CN110827308A - Image processing method, device, electronic device and storage medium - Google Patents

Abstract

The present application relates to an image processing method, device, electronic device and storage medium that help to promote the development of artificial intelligence in pathological diagnosis. The method includes: acquiring a pathological image to be processed; gray value, using different threshold methods to perform threshold segmentation on the pathological image to be processed, to obtain tissue region extraction results corresponding to different threshold methods; and performing bit AND processing on the tissue region extraction results corresponding to the different threshold methods, Obtain the extraction result of the target tissue area. The present application uses different threshold methods to perform threshold segmentation on the pathological images to be processed, and performs bit AND processing on the extraction results corresponding to different threshold methods. Compared with image processing using a single threshold method, the accuracy of image processing can be improved, and The application of artificial intelligence in the field of auxiliary pathological diagnosis lays the foundation, which in turn can improve the reading speed, shorten the reading time, and save labor costs.

Description

Image processing method, device, electronic device and storage medium

technical field

The present application relates to the technical field of image processing, and in particular, to an image processing method, an image processing apparatus, an electronic device and a storage medium.

Background technique

In recent years, with the continuous development of computational vision technology, especially the continuous maturity of deep learning technology represented by convolutional neural networks, and its continuous penetration into various fields of medical images, pathological image processing has become an important research in computer vision. content. How to use computer vision technology to accurately identify pathological images and then serve pathological diagnosis is a research hotspot in the field of pathological artificial intelligence.

Because the color of pathological images is relatively single and the difference between the target tissue area and the background area is large, the method of threshold segmentation is often used to identify the target tissue area. The accuracy of target tissue region identification is not high.

SUMMARY OF THE INVENTION

In view of this, the present application provides an image processing method, an image processing apparatus, an electronic device and a storage medium capable of improving the accuracy of image processing.

An image processing method, comprising: acquiring a pathological image to be processed; based on the gray value of each pixel of the pathological image to be processed, threshold segmentation is performed on the pathological image to be processed using different threshold methods respectively, to obtain corresponding and performing bit AND processing on the tissue region extraction results corresponding to the different threshold methods to obtain the target tissue region extraction result.

The image processing method provided by the present application performs threshold segmentation on the pathological image to be processed by using different threshold methods, and performs bit AND processing on the extraction results corresponding to different threshold methods. Compared with image processing using a single threshold method, the image can be improved. Accuracy of processing results.

Optionally, the pathological image to be processed is an HSV pathological image, and the acquiring the pathological image to be processed includes: acquiring an RGB pathological image to be processed, and processing the pathological image to be processed based on a monochromatic channel of the RGB pathological image to be processed. The RGB pathological image is subjected to threshold segmentation, and the threshold-segmented RGB pathological image to be processed is converted into the to-be-processed HSV pathological image.

Since the pathologist will make corresponding marks on the pathological section in order to make the pathological diagnosis when reading the film, or the pathological section itself has some marks, therefore, the pathological image obtained by scanning the pathological section by the pathological section scanner also exists in the pathological section. Mark accordingly. In the present application, by acquiring the RGB pathological image to be processed, and performing threshold segmentation on the RGB pathological image to be processed based on a single color channel of the RGB pathological image to be processed, these marks can be removed, thereby improving the accuracy of image processing; and Since the HSV color space is closer to the color space that the human eye can perceive, this application uses HSV pathological images as the pathological images to be processed, which can simulate the color space sensitivity of pathologists when reading images, and is more conducive to the research of pathological diagnosis artificial intelligence .

Optionally, based on the gray value of each pixel of the pathological image to be processed, different threshold methods are used to perform threshold segmentation on the pathological image to be processed, to obtain tissue region extraction results corresponding to different threshold methods, including: Threshold segmentation is performed on the pathological image to be processed by artificial experience selection method to obtain a first tissue region extraction result; and a maximum inter-class variance method is used to perform threshold segmentation on the to-be-processed pathological image to obtain a second tissue region extraction result.

