CN115272362A - Method and device for segmenting effective area of digital pathology full-field image - Google Patents

Abstract

The application relates to a method and a device for segmenting an effective region of a digital pathology full-field image. The method comprises the following steps: acquiring a thumbnail image of a digital pathology full-field image, and obtaining a scaling; removing noises such as characters, shadow, foreign matters and the like on the thumbnail; converting the thumbnail into a gray-scale image; enhancing the contrast of the gray level image by using a histogram equalization algorithm; after the gray level image with the enhanced contrast ratio is subjected to Gaussian blur, converting the image into a binary image by using a threshold value method; carrying out post-processing optimization on the generated binary image; and determining the peripheral outline coordinates of the effective area according to the gradient, and mapping the coordinates onto the full-field map according to the scaling obtained in the first step.

Description

A digital pathological full-field image effective region segmentation method and device

technical field

The present application relates to the technical field of image processing, in particular to a method and a device for segmenting effective regions of digital pathological full-field images.

Background technique

With the development of digital pathological full-field image scanning technology, digital scanners have emerged to scan pathological slices and generate an ultra-high-resolution full-field image file of more than one billion pixels.

At present, the mainstream method for artificial intelligence analysis of digital pathology full-field images is to use the sliding window method to divide digital pathology full-field images into hundreds or thousands of small pictures of fixed sizes, and then send these small pictures to the GPU at one time. Computational analysis is performed, and finally the analysis results of all the small pictures are counted and summarized to form the final digital pathology full-field image analysis results.

However, there are a large number of blank areas and irrelevant areas on a digital pathology full-field image. The effective tissue area may only account for one-tenth or even less of the entire digital pathology full-field image. Directly analyzing the entire digital pathology full-field image will not only waste a lot of analysis time and computing power in irrelevant areas In addition, artificial intelligence algorithms cannot effectively identify impurities, dye solutions or text marks in irrelevant areas, which will also interfere with the accuracy of artificial intelligence analysis.

Contents of the invention

Based on this, it is necessary to provide a method for segmenting effective regions of digital pathology full-field images for the above technical problems.

A digital pathological full-field image effective region segmentation method, the method comprising:

Obtain the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio;

Remove the noise on the thumbnail image of the tissue to be processed to obtain the tissue effect image;

Convert the tissue effect image into a grayscale image, and use the histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image;

Perform Gaussian blurring on the tissue-enhanced image, and convert the image into a binary image using a threshold method;

Perform post-processing optimization on the binary image according to the foreground and background, and obtain the optimized image of the tissue area;

According to the gray value gradient change of the optimized image of the tissue area, the peripheral contour coordinates of the target area are determined, and the peripheral contour coordinates are converted to the full-field map coordinates according to the preset scaling ratio.

In one of the embodiments, acquiring the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio further includes: scaling the digital pathology full-field image into the thumbnail image of the tissue to be processed according to the preset zoom ratio .

In one of the embodiments, the noise includes text noise, shadow noise and foreign object noise;

Remove the noise on the thumbnail image of the tissue to be processed, and obtain the tissue effect image, including:

Convert the thumbnail image of the tissue to be processed from the RGB color space to the HSV color space to obtain the HSV tissue color image;

For the pixel in the HSV tissue color image whose H value and S value are both lower than the color threshold, the pixel is covered with white to obtain the tissue effect image.

In one of the embodiments, a histogram equalization algorithm is used to enhance the contrast of the grayscale image to obtain a tissue enhanced image, including:

Divide the grayscale image into a preset number of image blocks;

After using a histogram equalization algorithm to enhance the contrast of each of the image blocks, they are combined to obtain a tissue-enhanced image.

In one of the embodiments, performing post-processing optimization on the generated binary image further includes: using a morphological closing operation on the binary image to remove holes in the foreground area, and using a morphological opening operation to remove fragmented objects outside the foreground area ; Among them, the foreground area is an effective tissue or cell area, and the fragmented target includes a fragmented foreground area and a fragmented error area.

In the binary image generated above, the foreground is an effective tissue or cell area, and the background is an irrelevant area. In the generated original binary image, there are fragmentary background holes in the effective area and fragmentary foreground areas outside the tissue area. These fragmentary error positions need to be removed by post-processing optimization. In the present invention, the morphological closing operation is used for the original binary image to remove the holes in the foreground area, and the morphological opening operation is used to remove the fragmented objects outside the large foreground area. After these errors are removed, the foreground of the binary image is expanded to a certain extent, so that the range of the foreground can completely include the effective tissue or cell area. According to the gradient change of the gray value of the binary image, the edge contour coordinates of the foreground are obtained, and then multiplied by the scaling ratio of the first step to obtain the contour coordinates of the effective area on the original image of the full-field image.

