a part of the object with weaker information, so as to enhance or correct the information, and further improve the information content of the object to be enhanced, so that the information content of the object to be enhanced which is visually visible is improved.
If the object to be enhanced is an image obtained by segmenting the original medical image, the image quality is improved by processing the image according to the resolution and the like of the object to be enhanced, or the information content of the object to be enhanced is increased, so that the visually visible information content of the object to be enhanced is improved.
In particular implementation, the present application is not limited by the execution sequence of the described steps, and some steps may be performed in other sequences or simultaneously without conflict.
As can be seen from the above, the image processing method provided in the embodiment of the present application, by obtaining the relevant information related to the object to be enhanced and performing enhancement processing on the object to be enhanced through the relevant information, can make the medical image after enhancement processing clear and complete, and is convenient for medical staff to diagnose according to the medical image after enhancement processing, thereby identifying the focus and the type of the focus.
According to the method described in the foregoing embodiment, it can be known that the medical image to be processed includes an organ, wherein the organ may be a blood vessel, a liver, a lung, a head and neck, and the like, and since there are many organs of a human body, the method of the present application can be applied to the aspect of the image to be processed including the organs of the human body, and therefore, only one of the organs is used in the following embodiment to explain the solution of the present application, and the blood vessel is used in the following embodiment as an example for explanation.
In the present application, three defect types of blood vessels and a strengthening treatment method performed for the three defect types are listed, and the following examples will be described in further detail.
Referring to fig. 2, fig. 2 is a second flow chart of the image processing method according to the embodiment of the invention. The method comprises the following steps:
201. acquiring a medical image to be processed.
Wherein the medical image to be processed comprises a blood vessel.
202. In response to the received instruction to be enhanced, an object to be enhanced is determined from the medical image to be processed.
The images around the blood vessel can be selected through clicking or frame selection operation of a user, and then a part needing reinforcement is selected as an object to be reinforced.
203. And determining the defect type of the object to be strengthened according to the original image of the object to be strengthened.
In this embodiment, the defect type is a first predetermined type, and the first predetermined type refers to a suspected lesion. For example, a small bump exists at a blood vessel position in the medical image, and the small bump may be a lesion or a bump caused by local high pressure, so that it cannot be determined whether the small bump is a lesion, and the small bump is set as a suspected lesion.
204. Determining a contour region of an object to be strengthened, and enlarging the contour region along a direction far away from the contour region according to a first preset threshold value to obtain a strengthened region.
In this embodiment, the reinforced region is obtained by expanding a fixed distance along the outside of the contour region.
The first preset threshold is a fixed distance, and the contour region is appropriately enlarged to facilitate analysis of an object to be enhanced of the suspected lesion.
205. And determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
In this embodiment, if the object to be enhanced is a suspected lesion, the contour region of the object to be enhanced needs to be enhanced, and the voxel point adjacent to the contour region in the enhanced region is used as the related voxel point.
206. And when the defect type is the first preset type, determining an additive voxel point from the associated voxel points according to a second preset threshold value.
The second preset threshold may be a range of the recognition probability value, or may also be a specific numerical value, and a specific setting manner may be self-defined, which is not limited herein.
For example, when the recognition probability value of the lesion at the blood vessel ranges from 2.0 to 3.0, the second preset threshold may be set to 2.0 to 3.0, and the associated voxel point having the recognition probability value ranging from 2.0 to 3.0 may be used as the additive voxel point. It should be understood that the description is only used as an example, and is not used to limit the recognition probability value of the voxel point of the object to be enhanced in the embodiment.
For another example, when the recognition probability value of the lesion at the blood vessel is in the range of 2.0 to 3.0, the preset threshold may be set to 0.2, and the associated voxel point having the recognition probability value in the range of 0.8 to 3.2 may be taken as the additive voxel point.
Further embodiments are provided in which, based on the setting of the second preset threshold, determining an additive voxel point is determined, wherein, in an embodiment, when the defect type is the first preset type, determining the additive voxel point from the associated voxel points according to the second preset threshold includes:
2061. and acquiring the correlation prime point with the highest correlation with the contour region from the reinforced region.
The voxel points adjacent to the contour region are set to have high relevance with the contour region, and the voxel points with high relevance with the contour region are screened from the reinforced region to be used as the relevant voxel points. Wherein, different profile region positions correspond to different associated prime points.
For example, the coordinate position of the first voxel point on the outline area is (x, y), and the coordinate positions adjacent to (x, y) are three, wherein the coordinate position of the second voxel point is (x +1, y-1), and the second voxel point is located in the enhanced area, and the second voxel point is taken as the voxel point having the highest correlation with the first voxel point.
2062. A difference value of the recognition probability values between the associated voxel points having the highest relevance and the contour region is calculated.
And after determining the associated voxel points of all the voxel points on the contour region according to the coordinate positions of the voxel points, calculating the difference value of the identification probability values between each group of voxel points with the highest association. And each group of voxel points with the highest relevance are adjacent on the coordinate position, and two adjacent voxel points are respectively positioned in the contour region and the reinforced region.
For example, the first voxel point and the second voxel point are used as a group of voxel points having the highest relevance, and the difference between the recognition probability values of the first voxel point and the second voxel point is calculated.
And taking the associated voxel point with the difference value smaller than a second preset threshold value as an added voxel point.
The second preset threshold refers to a specific numerical value, and the magnitude of the numerical value can be set by a user, which is not limited herein, for example, when the second preset threshold is 0.3, and the difference between the recognition probability values of the first voxel point and the second voxel point is 0.2, the second voxel point is taken as an added voxel point.
Since there are various ways to set the second preset threshold, it is sufficient that the additional voxel points can be selected from the associated voxel points by setting the second preset threshold.