Optionally, after obtaining the extraction result of the target tissue region, the method further includes: performing an opening operation and/or a closing operation on the extraction result of the target tissue region.

After obtaining the extraction result of the target tissue region, the image processing method provided by the present application can optimize the boundary of the extraction result of the target tissue region by performing an opening operation and/or a closing operation on the extraction result of the target tissue region, so as to output a better target tissue Region extraction results.

An image processing device, comprising: an acquisition module for acquiring a pathological image to be processed; an extraction module for using different threshold methods for the pathological image to be processed based on the gray value of each pixel of the pathological image to be processed The image is subjected to threshold segmentation to obtain tissue region extraction results corresponding to different threshold methods; and a processing module is used to perform bit AND processing on the tissue region extraction results corresponding to the different threshold methods to obtain target tissue region extraction results.

Optionally, the pathological image to be processed is an HSV pathological image, the acquisition module includes an acquisition unit, a segmentation unit and a conversion unit, the acquisition unit is used to acquire the RGB pathological image to be processed, and the segmentation unit is used to A monochromatic channel of the RGB pathological image to be processed performs threshold segmentation on the RGB pathological image to be processed, and the conversion unit is configured to convert the RGB pathological image to be processed after threshold segmentation into the HSV pathological image to be processed.

Optionally, the extraction module is configured to: perform threshold segmentation on the pathological image to be processed by using an artificial experience selection method to obtain a first tissue region extraction result; and use the maximum inter-class variance method to perform threshold segmentation on the pathological image to be processed. Threshold segmentation to obtain the extraction result of the second tissue region.

Optionally, the processing module is further configured to perform opening operation and/or closing operation processing on the extraction result of the target tissue region.

An electronic device includes a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor causes the processor to execute the above-mentioned image processing method or realize the above-mentioned image processing. function of the device.

A non-volatile readable storage medium storing computer readable instructions, when the computer readable instructions are executed by a processor, the processor causes the processor to execute the above image processing method or realize the function of the above image processing apparatus.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features, objects and advantages of the present application will become apparent from the description, drawings and claims.

Description of drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, therefore It should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present application.

FIG. 2 is a flowchart of acquiring an image to be recognized according to an embodiment of the present application.

FIG. 3 provides a process for performing threshold segmentation on the pathological image to be processed by using different threshold methods based on the gray value of each pixel of the pathological image to be processed, and obtaining tissue region extraction results corresponding to different threshold methods, according to an embodiment of the present application. picture.

FIG. 4 is a structural block diagram of an image processing apparatus provided by an embodiment of the present application.

FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.

Reference numerals: image processing apparatus 100 ; acquisition module 10 ; acquisition unit 11 ; segmentation unit 13 ; conversion unit 15 ; extraction module 20 ; processing module 30 .

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

Referring to FIG. 1 , an embodiment of the present application provides an image processing method, which is applied to extraction of a target tissue region of a pathological image. The method includes the following steps.

Step S101: Acquire a pathological image to be processed.

In this embodiment, the pathological image to be processed may include a target tissue area and a background area. Wherein, the background area includes a marked area including marks such as a pathologist's reading mark or a pathological section's own mark, and an area that is irrelevant to pathological diagnosis such as a residual area of dye solution, a tissue-free area or a fat area.

The pathological image to be processed may be a pathological image in a color space such as HSV color space or RGB color space. Among them, HSV respectively represents Hue (hue), Saturation (saturation), Value (lightness); RGB respectively represents Red (red), Green (green), Blue (blue). In this paper, pathological images in HSV color space are referred to as HSV pathological images, and pathological images in RGB color space are referred to as RGB pathological images.

Since the HSV color space is closer to the most sensitive color space of the human eye, in order to simulate the sensitivity of the pathologist to the color space when viewing pathological slices, and to facilitate the research on artificial intelligence for pathological diagnosis, in this embodiment, the pathological image to be processed Pathological images of HSV to be processed.