A digital pathology full-field image effective area segmentation device, said device comprising:

A thumbnail image acquisition module, configured to acquire a thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to a preset scaling ratio;

The noise processing module is used to remove the noise on the thumbnail image of the tissue to be processed to obtain the tissue effect image;

The contrast enhancement module is used to convert the tissue effect image into a grayscale image, and uses a histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image;

The binary image conversion module is used to perform Gaussian blur on the tissue enhanced image, and convert the image into a binary image using a threshold method;

The post-processing module is used to perform post-processing optimization on the binary image according to the foreground and background to obtain an optimized image of the tissue region;

The contour coordinate calculation module is used to optimize the gray value gradient change of the image according to the tissue area, determine the peripheral contour coordinates of the target area, and convert the peripheral contour coordinates to the full field map coordinates according to the preset scaling ratio.

A computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Obtain the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio;

Remove the noise on the thumbnail image of the tissue to be processed to obtain the tissue effect image;

Convert the tissue effect image into a grayscale image, and use the histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image;

Perform Gaussian blurring on the tissue-enhanced image, and convert the image into a binary image using a threshold method;

Perform post-processing optimization on the binary image according to the foreground and background, and obtain the optimized image of the tissue area;

According to the gray value gradient change of the optimized image of the tissue area, the peripheral contour coordinates of the target area are determined, and the peripheral contour coordinates are converted to the full-field map coordinates according to the preset scaling ratio.

A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtain the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio;

Remove the noise on the thumbnail image of the tissue to be processed to obtain the tissue effect image;

Convert the tissue effect image into a grayscale image, and use the histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image;

Perform Gaussian blurring on the tissue-enhanced image, and convert the image into a binary image using a threshold method;

Perform post-processing optimization on the binary image according to the foreground and background, and obtain the optimized image of the tissue area;

According to the gray value gradient change of the optimized image of the tissue area, the peripheral contour coordinates of the target area are determined, and the peripheral contour coordinates are converted to the full-field map coordinates according to the preset scaling ratio.

The above-mentioned method and device for segmenting effective areas of digital pathological full-field images can quickly locate and segment effective tissue or cell areas by quickly focusing on the effective areas, so that the artificial intelligence algorithm only analyzes the effective areas, thereby saving a lot of time. The analysis time and computing power are improved, and the robustness and accuracy of artificial intelligence analysis are also improved.

Description of drawings

Fig. 1 is a flow chart of a method for segmenting an effective area of a digital pathological full-field image in an embodiment;

Fig. 2 is a schematic diagram of processing effect in an embodiment;

Fig. 3 is a structural schematic diagram of an effective area segmentation device for a digital pathological full-field image in an embodiment;

Figure 4 is an internal block diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In one embodiment, as shown in Figure 1, a method for valid area segmentation of a digital pathological full-field image is provided, comprising the following steps:

Step S110, acquiring the thumbnail image of the tissue to be processed processed according to the preset scaling ratio of the digital pathology full-field image.

Among them, to determine the effective tissue or cell area on the digital pathological full-field image, it is first necessary to obtain the global view of the pathological section. On the stained and prepared slides, even in a relatively low-power field of view, the area where the effective tissue is located can be clearly distinguished. On the premise of fully balancing the calculation time saved by the low-magnification field of view and the loss of edge precision, the magnification of the thumbnail image acquired by the present invention is 0.625 times. After the thumbnail is obtained, the outline coordinates of the effective area calculated on the thumbnail are remapped back to the original full-field image according to the scaling ratio. In the present invention, the magnification of the thumbnail image is 1.25 times. If the digital pathological full-field image is scanned by a scanner with a magnification of 40 times, the zoom ratio is 40/0.625=64. It can be seen that the side length of the thumbnail image is one sixty-fourth of the original image of the full-field image.

Step S120, removing noise on the thumbnail image of the tissue to be processed to obtain a tissue effect image.

Among them, the thumbnail is converted from the RGB (R: red, G: green, B: blue) color space to the HSV (H: hue, S: saturation, V: lightness) color space, which can be obtained by using a large number of slices for experiments. It is known that the values of the H and S channels of these noises on the thumbnail are obviously lower than the normal tissue area, so the values of the H and S channels are thresholded. When the values of H and S at a certain position are lower than the threshold, It can be determined that this position is located on these noise interferers, and then these positions are directly covered with white to achieve the effect of removing noise.

Step S130, converting the tissue effect image into a grayscale image, and using a histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image.