207. And supplementing the additive element points to the object to be enhanced to obtain the enhanced medical image.
And after the added voxel points are supplemented to the object to be strengthened, performing voxel point supplementation on the outline of the object to be strengthened to enable the outline of the object to be strengthened with the suspected focus to be clearer, and further facilitating medical staff to judge whether the focus exists in the processed medical image.
In some embodiments, after obtaining the enhanced medical image, the method further includes:
judging whether an object to be enhanced in the medical image after the enhancement processing is a focus;
if the disease is a focus, analyzing the focus;
if the focus is not the focus, judging whether to continue to perform strengthening treatment on the object to be strengthened;
if the object to be enhanced needs to be enhanced, the step 204 and 207 is continued until it can be determined whether the object to be enhanced is a lesion.
In this embodiment, the medical image after the enhancement processing is verified, and then whether the object to be enhanced still has a defect is continuously judged, and when the defect exists, the object to be enhanced is continuously enhanced, so that the final result can clearly identify the original suspected focus part, and further determine whether the object is a focus, thereby optimizing the image processing flow.
As can be seen from the above, the image processing method provided in the embodiment of the present invention supplements the relevant voxel points with high relevance to the object to be enhanced, and further supplements the key information of the object to be enhanced, so that the contour of the object to be enhanced is clearer, and the medical staff can conveniently identify whether the object is a focus.
Referring to fig. 3, fig. 3 is a third flow chart of the image processing method according to the embodiment of the invention. The method comprises the following steps:
301. acquiring a medical image to be processed.
Wherein the medical image to be processed comprises a blood vessel.
302. In response to the received instruction to be enhanced, an object to be enhanced is determined from the medical image to be processed.
The images around the blood vessel can be selected through clicking or frame selection operation of a user, and then a part needing reinforcement is selected as an object to be reinforced.
303. And determining the defect type of the object to be strengthened according to the original image of the object to be strengthened.
In this embodiment, the defect type is a second predetermined type, the second predetermined type refers to a fuzzy symptom, and the fuzzy symptom refers to an unclear symptom of the lesion, or an unclear boundary between the lesion and the blood vessel, or an unclear symptom of the blood vessel.
For example, the contrast between the lesion area and the blood vessel is weak, and the lesion and the blood vessel cannot be distinguished;
for another example, when a scanned image is cut, the boundary between a blood vessel and a focus is inaccurate due to inaccurate cutting;
for another example, some artifacts exist near blood vessels, which further cause the blurring of the symptoms of the blood vessels, wherein the artifacts refer to virtual images appearing on the images due to problems of human breathing, local wiggling and the like; alternatively, local dilation of the vessel occurs due to vessel occlusion, which also results in blurring of the vessel's signs.
Wherein, the signs refer to the boundary, width, bending and other morphological characteristics of the focus or the blood vessel.
304. Determining a contour region of an object to be strengthened, and enlarging the contour region along a direction far away from the contour region according to a first preset threshold value to obtain a strengthened region.
In this embodiment, the enhancement processing is performed on the object to be enhanced, and when the lesion is blurred, the region within the contour region and the region inside the contour region are set as enhancement regions based on the contour region, or the region on both sides of the contour region and the regions on both sides of the contour region are set as enhancement regions, and the lesion is further subjected to sharpness enhancement processing.
When the reinforced area is the area of the object to be reinforced, the first preset threshold value can be determined according to the range of the outline area;
when the reinforced area is the outline area and the areas on two sides of the outline area, the first preset threshold has two positive and negative values which respectively represent the inward shrinking distance and the outward expanding distance.
305. And determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
In this embodiment, the voxel points in the enhancement region including the contour region are used as related voxel points, and the focus is further subjected to sharpness restoration processing.
306. And performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
By performing definition restoration processing on an object to be enhanced, the boundary between a focus and a blood vessel can be distinguished, or the contour of the focus can be restored.
Since there are various methods for performing sharpness restoration on the associated voxel point, three sharpness restoration methods are listed below, and the following examples will be given for the three sharpness restoration methods.
In an embodiment, performing enhancement processing on an object to be enhanced according to the associated information to obtain an enhanced medical image, includes:
and when the defect type is a second preset type, increasing the contrast of the correlative voxel until the contrast is not less than a preset contrast threshold, and obtaining the medical image after the strengthening treatment.
In this embodiment, the contrast of the associated voxel point is adjusted to improve the contrast of the associated voxel point, so that the object to be enhanced is clearer.
In another embodiment, performing enhancement processing on the object to be enhanced according to the associated information to obtain an enhanced medical image, includes:
and when the defect type is a second preset type, performing definition restoration processing on the associated voxel point through a preset definition restoration model to obtain a strengthened medical image.
In this embodiment, a sharpness restoration model may be obtained by training through a neural network deep learning algorithm in advance, wherein when training the sharpness restoration model, a plurality of samples may be learned through learning, and the plurality of samples include a plurality of sets of contrast images before and after sharpness restoration.
And inputting the associated voxel points into a definition restoration model, so that the definition of the associated voxel points can be restored, and a medical image after definition restoration is obtained.
And performing definition restoration on the associated voxel points to obtain clearer symptoms of the object to be strengthened.
Or, in another embodiment, performing enhancement processing on the object to be enhanced according to the associated information to obtain an enhanced medical image, including:
3061. and when the defect type is a second preset type, determining an additive voxel point from the associated voxel points according to a second preset threshold value.
The second preset threshold may be a range of the recognition probability value, or may also be a specific numerical value, and a specific setting manner may be self-defined, which is not limited herein.