Exemplarily, the way of acquiring the HSV pathological image to be processed may be indirect acquisition by acquiring the RGB pathological image. Specifically, please refer to FIG. 2 together. The method of indirectly acquiring the pathological image of the HSV to be processed may include the following steps.

Step S201: Acquire a to-be-processed RGB pathological image.

The RGB pathological image to be processed can be obtained by scanning the pathological section with a pathological section scanner.

Step S202: Perform threshold segmentation on the RGB pathological image to be processed based on a single color channel of the RGB pathological image to be processed.

Since the color of the pathologist's reading mark and the pathological section's own mark is usually black, and the color of the target tissue area of the pathological image is usually red, the two are highly distinguishable on the R channel. Therefore, a threshold value T can be set on the R channel of the RGB pathological image to remove the marked area. The principle of threshold segmentation based on R channel of RGB pathological image is as follows:

For any point (x, y, R) of the RGB pathological image f(x, y, R)>T, it is called an object point, otherwise the point is called a background point, where the object point corresponds to the target tissue area, and the background point corresponds to background area. The segmented image g(x, y, z) is given by:

Where x is the abscissa, y is the ordinate, z is the channel, and R represents the R channel value of the RGB color space.

It can be understood that the selection of the channel for threshold segmentation of the RGB pathological image here is related to the color of the marked area, and the above-mentioned threshold segmentation based on the R channel of the RGB pathological image is only an example, and is not limited thereto. For example, in other embodiments, when the color of the marked area is blue, the RGB pathological image may also be subjected to threshold segmentation based on the B channel of the RGB pathological image.

Step S203 : Convert the RGB pathological image to be processed after threshold segmentation into an HSV pathological image to obtain the to-be-processed HSV image.

The method for converting the RGB pathological image to be processed after the threshold segmentation into the HSV pathological image is the prior art in the art, and for the sake of brevity of the description, it will not be described in detail here.

Because the color difference between the marked area and the target tissue area is large, and the marked area is not related to the pathological diagnosis, the RGB pathological image to be processed is obtained indirectly by obtaining the RGB pathological image. The HSV pathological image method can process the pathological image in the RGB color space to remove the marked area, thereby improving the accuracy of the pathological diagnosis to a certain extent.

Step S102: Based on the gray value of each pixel of the pathological image to be processed, threshold segmentation is performed on the pathological image to be processed using different threshold methods respectively, to obtain tissue region extraction results corresponding to the different threshold methods.

In this embodiment, based on the gray value of each pixel of the pathological image to be processed, different thresholding methods are used to perform threshold segmentation on the HSV pathological image to be processed, to obtain tissue region extraction results corresponding to different thresholding methods. Wherein, the different threshold methods include at least two of manual experience selection method, maximum inter-class variance method, adaptive threshold method and the like. In this embodiment, the different threshold methods used are the manual experience selection method and the maximum inter-class variance method. Please refer to FIG. 3 together. Based on the gray value of each pixel of the pathological image to be processed, different threshold methods are used to perform threshold segmentation on the pathological image to be processed, and obtaining tissue region extraction results corresponding to different threshold methods includes the following steps.

Step S301: Perform threshold segmentation on the pathological image to be processed by using an artificial experience selection method to obtain a first tissue region extraction result.

In this embodiment, an artificial experience selection method is used to perform threshold segmentation on the to-be-processed HSV pathological image to obtain a first tissue region extraction result.