Among them, it is designed for some lightly stained slices. This is achieved using the Contrast-Limited Adaptive Histogram Equalization (CLAHE) method. This method divides the image into small blocks of the same size, and then performs histogram equalization on each small block separately. It is also possible to prevent noise from being enhanced as well by limiting the contrast.

Step S140, performing Gaussian blurring on the enhanced tissue image, and converting the image into a binary image using a threshold method.

Among them, the Gaussian filter is used to denoise the image first, in addition to denoising, it can also make the outline of the tissue smoother. Then normalize the gray value of the image to the interval [0, 1], set the threshold, and use the threshold method to binarize the image. The area whose gray value is higher than the threshold is the background, and the gray value Areas below the threshold are foreground.

Step S150, perform post-processing optimization on the binary image according to foreground and background, to obtain an optimized tissue region image.

Among them, in the generated binary image, the foreground is an effective tissue or cell area, and the background is an irrelevant area. In the generated original binary image, there are fragmentary background holes in the effective area and fragmentary foreground areas outside the tissue area. These fragmentary error positions need to be removed by post-processing optimization. In the present invention, the morphological closing operation is used for the original binary image to remove the holes in the foreground area, and the morphological opening operation is used to remove the fragmented objects outside the large foreground area. After these errors are removed, the foreground of the binary image is expanded to a certain extent, so that the range of the foreground can completely include the effective tissue or cell area. According to the gradient change of the gray value of the binary image, the edge contour coordinates of the foreground are obtained, and then multiplied by the scaling ratio of the first step to obtain the contour coordinates of the effective area on the original image of the full-field image.

Step S160, determine the peripheral contour coordinates of the target area according to the gradient change of the gray value of the optimized image of the tissue region, and convert the peripheral contour coordinates to the full-field image coordinates according to the preset scaling ratio.

Among them, the outer contour coordinates of the target area are determined according to the gradient change of the gray value, and Canny operator, Sobel operator, LOG operator or Laplacian operator can be used for edge detection to obtain the outer contour coordinates of the target area.

In the effective area segmentation method of the digital pathology full-field image above, the thumbnail image of the digital pathology full-field image is obtained, and the zoom ratio is obtained; noises such as text, shadows and foreign objects on the thumbnail are removed; the thumbnail is converted into a grayscale image; Use the histogram equalization algorithm to enhance the contrast of the grayscale image; after performing Gaussian blur on the contrast-enhanced grayscale image, use the threshold method to convert the image into a binary image; optimize the post-processing of the generated binary image; according to the gradient Determine the outer contour coordinates of the effective area, and map the coordinates to the full-field map according to the scaling ratio obtained in the first step, which can quickly locate and segment effective tissue or cell areas, so that the artificial intelligence algorithm can only perform on the effective area. Analysis, which saves a lot of analysis time and computing power, and also improves the robustness and accuracy of artificial intelligence analysis.

In one of the embodiments, the acquiring the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio further includes: scaling the digital pathology full-field image into the thumbnail image of the tissue to be processed according to the preset zoom ratio. thumbnail image.

In one of the embodiments, the noise includes text noise, shadow noise and foreign object noise. The noise on the thumbnail image of the tissue to be processed is removed to obtain the tissue effect image, which also includes: converting the thumbnail image of the tissue to be processed from the RGB color space to the HSV color space to obtain the HSV tissue color image; the H in the HSV tissue color image The pixels whose value and S value are lower than the color threshold value are covered with white to obtain the tissue effect image.

In one of the embodiments, using a histogram equalization algorithm to enhance the contrast of the grayscale image to obtain a tissue enhanced image also includes: dividing the grayscale image into a preset number of image blocks; using a histogram for each of the image blocks After the image equalization algorithm enhances the contrast, it is combined to obtain a tissue-enhanced image.

In one of the embodiments, Gaussian blur is performed on the tissue-enhanced image, and the threshold method is used to convert the image into a binary image, which also includes: processing the tissue-enhanced image through a Gaussian filter to obtain a noise-reduced binary image; The grayscale value of the binary image is normalized to the interval [0, 1], and according to the set grayscale threshold, the area with a grayscale value higher than the set grayscale threshold is used as the background area, and the grayscale value is lower than that of the background area. The area equal to or equal to the set gray threshold is taken as the foreground area, and a binary image of the background area and the foreground area is obtained.

In one of the embodiments, the post-processing optimization of the generated binary image includes: using a morphological closing operation on the binary image to remove holes in the foreground area, and using a morphological opening operation to remove fragmentary objects outside the foreground area; Wherein, the foreground area is a valid tissue or cell area, and the fragmented target includes a fragmented foreground area and a fragmented error area.