For example, when the recognition probability value of the lesion at the blood vessel is in the range of 2.0 to 3.0 and the recognition probability value of the blood vessel is in the range of 3.5 to 4.0, the second preset threshold may be set to 2.0 to 4.0, and the associated voxel point having the recognition probability value in the range of 2.0 to 4.0 may be taken as the additive voxel point. It should be understood that the description is only used as an example, and is not used to limit the recognition probability value of the voxel point of the object to be enhanced in the embodiment.
For another example, when the recognition probability value of the lesion at the blood vessel is in the range of 2.0 to 3.0, the preset threshold may be set to 0.2, and the associated voxel point having the recognition probability value in the range of 0.8 to 3.2 may be taken as the additive voxel point.
3062. And supplementing the additive element points to the object to be enhanced to obtain the enhanced medical image.
After the added voxel points are supplemented to the object to be strengthened, the voxel point supplementation is carried out on the region of the object to be strengthened, so that the symptom of the object to be strengthened with fuzzy symptoms is clearer, and further, medical staff can judge the specific characteristics of the focus or analyze the abnormal condition of the blood vessel according to the processed medical image conveniently.
In some embodiments, after obtaining the enhanced medical image, the method further includes:
judging whether the definition of the object to be enhanced in the medical image after the enhancement processing meets the diagnosis requirement or not;
if so, identifying the focus from the medical image after the strengthening treatment;
if not, the step of 304-206 is continuously executed to continuously execute the definition restoring processing step on the object to be strengthened until the definition of the object to be strengthened meets the diagnosis requirement.
The diagnosis requirement refers to whether the medical staff can see clearly the outline of the focus in the medical image, or judge that the disease cause is caused according to the image of the focus, or the medical staff can distinguish the focus from the blood vessel.
In the embodiment, the medical image after the strengthening treatment is verified, whether the object to be strengthened meets the diagnosis requirement is continuously judged, and when the object to be strengthened does not meet the diagnosis requirement, the definition of the object to be strengthened is continuously restored until medical staff can distinguish the specific cause of the focus, so that the image processing flow is optimized.
As can be seen from the above, the image processing method provided in the embodiment of the present invention performs sharpness restoration on the features of the object to be enhanced, so that the features of the object to be enhanced are easy to identify, and the blood vessels and the lesions can be distinguished, and further medical diagnosis can be performed according to the features of the lesions.
Referring to fig. 4, fig. 4 is a fourth flowchart illustrating an image processing method according to an embodiment of the invention. The method comprises the following steps:
401. acquiring a medical image to be processed.
Wherein the medical image to be processed comprises a blood vessel.
402. In response to the received instruction to be enhanced, an object to be enhanced is determined from the medical image to be processed.
The images around the blood vessel can be selected through the clicking or frame selection operation, and then the part needing to be strengthened is selected as the object to be strengthened.
403. And determining the defect type of the object to be strengthened according to the original image of the object to be strengthened.
In this embodiment, the defect type is a third predetermined type, and the third predetermined type refers to a blood vessel fracture, for example, a fracture of a blood vessel in a medical image may be a fracture caused by a lesion in the blood vessel or a fracture caused by an inability to visualize.
404. Determining a contour region of an object to be strengthened, and enlarging the contour region along a direction far away from the contour region according to a first preset threshold value to obtain a strengthened region.
In this embodiment, the contour region includes two broken regions, namely a first contour region and a second contour region, and the range of the contour region is expanded so that the contour region includes the first contour region and the second contour region, and a region including a middle portion between the first contour region and the second contour region is used as a reinforcing region.
The first preset threshold refers to the distance of flaring, and the distance can be determined according to the distance between the first contour region and the second contour region, as long as two fracture regions are included.
405. And determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
In the present embodiment, in the case where the object to be enhanced is a blood vessel fracture, a voxel point located at the middle position of the fracture region in the enhancement region is taken as a related voxel point.
406. When the defect type is a third preset type, the contour region comprises a first contour region and a second contour region.
407. And connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain the strengthened medical image.
In this embodiment, the broken blood vessels are connected by the associated voxel points, and a repaired blood vessel image is obtained.
Since there are various ways of connecting the broken blood vessels by the associated voxel points, three connection ways are listed below, and the following examples will illustrate methods for repairing blood vessels with respect to the three connection ways.
In an embodiment, performing enhancement processing on an object to be enhanced according to the associated information to obtain an enhanced medical image, includes:
and sequentially connecting voxel points with highest probability value and meeting preset conditions between the associated voxel points and the edge voxel points by taking the edge voxel points of the first contour region and/or the second contour region as starting points, and performing fracture repair processing on the object to be strengthened to obtain the strengthened medical image, wherein the preset conditions are that the distance is shortest or the smoothness of a connecting line is highest.
For example, in an example, with a third voxel point of the edge voxel points of the first contour region as a starting point, the identification probability value of the third voxel point is 70, a fourth voxel point having the highest identification probability value with the third voxel point among the associated voxel points is 68, and a fifth voxel point having the highest identification probability value with the third voxel point and the fourth voxel point among the edge voxel points of the second contour region is 69, so that the third voxel point in the first contour region, the fourth voxel point in the associated voxel points, and the fifth voxel point in the second contour region are sequentially connected.
By analogy, the edge voxel points, the associated voxel points and the edge voxel points in the first contour region are sequentially connected, and the corresponding number of connecting lines can be obtained according to the number of the edge voxel points in the first contour region or the second contour region.
It should be noted that, the connection lines established between the edge voxel points of the first contour region, the associated voxel points and the edge voxel points of the second contour region do not differentiate the connection order, as long as the three satisfy the condition that the recognition probability value is the highest.
After all the connecting lines are obtained, the connecting lines are screened out to meet the requirement of shortest distance or best smoothness reservation, wherein the shortest distance refers to the shortest distance between two edge voxel points at two ends of the current connecting line compared with the connection with other voxel points.