The artificial experience selection method is used to perform threshold processing on the HSV pathological image to be processed. The threshold is selected according to the HSV gray value information of the target tissue area, and the HSV pathological image to be processed is binarized, that is, according to the gray value of each pixel of the HSV pathological image. and the preset gray value range, image binarization processing is performed on the HSV pathological image, and the principle is as follows:

Among them, φ(x, y, z) is the HSV pathological image converted from the RGB pathological image obtained by scanning the pathological section by the pathological section scanner after thresholding to remove the marked area, hsv_threshold(φ(x, y, z) ) is the output image processed by the artificial experience selection method, x is the abscissa, y is the ordinate, and z is the channel. T1 and T2 respectively represent the upper threshold value and lower threshold value of threshold segmentation using the artificial experience selection method. In this embodiment, in order to improve the accuracy of threshold segmentation using the manual experience selection method, the value range of T1 is 10-30, and the value range of T2 is 180-220.

Step 302: Perform threshold segmentation on the pathological image to be processed by using the maximum inter-class variance method to obtain a second tissue region extraction result.

In this embodiment, the maximum inter-class variance method is used to perform threshold segmentation on the to-be-processed HSV pathological image to obtain the extraction result of the second tissue region.

Specifically, the principle of threshold segmentation of the HSV pathological image to be processed using the maximum inter-class variance is as follows: first, the HSV pathological image to be processed is divided into two parts, the target and the background according to its grayscale characteristics, wherein the target corresponds to the target tissue area, The background corresponds to the background area; assuming that the segmentation threshold between the target and the background in the HSV pathological image is T, the ratio of the number of pixels in the target and background areas to the entire HSV pathological image is ω0 and ω1, respectively, and μ is the global grayscale of the HSV pathological image. The grayscale values of the target and the background are μ0 and μ1, respectively, where ω ₀ +ω ₁ =1, μ=ω ₀ ×μ ₀ +ω ₁ ×μ ₁ , and the inter-class variance of the target and the background is recorded as σ2, then there are:

σ ² =ω ₀ ×(μ ₀ -μ) ² +ω ₁ ×(μ ₁ -μ) ²

Its equivalent formula is σ ² =ω ₀ ω ₁ ×(μ ₀ -μ ₁ ) ² . Through traversal and solving, the threshold T that maximizes the inter-class variance σ2 can be finally obtained. Then, the threshold T that maximizes the inter-class variance σ2 is taken as the image binarization threshold, and the HSV image to be processed is subjected to threshold segmentation.

Step S103: Perform bit AND processing on the tissue region extraction results obtained by using different threshold methods to obtain the target tissue region extraction result.

In this embodiment, the first tissue region extraction result obtained by threshold segmentation of the HSV pathological image to be identified using the artificial experience selection method and the second tissue region extraction result obtained by threshold segmentation of the HSV pathological image to be identified using the maximum inter-class variance method The tissue region extraction results are bit-AND processed to obtain the target tissue region extraction results. The principle is as follows:

h(x,y,z)=hsv_threshold(φ(x,y,z))&hsv_otsu(φ(x,y,z))

Where φ(x, y, z) is the pathological image of HSV to be identified which is converted from the RGB pathological image obtained by scanning the pathological slice through the pathological slice scanner after threshold segmentation to remove the marked area, h(x, y, z) For the output image after bitwise and processing the tissue region extraction results obtained by different threshold methods, x is the abscissa, y is the ordinate, z is the channel, hsv_threshold represents the manual experience selection method, hsv_otsu represents the maximum inter-class variance method, & represents bit and processing.

Among them, the rules of bit AND processing are as follows:

0&0=0

0&1=0

1&0=0

1&1=1

Among them, 0 corresponds to the background area, 1 corresponds to the target tissue area, the digits before the bit and the symbol & represent the binarization processing result obtained after thresholding the HSV pathological image to be processed by the artificial experience selection method, the bit and the symbol & after The numbers represent the binarization results obtained by thresholding the HSV pathological image to be processed by the maximum inter-class variance method.

The image processing method provided by this application uses different threshold methods to perform threshold segmentation on the pathological image to be recognized to obtain tissue area extraction results, and performs bit AND processing on the tissue area extraction results obtained by using different threshold methods. A single threshold method is used to process the image to be recognized, which can remove the residual areas of dye solution, unorganized areas, fat areas and other areas that are not relevant for pathological diagnosis, so as to avoid these areas being extracted as target tissue areas, thereby improving image processing results. accuracy.