Among them, as shown in Figure 2, in the generated binary image, the foreground area is an effective tissue or cell area, such as the effective area in Figure 2, and the background area is an irrelevant area; in the generated binary image, there are parts in There are fragmented background holes in the foreground area, such as the holes in the effective area in Figure 2; and fragmented foreground areas outside the large tissue area. The fragmented foreground area refers to some small tissue areas that are separated from the large tissue area. The area is the tissue fragments accidentally attached to the film, as shown in Figure 2. There are also fragmented error areas, which are the impurity areas in the image. For example, impurities include glass fragments, marker marks, etc., as shown in Figure 2. Marked text noise and foreign object noise, these fragmentary objects need to be removed through post-processing optimization. In the present invention, a morphological closing operation is used on the generated binary image to remove holes in the foreground area, and a morphological opening operation is used to remove fragmentary objects that are free from a large area of the foreground area. After removing these errors, the foreground of the binary image is expanded to a certain extent, so that the range of the foreground can completely include the effective tissue or cell area, and the edge contour of the foreground is calculated according to the gradient change of the gray value of the binary image Coordinates are multiplied by the scaling ratio of the first step to obtain the contour coordinates of the effective area on the original image of the full-field image.

In this embodiment, the filtering of fragmented objects can facilitate the analysis of the effective area by the artificial intelligence algorithm in the later stage and improve the processing efficiency.

It should be understood that although the various steps in the flow chart of FIG. 1 are displayed sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in FIG. 1 may include multiple steps or stages, and these steps or stages may not necessarily be executed at the same time, but may be executed at different times, and the execution sequence of these steps or stages may also be It is not necessarily performed sequentially, but may be performed alternately or alternately with other steps or at least a part of steps or stages in other steps.

In one embodiment, as shown in FIG. 3 , a device for segmenting an effective area of a digital pathological full-field image is provided, and the device includes: a thumbnail image acquisition module 310, a noise processing module 320, a contrast enhancement module 330, a binary image The conversion module 340, the post-processing module 350 and the contour coordinate calculation module 360, wherein: the thumbnail image acquisition module 310 is used to acquire the thumbnail image of the tissue to be processed processed by the digital pathology full-field image according to the preset zoom ratio; the noise processing module 320, It is used to remove noise on the thumbnail image of the tissue to be processed to obtain a tissue effect image; the contrast enhancement module 330 is used to convert the tissue effect image into a grayscale image, and use a histogram equalization algorithm to enhance the contrast of the grayscale image, Obtain the enhanced tissue image; the binary image conversion module 340 is used to perform Gaussian blurring on the enhanced tissue image, and converts the image into a binary image using the threshold method; the post-processing module 350 is used to perform the binary image according to the foreground and background Post-processing optimization to obtain an optimized image of the tissue area; the contour coordinate calculation module 360 is used to determine the peripheral contour coordinates of the target area according to the gradient change of the gray value of the tissue region optimized image, and convert the peripheral contour coordinates according to the preset scaling ratio to full-field map coordinates.

In one of the embodiments, the thumbnail image acquisition module 310 is further configured to scale the digital pathology full-field image into a thumbnail image of the tissue to be processed according to a preset scaling ratio.

In one of the embodiments, the noise processing module 320 includes: an HSV tissue color image conversion unit, which is used to convert the thumbnail image of the tissue to be processed from the RGB color space to the HSV color space to obtain the HSV tissue color image; the tissue effect image acquisition The unit is used to cover the pixel with white in the HSV tissue color image where both the H value and the S value are lower than the color threshold, so as to obtain the tissue effect image.

In one of the embodiments, the contrast enhancement module 330 includes: a segmentation unit for dividing the grayscale image into a preset number of image blocks; a contrast enhancement unit for using a histogram for each of the image blocks After the equalization algorithm enhances the contrast, it is combined to obtain a tissue enhanced image.

In one of the embodiments, the binary image conversion module 340 includes: a noise reduction unit, which is used to process the tissue enhanced image through a Gaussian filter to obtain a noise-reduced binary image; a binary image conversion unit, which is used to convert the noise reduction The grayscale value of the binary image is normalized to the interval [0, 1], and according to the set grayscale threshold, the area with a grayscale value higher than the set grayscale threshold is used as the background area, and the grayscale value is lower than that of the background area. The area equal to or equal to the set gray threshold is taken as the foreground area, and a binary image of the background area and the foreground area is obtained.