For example, in the above example, the recognition probability value of the third voxel point is 70, the recognition probability value of the fourth voxel point is 68, the recognition probability value of the fifth voxel point is 69, and the recognition probability value of the sixth voxel point is 69 in the second contour region, where the third voxel point, the fourth voxel point, and the fifth voxel point may be connected to form a first connection line, and the third voxel point, the fourth voxel point, and the sixth voxel point may also be connected to form a second connection line, and since the first connection line length is smaller than the second connection line length, the first connection line is selected and stored based on the precondition that the distance is shortest.
For another example, in the above example, if the lengths of the first connection line and the second connection line are the same, the smoothness of the first connection line and the second connection line are compared, wherein the smoothness of the first connection line is higher than that of the second connection line, and the second connection line is retained; alternatively, the smoothness of the first and second links are directly compared.
In another embodiment, performing enhancement processing on the object to be enhanced according to the associated information to obtain an enhanced medical image, includes:
and connecting the first contour region and the second contour region based on the associated voxel points according to a shortest path algorithm to perform fracture repair processing on the object to be reinforced to obtain the reinforced medical image.
The first contour region, the related voxel point and each voxel point in the second contour region can be connected in sequence through a dijkstra algorithm by a dijkstra algorithm, and then the connection repair of the broken blood vessel is realized.
Or, in another embodiment, performing enhancement processing on the object to be enhanced according to the associated information to obtain an enhanced medical image, including:
and connecting and repairing edge voxel points of the first contour region and the second contour region by using the associated voxel points through a preset fracture repair model to obtain the medical image after the strengthening treatment.
The fracture repairing model is obtained through deep learning neural network model training, and the first contour region, the correlative body prime point and the second contour region are used as input, so that a repairing result is obtained.
In one example, the training fracture repair model may be trained by a before-and-after-fracture comparison map of the blood vessel;
in another example, the fracture repair model can also be obtained by training an image of the blood vessel center line as an input, wherein the image of the blood vessel center line is a template image constructed according to past medical experience, or a marked image of the blood vessel center line after a large number of manual diagnoses of a doctor.
In another example, the image of the fracture region and the image of the repair result can be used as input, and the obtained fracture repair model is trained through a deep learning neural network model.
In some embodiments, after connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be enhanced, and obtain the enhanced medical image, the method further includes:
judging whether the first contour region and the second contour region are still broken or not;
if yes, judging that the object to be strengthened is a focus;
if not, judging that the object to be strengthened is not the focus.
In this embodiment, after performing fracture repair on a blood vessel, it is determined whether the blood vessel is still in a fractured state, for example, as shown in fig. 5, a structural diagram of a myocardial bridge is shown, where the myocardial bridge stretches or bends along with the movement of a myocardial, and then the myocardial bridge is fractured during development, and a weaker connection line can be seen through the fracture repair, which indicates that the feature is not a lesion, and is a special blood vessel structure such as a myocardial bridge. On the other hand, if the lesion is calcified or thrombus, the lesion cannot be repaired, and the blood vessel is still in a broken state, indicating that the lesion is characterized by this.
As can be seen from the above, the image processing method provided in the embodiment of the present invention can further determine whether a focus exists by performing fracture repair processing on a fractured blood vessel, thereby facilitating subsequent medical diagnosis.
An image processing apparatus 500 is also provided in an embodiment. Referring to fig. 6, fig. 6 is a schematic structural diagram of an image processing apparatus 500 according to an embodiment of the present disclosure. The image processing apparatus 500 is applied to a computer device, and the image processing apparatus 500 includes an image obtaining module 501, an instruction processing module 502, an associated information obtaining module 503, and an image processing module 504, as follows:
an image obtaining module 501, configured to obtain a medical image to be processed;
an instruction processing module 502, configured to determine, in response to the received instruction to be enhanced, an object to be enhanced from the medical image to be processed;
the associated information acquiring module 503 is configured to acquire associated information of an object to be enhanced;
the image processing module 504 is configured to perform enhancement processing on the object to be enhanced according to the associated information, so as to obtain an enhanced medical image.
In some embodiments, the image acquisition module 501 is further configured to:
acquiring an original medical image;
and determining an image comprising the organ area from the original medical image, and taking the image comprising the organ area as a medical image to be processed.
In some embodiments, the association information obtaining module 503 is further configured to:
determining the defect type of the object to be strengthened according to the original image of the object to be strengthened;
determining a contour region of an object to be strengthened, and enlarging the contour region in a direction away from the contour region according to a first preset threshold value to obtain a strengthened region;
and determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
In some embodiments, the image processing module 504 is further configured to:
when the defect type is a first preset type, determining an additive voxel point from the associated voxel points according to a second preset threshold;
and supplementing the additive element points to the object to be enhanced to obtain the enhanced medical image.
In some embodiments, when the defect type is a first preset type, determining an additive voxel point from the associated voxel points according to a second preset threshold comprises:
when the defect type is a first preset type, acquiring a correlation prime point with the highest correlation with the outline region from the reinforced region;
calculating a difference value of recognition probability values between the associated voxel points with the highest relevance and the contour region;
and taking the associated voxel point with the difference value smaller than a second preset threshold value as an added voxel point.
In some embodiments, the image processing module 504 is further configured to:
and when the defect type is a second preset type, increasing the contrast of the correlative voxel until the contrast is not less than a preset contrast threshold, and obtaining the medical image after the strengthening treatment.
In some embodiments, the image processing module 504 is further configured to:
and when the defect type is a second preset type, performing definition repair processing on the associated voxel point through a preset definition repair model to obtain a reinforced medical image.
In some embodiments, the image processing module 504 is further configured to:
when the defect type is a third preset type, the contour region comprises a first contour region and a second contour region;
and connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain the strengthened medical image.