It can be understood that, in other embodiments, after obtaining the extraction result of the target tissue region, the image processing method further includes step S104 : performing an opening operation and/or a closing operation on the extraction result of the target tissue region. The opening operation and/or the closing operation can optimize the target tissue region contour to output better target tissue region extraction results.

It can be understood that, in other embodiments, when threshold segmentation is performed on the RGB pathological image to be processed based on a single color channel of the RGB pathological image to be processed, different threshold methods can be used to perform threshold segmentation on the RGB pathological image to be processed, and then different thresholding methods can be used. The threshold method performs bit AND processing on the processing results obtained by threshold segmentation of the RGB pathological image to be processed to improve the accuracy of removing the marked area.

Referring to FIG. 4 , based on the same inventive concept, an image processing apparatus 100 is also provided in the embodiment of the present application, including an acquisition module 10 for acquiring a pathological image to be processed; an extraction module 20 for acquiring a pathological image based on each pixel of the pathological image to be processed The grayscale values of the to-be-processed pathological images are segmented using different threshold methods respectively to obtain the tissue region extraction results corresponding to the different threshold methods; and the processing module 30 is used to bit-and-match the tissue region extraction results corresponding to the different threshold methods. processing to obtain the extraction result of the target tissue region.

The pathological image to be processed may be an HSV pathological image. The acquisition module 10 can indirectly acquire the to-be-processed HSV pathological image by acquiring the RGB to-be-processed pathological image. Specifically, the obtaining module 10 may include an obtaining unit 11 , a dividing unit 13 and a converting unit 15 . The acquisition unit 11 is used to acquire the RGB pathological image to be processed. The segmentation unit 13 is configured to perform threshold segmentation on the RGB pathological image to be processed based on a single color channel of the RGB pathological image to be processed. The conversion unit 15 is used for converting the RGB pathological image to be processed after threshold segmentation into the HSV pathological image to be processed.

The extraction module 20 is used to perform threshold segmentation on the pathological image to be processed by artificial experience selection method to obtain the first tissue region extraction result; and use the maximum inter-class variance method to perform threshold segmentation on the to-be-processed pathological image to obtain the second tissue region extraction result.

The processing module 30 is further configured to perform opening operation and/or closing operation processing on the extraction result of the target tissue region.

It can be understood that the image processing apparatus provided in this application corresponds to the image processing method provided in this application. In order to make the description concise, the same or similar parts may refer to the content of the image processing method, which will not be repeated here.

Each module in the above-mentioned image processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in or independent of the processor in the server in the form of hardware, or may be stored in the memory in the server in the form of software, so that the processor can call and execute operations corresponding to the above modules. The processor may be a central processing unit (CPU), a microprocessor, a single-chip microcomputer, or the like.

The above image processing method and/or image processing apparatus may be implemented in the form of computer-readable instructions, and the computer-readable instructions may be executed on the electronic device as shown in FIG. 5 .

An embodiment of the present application also provides an electronic device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor implements the above-mentioned image processing method when executing the program.

FIG. 5 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application, and the electronic device may be a server. Referring to FIG. 5 , the electronic device includes a processor, a non-volatile storage medium, an internal memory, an input device, a display screen and a network interface connected through a system bus. The non-volatile storage medium of the electronic device can store an operating system and computer-readable instructions. When the computer-readable instructions are executed, the processor can execute an image processing method according to the embodiments of the present application. The method For the specific implementation process, reference may be made to the specific content of FIG. 1 to FIG. 3 , which will not be repeated here. The processor of the electronic device is used to provide computing and control capabilities to support the operation of the entire electronic device. Computer-readable instructions may be stored in the internal memory, and when executed by the processor, the computer-readable instructions may cause the processor to execute an image processing method. The input device of the electronic device is used for inputting various parameters, the display screen of the electronic device is used for display, and the network interface of the electronic device is used for network communication. Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium that stores computer-readable instructions thereon, and when the program is executed by a processor, implements the steps in the above-mentioned image processing method.