In one of the embodiments, the post-processing module 350 is also used to remove holes in the foreground region by using a morphological closing operation on the binary image, and remove fragmentary objects outside the foreground region by using a morphological opening operation; wherein, the foreground Regions are valid tissue or cell regions, and fragmented targets include fragmented foreground regions and fragmented error regions.

For the specific limitations of the device for quickly segmenting the effective area of a digital pathological full-field image, please refer to the above-mentioned definition of the method for image segmentation effective area, which will not be repeated here. Each module in the above-mentioned device for quickly segmenting the effective area of the digital pathological full-field image can be realized in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules. In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 4 . The computer device includes a processor, memory and a network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The computer device's database is used to store thumbnail data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a fast and effective area focusing method is realized.

Those skilled in the art can understand that the structure shown in Figure 4 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 to the computer equipment on which the solution of the application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, there is also provided a computer device, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only represent several implementation modes of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as limiting the scope of the patent for the invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Claims (9)

1. A method for segmenting effective regions of a digital pathology full-field image is characterized by comprising the following steps:

acquiring a to-be-processed tissue thumbnail image of a digital pathology full-field image processed according to a preset scaling;

removing noise on the to-be-processed tissue thumbnail image to obtain a tissue effect image;

converting the tissue effect image into a gray-scale image, and enhancing the contrast of the gray-scale image by using a histogram equalization algorithm to obtain a tissue enhanced image;

performing Gaussian blur on the tissue enhanced image, and converting the image into a binary image by using a threshold value method;

carrying out post-processing optimization on the binary image according to the foreground and the background to obtain an organization area optimization image;

and determining the peripheral contour coordinate of the target area according to the gray value gradient change of the tissue area optimization image, and converting the peripheral contour coordinate into the full-field image coordinate according to a preset scaling.

2. The method of claim 1, wherein obtaining the thumbnail image of the tissue to be processed with the digital pathology full field image processed according to the preset scaling further comprises: and zooming the digital pathology full-field image into a tissue thumbnail image to be processed according to a preset zooming scale.

3. The method of claim 1, wherein the noise comprises text noise, shadow noise, and foreign object noise;

removing noise on the thumbnail image of the tissue to be processed to obtain a tissue effect image, and further comprising:

converting the tissue thumbnail image to be processed from an RGB color space into an HSV color space to obtain an HSV tissue color image;

and for pixel points of which the H value and the S value in the HSV tissue color image are lower than the color threshold, covering the pixel points in white to obtain a tissue effect image.

4. The method of claim 1, wherein enhancing contrast of the grayscale image using a histogram equalization algorithm results in a tissue enhanced image, further comprising:

dividing the gray level image into a preset number of image blocks;

and enhancing the contrast of each image block by using a histogram equalization algorithm, and combining to obtain a tissue enhanced image.

5. The method of claim 1, wherein the tissue enhanced image is gaussian blurred and converted to a binary image using a thresholding method, further comprising:

processing the tissue enhancement image through a Gaussian filter to obtain a noise reduction binary image;

normalizing the gray value of the noise-reduction binary image to be in the interval of [0, 1], taking the area with the gray value higher than the set gray threshold value as a background area and the area with the gray value lower than or equal to the set gray threshold value as a foreground area according to the set gray threshold value, and obtaining the binary image about the background area and the foreground area.

6. The method of claim 1, wherein post-processing optimization of the generated binary image comprises:

removing holes in the foreground area of the binary image by adopting a morphological closing operation, and removing fragmentary targets outside the foreground area by adopting a morphological opening operation; wherein, the foreground region is an effective tissue or cell region, and the fragmentary target comprises a fragmentary foreground region and a fragmentary error region.

7. An apparatus for segmenting an effective region of a digital pathology full-field image, the apparatus comprising:

the thumbnail acquisition module is used for acquiring a thumbnail image of the tissue to be processed, which is processed by the digital pathology full-field image according to a preset scaling;

the noise processing module is used for removing noise on the to-be-processed tissue thumbnail image to obtain a tissue effect image;

the contrast enhancement module is used for converting the tissue effect image into a gray image and enhancing the contrast of the gray image by using a histogram equalization algorithm to obtain a tissue enhancement image;

the binary image conversion module is used for carrying out Gaussian blur on the tissue enhanced image and converting the image into a binary image by using a threshold value method;

the post-processing module is used for carrying out post-processing optimization on the binary image according to the foreground and the background to obtain an organization area optimized image;

and the contour coordinate calculation module is used for determining the peripheral contour coordinate of the target region according to the gray value gradient change of the tissue region optimization image, and converting the peripheral contour coordinate into the full-field image coordinate according to a preset scaling.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

Images