In some embodiments, connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be enhanced, and obtaining the enhanced medical image includes:
and sequentially connecting voxel points with highest probability value and meeting preset conditions between the associated voxel points and the edge voxel points by taking the edge voxel points of the first contour region and/or the second contour region as starting points, and performing fracture repair processing on the object to be strengthened to obtain the strengthened medical image, wherein the preset conditions are that the distance is shortest or the smoothness of a connecting line is highest.
In some embodiments, connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be enhanced, and obtaining the enhanced medical image includes:
connecting the first contour region and the second contour region based on the associated voxel points according to a shortest path algorithm to perform fracture repair processing on the object to be reinforced to obtain a reinforced medical image;
or, performing connection repair on edge voxel points of the first contour region and the second contour region by using the associated voxel points through a preset fracture repair model to obtain the medical image after the strengthening treatment.
In some embodiments, after connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be enhanced, and obtain the enhanced medical image, the method further includes:
judging whether the first contour region and the second contour region are still broken or not;
if yes, judging that the object to be strengthened is a focus;
if not, judging that the object to be strengthened is not the focus.
It should be noted that the image processing apparatus 500 provided in this embodiment of the present application and the image processing method in the foregoing embodiment belong to the same concept, and any method provided in the embodiment of the image processing method can be implemented by the image processing apparatus 500, and the specific implementation process thereof is described in detail in the embodiment of the image processing method, and is not described herein again.
Therefore, the image processing device provided by the embodiment of the application can make the processed image more clear and complete by performing the strengthening processing on the image to be processed, is convenient to identify, and is convenient for medical staff to perform medical diagnosis according to the processed image or directly display the characteristics of certain focuses.
The embodiment of the present application further provides a Computer device, where the Computer device may be a terminal, and the terminal may be a terminal device such as a smart phone, a tablet Computer, a notebook Computer, a touch screen, a game console, a Personal Computer (PC), a Personal Digital Assistant (PDA), and the like. As shown in fig. 7, fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application. The computer apparatus 600 includes a processor 601 having one or more processing cores, a memory 602 having one or more computer-readable storage media, and a computer program stored on the memory 602 and executable on the processor. The processor 601 is electrically connected to the memory 602. Those skilled in the art will appreciate that the computer device configurations illustrated in the figures are not meant to be limiting of computer devices and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
The processor 601 is a control center of the computer apparatus 600, connects various parts of the entire computer apparatus 600 using various interfaces and lines, performs various functions of the computer apparatus 600 and processes data by running or loading software programs and/or modules stored in the memory 602, and calling data stored in the memory 602, thereby monitoring the computer apparatus 600 as a whole.
In the embodiment of the present application, the processor 601 in the computer device 600 loads instructions corresponding to processes of one or more applications into the memory 602, and the processor 601 executes the applications stored in the memory 602 according to the following steps, so as to implement various functions:
acquiring a medical image to be processed;
in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed;
acquiring the associated information of an object to be strengthened;
and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Optionally, as shown in fig. 7, the computer device 600 further includes: a touch display screen 603, a radio frequency circuit 604, an audio circuit 605, an input unit 606, and a power supply 607. The processor 601 is electrically connected to the touch display screen 603, the radio frequency circuit 604, the audio circuit 605, the input unit 606, and the power supply 607. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 7 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
The touch display screen 603 can be used for displaying a graphical user interface and receiving operation instructions generated by a user acting on the graphical user interface. The touch display screen 603 may include a display panel and a touch panel. The display panel may be used, among other things, to display information entered by or provided to a user and various graphical user interfaces of the computer device, which may be made up of graphics, text, icons, video, and any combination thereof. Alternatively, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. The touch panel may be used to collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel using any suitable object or accessory such as a finger, a stylus pen, and the like), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Alternatively, the touch panel may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 601, and can receive and execute commands sent by the processor 601. The touch panel may overlay the display panel, and when the touch panel detects a touch operation thereon or nearby, the touch panel transmits the touch operation to the processor 601 to determine the type of the touch event, and then the processor 601 provides a corresponding visual output on the display panel according to the type of the touch event. In the embodiment of the present application, the touch panel and the display panel may be integrated into the touch display screen 603 to implement input and output functions. However, in some embodiments, the touch panel and the display panel may be implemented as two separate components to perform the input and output functions. That is, the touch display screen 603 can also be used as a part of the input unit 606 to implement an input function.
The rf circuit 604 may be used for transceiving rf signals to establish wireless communication with a network device or other computer device via wireless communication, and for transceiving signals with the network device or other computer device.
The audio circuit 605 may be used to provide an audio interface between the user and the computer device through speakers, microphones. The audio circuit 605 may transmit the electrical signal converted from the received audio data to a speaker, and convert the electrical signal into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 605 and converted into audio data, which is then processed by the audio data output processor 601, and then transmitted to, for example, another computer device via the radio frequency circuit 604, or output to the memory 602 for further processing. The audio circuit 605 may also include an earbud jack to provide communication of peripheral headphones with the computer device.
The input unit 606 may be used to receive input numbers, character information, or user characteristic information (e.g., fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.
The power supply 607 is used to power the various components of the computer device 600. Optionally, the power supply 607 may be logically connected to the processor 601 through a power management system, so as to implement functions of managing charging, discharging, and power consumption management through the power management system. The power supply 607 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
Although not shown in fig. 7, the computer device 600 may further include a camera, a sensor, a wireless fidelity module, a bluetooth module, etc., which are not described in detail herein.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
As can be seen from the above, the computer device provided in this embodiment can acquire the medical image to be processed, determine the object to be enhanced in response to the received instruction to be enhanced, acquire the associated information of the object to be enhanced, and perform enhancement processing on the object to be enhanced according to the associated information, so that the object to be enhanced has complete features, and is convenient for medical staff to identify and diagnose.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer programs can be loaded by a processor to execute the steps in any image processing method provided by the present application. For example, the computer program may perform the steps of:
acquiring a medical image to be processed;
in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed;
acquiring the associated information of an object to be strengthened;
and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like. Since the computer program stored in the storage medium can execute the steps in any image processing method provided in the embodiments of the present application, the beneficial effects that can be achieved by any image processing method provided in the embodiments of the present application can be achieved, and detailed descriptions are omitted here for the foregoing embodiments.