Any reference to a memory, storage, database or other medium as used herein may include non-volatile. Suitable nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms.

In addition, units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

Furthermore, each functional module in each embodiment of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such existence between these entities or operations. The actual relationship or sequence.

The above descriptions are merely examples of the present application, and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes may be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims (10)

1. An image processing method, comprising:

acquiring a pathological image to be processed;

based on the gray value of each pixel of the pathological image to be processed, performing threshold segmentation on the pathological image to be processed by using different threshold methods respectively to obtain tissue region extraction results corresponding to the different threshold methods; and

and carrying out bit and processing on the tissue region extraction results obtained by adopting different threshold methods to obtain a target tissue region extraction result.

2. The image processing method according to claim 1, wherein the pathology image to be processed is an HSV pathology image to be processed, and the acquiring the pathology image to be processed includes:

the method comprises the steps of obtaining an RGB pathological image to be processed, carrying out threshold segmentation on the RGB pathological image to be processed based on a single-color channel of the RGB pathological image to be processed, and converting the RGB pathological image to be processed after threshold segmentation into the HSV pathological image to be processed.

3. The image processing method according to claim 1, wherein the threshold segmentation is performed on the pathological image to be processed by using different threshold methods respectively based on the gray value of each pixel of the pathological image to be processed to obtain tissue region extraction results corresponding to the different threshold methods, and the method comprises:

performing threshold segmentation on the pathological image to be processed by adopting an artificial experience selection method to obtain a first tissue region extraction result; and

and performing threshold segmentation on the pathological image to be processed by adopting a maximum inter-class variance method to obtain a second tissue region extraction result.

4. The image processing method of claim 1, wherein after the obtaining the target tissue region extraction result, the method further comprises:

and performing opening operation and/or closing operation processing on the target tissue region extraction result.

5. An image processing apparatus characterized by comprising:

the acquisition module is used for acquiring a pathological image to be processed;

the extraction module is used for carrying out threshold segmentation on the pathological image to be processed by using different threshold methods respectively based on the gray value of each pixel of the pathological image to be processed to obtain tissue region extraction results corresponding to the different threshold methods; and

and the processing module is used for carrying out bit and processing on the tissue region extraction results corresponding to the different threshold methods to obtain a target tissue region extraction result.

6. The image processing apparatus according to claim 5, wherein the pathological image to be processed is an HSV pathological image to be processed, the acquiring module includes an acquiring unit configured to acquire an RGB pathological image to be processed, a segmenting unit configured to threshold-segment the RGB pathological image to be processed based on a monochrome channel of the RGB pathological image to be processed, and a converting unit configured to convert the RGB pathological image to be processed into the HSV pathological image to be processed.

7. The image processing apparatus according to claim 5, wherein the extraction module is configured to:

performing threshold segmentation on the pathological image to be processed by adopting an artificial experience selection method to obtain a first tissue region extraction result; and

and performing threshold segmentation on the pathological image to be processed by adopting a maximum inter-class variance method to obtain a second tissue region extraction result.

8. The image processing apparatus according to claim 5, wherein the processing module is further configured to perform an on-operation and/or an off-operation on the target tissue region extraction result.

9. An electronic device comprising a memory and a processor, the memory having stored therein computer-readable instructions that, when executed by the processor, cause the processor to perform the image processing method of any of claims 1 to 4 or to implement the functionality of the image processing apparatus of any of claims 5-8.

10. A non-transitory readable storage medium storing computer readable instructions that, when executed by a processor, cause the processor to perform the image processing method of any one of claims 1 to 4 or implement the functions of the image processing apparatus of any one of claims 5 to 8.

Images