The foregoing detailed description has provided an image processing method, an apparatus, a medium, and a computer device according to embodiments of the present application, and specific examples have been applied in the present application to explain the principles and implementations of the present application, and the descriptions of the foregoing embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (15)
1. An image processing method, comprising:
acquiring a medical image to be processed;
in response to the received instruction to be enhanced, determining an object to be enhanced from the medical image to be processed;
acquiring the associated information of the object to be strengthened;
and performing reinforcement processing on the object to be reinforced according to the associated information to obtain a reinforced medical image.
2. The method of claim 1, wherein the acquiring the medical image to be processed comprises:
acquiring an original medical image;
determining an image including an organ region from the original medical image, and taking the image including the organ region as the medical image to be processed.
3. The method according to claim 1, wherein the medical image to be processed is a medical image reconstructed by an AI algorithm.
4. The method according to claim 1, wherein the obtaining of the associated information of the object to be strengthened includes:
determining the defect type of the object to be strengthened according to the original image of the object to be strengthened;
determining a contour region of the object to be strengthened, and expanding the contour region along a direction far away from the contour region according to a first preset threshold value to obtain a strengthened region;
and determining the associated information of the object to be strengthened from the strengthening region according to the defect type of the object to be strengthened, wherein the associated information is an associated prime point.
5. The method according to claim 4, wherein the performing the enhancement processing on the object to be enhanced according to the associated information to obtain the enhanced medical image comprises:
when the defect type is a first preset type, determining an additive voxel point from the associated voxel points according to a second preset threshold;
and supplementing the addition element points to the object to be enhanced to obtain the enhanced medical image.
6. The method of claim 5, wherein determining an additive voxel point from the associated voxel points according to a second predetermined threshold when the defect type is a first predetermined type comprises:
when the defect type is the first preset type, acquiring a correlation prime point with the highest relevance with the contour region from the reinforced region;
calculating a difference in recognition probability values between the associated voxel points having the highest relevance and the contour region;
and taking the associated voxel point with the difference value smaller than the second preset threshold value as an additive voxel point.
7. The method according to claim 4, wherein the performing the enhancement processing on the object to be enhanced according to the associated information to obtain the enhanced medical image comprises:
and when the defect type is a second preset type, increasing the contrast of the associated voxel point until the contrast is not less than a preset contrast threshold value, and obtaining the medical image after the strengthening treatment.
8. The method according to claim 4, wherein the performing the enhancement processing on the object to be enhanced according to the associated information to obtain the enhanced medical image comprises:
and when the defect type is a second preset type, performing definition repair processing on the associated voxel point through a preset definition repair model to obtain a reinforced medical image.
9. The method according to claim 4, wherein the performing the enhancement processing on the object to be enhanced according to the associated information to obtain the enhanced medical image comprises:
when the defect type is a third preset type, the contour region comprises a first contour region and a second contour region;
and connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain a strengthened medical image.
10. The method according to claim 9, wherein the connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain a strengthened medical image comprises:
and sequentially connecting voxel points with highest probability value and meeting preset conditions between the associated voxel points and the edge voxel points by taking the edge voxel points of the first contour region and/or the second contour region as starting points to perform fracture repair processing on the object to be strengthened to obtain the strengthened medical image, wherein the preset conditions are that the distance is shortest or the smoothness of a connecting line is highest.
11. The method according to claim 9, wherein the connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain a strengthened medical image comprises:
connecting the first contour region and the second contour region based on the associated voxel point according to a shortest path algorithm to perform fracture repair processing on the object to be reinforced to obtain a reinforced medical image;
or, performing connection repairing on the edge voxel points of the first contour region and the second contour region by using the associated voxel points through a preset fracture repairing model to obtain the medical image after the strengthening treatment.
12. The method according to any one of claims 9 to 11, wherein after connecting the first contour region and the second contour region according to the associated voxel point to perform fracture repair processing on the object to be strengthened to obtain a strengthened medical image, the method further comprises:
judging whether the first contour region and the second contour region are still fractured;
if yes, judging that the object to be strengthened is a focus;
if not, judging that the object to be strengthened is not the focus.
13. An image processing apparatus characterized by comprising:
the image acquisition module is used for acquiring a medical image to be processed;
the instruction processing module is used for responding to the received instruction to be enhanced and determining an object to be enhanced from the medical image to be enhanced;
the associated information acquisition module is used for acquiring the associated information of the object to be strengthened;
and the image processing module is used for carrying out reinforcement processing on the object to be reinforced according to the associated information to obtain a medical image after reinforcement processing.
14. A computer-readable storage medium, on which a computer program is stored, which, when run on a computer, causes the computer to perform the image processing method according to any one of claims 1 to 12.
15. A computer device comprising a processor and a memory, said memory storing a computer program, characterized in that said processor is adapted to execute the image processing method according to any of claims 1 to 12 by invoking said computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111059740.9A CN113689355B (en) | 2021-09-10 | 2021-09-10 | Image processing method, image processing device, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111059740.9A CN113689355B (en) | 2021-09-10 | 2021-09-10 | Image processing method, image processing device, storage medium and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113689355A true CN113689355A (en) | 2021-11-23 |
CN113689355B CN113689355B (en) | 2022-07-08 |
Family
ID=78585860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111059740.9A Active CN113689355B (en) | 2021-09-10 | 2021-09-10 | Image processing method, image processing device, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113689355B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114119578A (en) * | 2021-12-01 | 2022-03-01 | 数坤(北京)网络科技股份有限公司 | Image processing method and device, computer equipment and storage medium |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004318693A (en) * | 2003-04-18 | 2004-11-11 | Konica Minolta Photo Imaging Inc | Image processing method, image processor, and image processing program |
CN1599916A (en) * | 2001-12-07 | 2005-03-23 | 皇家飞利浦电子股份有限公司 | Medical viewing system and method for spatially enhancing structures in noisy images |
CN101706843A (en) * | 2009-11-16 | 2010-05-12 | 杭州电子科技大学 | Interactive film Interpretation method of mammary gland CR image |
KR20130007905A (en) * | 2011-07-11 | 2013-01-21 | 삼성전자주식회사 | Method and apparatus for processing a ultrasound image |
CN105976367A (en) * | 2016-04-29 | 2016-09-28 | 上海联影医疗科技有限公司 | Image segmentation method, pulmonary nodule detection method and computer-aided detection system |
CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
CN108665978A (en) * | 2018-04-03 | 2018-10-16 | 首都医科大学附属北京同仁医院 | Analysis method and system for tumour MRI image dynamic contract-enhanced degree |
US10290084B1 (en) * | 2018-11-14 | 2019-05-14 | Sonavista, Inc. | Correcting image blur in medical image |
CN109886933A (en) * | 2019-01-25 | 2019-06-14 | 腾讯科技(深圳)有限公司 | A kind of medical image recognition method, apparatus and storage medium |
US20190272628A1 (en) * | 2018-03-02 | 2019-09-05 | Utechzone Co., Ltd. | Apparatus and method for enhancing optical feature of workpiece, method for enhancing optical feature of workpiece through deep learning, and non-transitory computer-readable recording medium |
CN110689548A (en) * | 2019-09-29 | 2020-01-14 | 浪潮电子信息产业股份有限公司 | Medical image segmentation method, device, equipment and readable storage medium |
CN110705626A (en) * | 2019-09-26 | 2020-01-17 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
WO2020079694A1 (en) * | 2018-10-17 | 2020-04-23 | Inspekto A.M.V Ltd | Optimizing defect detection in an automatic visual inspection process |
CN111161289A (en) * | 2019-12-26 | 2020-05-15 | 杭州格像科技有限公司 | Method, device and computer program product for improving contour precision of object in image |
CN111489318A (en) * | 2020-03-20 | 2020-08-04 | 上海联影智能医疗科技有限公司 | Medical image enhancement method and computer-readable storage medium |
CN111553858A (en) * | 2020-04-28 | 2020-08-18 | 四川大学青岛研究院 | Image restoration method and system based on generation countermeasure network and application thereof |
CN111626998A (en) * | 2020-05-22 | 2020-09-04 | 深圳前海微众银行股份有限公司 | Image processing method, device, equipment and storage medium |
CN111627037A (en) * | 2020-05-22 | 2020-09-04 | 深圳前海微众银行股份有限公司 | Image area extraction method, device, equipment and storage medium |
CN111951215A (en) * | 2020-06-30 | 2020-11-17 | 数坤(北京)网络科技有限公司 | Image detection method and device and computer readable storage medium |
CN112330686A (en) * | 2019-08-05 | 2021-02-05 | 罗雄彪 | Method for segmenting and calibrating lung bronchus |
CN113034389A (en) * | 2021-03-17 | 2021-06-25 | 武汉联影智融医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
CN113096213A (en) * | 2021-04-30 | 2021-07-09 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
CN113299370A (en) * | 2021-07-05 | 2021-08-24 | 数坤(北京)网络科技股份有限公司 | Medical image display method and device, computer equipment and storage medium |
CN113362345A (en) * | 2021-06-30 | 2021-09-07 | 武汉中科医疗科技工业技术研究院有限公司 | Image segmentation method and device, computer equipment and storage medium |
-
2021
- 2021-09-10 CN CN202111059740.9A patent/CN113689355B/en active Active
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1599916A (en) * | 2001-12-07 | 2005-03-23 | 皇家飞利浦电子股份有限公司 | Medical viewing system and method for spatially enhancing structures in noisy images |
JP2004318693A (en) * | 2003-04-18 | 2004-11-11 | Konica Minolta Photo Imaging Inc | Image processing method, image processor, and image processing program |
CN101706843A (en) * | 2009-11-16 | 2010-05-12 | 杭州电子科技大学 | Interactive film Interpretation method of mammary gland CR image |
KR20130007905A (en) * | 2011-07-11 | 2013-01-21 | 삼성전자주식회사 | Method and apparatus for processing a ultrasound image |
CN105976367A (en) * | 2016-04-29 | 2016-09-28 | 上海联影医疗科技有限公司 | Image segmentation method, pulmonary nodule detection method and computer-aided detection system |
CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
US20190272628A1 (en) * | 2018-03-02 | 2019-09-05 | Utechzone Co., Ltd. | Apparatus and method for enhancing optical feature of workpiece, method for enhancing optical feature of workpiece through deep learning, and non-transitory computer-readable recording medium |
CN108665978A (en) * | 2018-04-03 | 2018-10-16 | 首都医科大学附属北京同仁医院 | Analysis method and system for tumour MRI image dynamic contract-enhanced degree |
WO2020079694A1 (en) * | 2018-10-17 | 2020-04-23 | Inspekto A.M.V Ltd | Optimizing defect detection in an automatic visual inspection process |
US10290084B1 (en) * | 2018-11-14 | 2019-05-14 | Sonavista, Inc. | Correcting image blur in medical image |
CN109886933A (en) * | 2019-01-25 | 2019-06-14 | 腾讯科技(深圳)有限公司 | A kind of medical image recognition method, apparatus and storage medium |
CN112330686A (en) * | 2019-08-05 | 2021-02-05 | 罗雄彪 | Method for segmenting and calibrating lung bronchus |
CN110705626A (en) * | 2019-09-26 | 2020-01-17 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110689548A (en) * | 2019-09-29 | 2020-01-14 | 浪潮电子信息产业股份有限公司 | Medical image segmentation method, device, equipment and readable storage medium |
CN111161289A (en) * | 2019-12-26 | 2020-05-15 | 杭州格像科技有限公司 | Method, device and computer program product for improving contour precision of object in image |
CN111489318A (en) * | 2020-03-20 | 2020-08-04 | 上海联影智能医疗科技有限公司 | Medical image enhancement method and computer-readable storage medium |
CN111553858A (en) * | 2020-04-28 | 2020-08-18 | 四川大学青岛研究院 | Image restoration method and system based on generation countermeasure network and application thereof |
CN111627037A (en) * | 2020-05-22 | 2020-09-04 | 深圳前海微众银行股份有限公司 | Image area extraction method, device, equipment and storage medium |
CN111626998A (en) * | 2020-05-22 | 2020-09-04 | 深圳前海微众银行股份有限公司 | Image processing method, device, equipment and storage medium |
CN111951215A (en) * | 2020-06-30 | 2020-11-17 | 数坤(北京)网络科技有限公司 | Image detection method and device and computer readable storage medium |
CN113034389A (en) * | 2021-03-17 | 2021-06-25 | 武汉联影智融医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
CN113096213A (en) * | 2021-04-30 | 2021-07-09 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
CN113362345A (en) * | 2021-06-30 | 2021-09-07 | 武汉中科医疗科技工业技术研究院有限公司 | Image segmentation method and device, computer equipment and storage medium |
CN113299370A (en) * | 2021-07-05 | 2021-08-24 | 数坤(北京)网络科技股份有限公司 | Medical image display method and device, computer equipment and storage medium |
Non-Patent Citations (5)
Title |
---|
SHAIKH MAHMUDUL ISLAM 等: "Image Enhancement Based Medical Image Analysis", 《2019 10TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT)》 * |
ZHUHUANG ZHOU 等: "Semi-automatic Breast Ultrasound Image Segmentation Based on Mean Shift and Graph Cuts", 《ULTRASONIC IMAGING》 * |
徐永潇: "基于三维重建的肺肿瘤分割技术研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
黄瑞 等: "磁共振 IVIM 和 PWI 技术在脑泡型包虫病诊断", 《神经放射学》 * |
龚勋 等: "甲状腺、乳腺超声影像自动分析技术综述", 《软件学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114119578A (en) * | 2021-12-01 | 2022-03-01 | 数坤(北京)网络科技股份有限公司 | Image processing method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN113689355B (en) | 2022-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7058373B2 (en) | Lesion detection and positioning methods, devices, devices, and storage media for medical images | |
EP3982292B1 (en) | Method for training image recognition model, and method and apparatus for image recognition | |
CN110504029B (en) | Medical image processing method, medical image identification method and medical image identification device | |
CN109191451B (en) | Abnormality detection method, apparatus, device, and medium | |
CN110276408B (en) | 3D image classification method, device, equipment and storage medium | |
CN113177928B (en) | Image identification method and device, electronic equipment and storage medium | |
CN110310271B (en) | Carotid plaque property discriminating method, storage medium and ultrasonic device | |
CN109087310B (en) | Meibomian gland texture region segmentation method and system, storage medium and intelligent terminal | |
JP2013051988A (en) | Device, method and program for image processing | |
CN113889238B (en) | Image identification method and device, electronic equipment and storage medium | |
US20200334801A1 (en) | Learning device, inspection system, learning method, inspection method, and program | |
CN112967284A (en) | Blood vessel image segmentation analysis method, device, equipment and storage medium | |
CN110648318A (en) | Auxiliary analysis method and device for skin diseases, electronic equipment and storage medium | |
CN113689355B (en) | Image processing method, image processing device, storage medium and computer equipment | |
CN110517771B (en) | Medical image processing method, medical image identification method and device | |
JP6744175B2 (en) | Medical image display device and interpretation report creation support device | |
CN111401102A (en) | Deep learning model training method and device, electronic equipment and storage medium | |
CN116452579B (en) | Chest radiography image-based pulmonary artery high pressure intelligent assessment method and system | |
CN115393251A (en) | Defect detection method and device for printed circuit board, storage medium and electronic equipment | |
CN110063753B (en) | Method and device for measuring head circumference of fetus in ultrasonic image | |
EP4257055A1 (en) | Method, apparatus, and recording medium for analyzing coronary plaque tissue through ultrasound image-based deep learning | |
CN113610840B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
US11972584B2 (en) | Tissue specific time gain compensation methods and systems | |
US20240249498A1 (en) | System, Method, and Computer Program Product for Extracting Features From Imaging Biomarkers With Machine-Learning Models | |
JP2009061176A (en) | Medical image processor and program |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230117 Address after: 518026 Rongchao Economic and Trade Center A308-D9, No. 4028, Jintian Road, Fuzhong Community, Lianhua Street, Futian District, Shenzhen, Guangdong Province Patentee after: Shukun (Shenzhen) Intelligent Network Technology Co.,Ltd. Address before: 100120 rooms 303, 304, 305, 321 and 322, building 3, No. 11, Chuangxin Road, science and Technology Park, Changping District, Beijing Patentee before: Shukun (Beijing) Network Technology Co.,Ltd. |