WO2024119322A1

WO2024119322A1 - Method and apparatus for evaluating quality of grayscale image, and electronic device and storage medium

Info

Publication number: WO2024119322A1
Application number: PCT/CN2022/136658
Authority: WO
Inventors: 岑伟轩; 李美; 黎宇翔
Original assignee: 深圳华大生命科学研究院
Priority date: 2022-12-05
Filing date: 2022-12-05
Publication date: 2024-06-13

Abstract

The present disclosure relates to the technical field of data processing. Disclosed are a method and apparatus for evaluating the quality of a grayscale image, and an electronic device and a storage medium. The method comprises: separately performing calculation to obtain an outer contour image and an inner contour image of a grayscale image of tissue in a target region; equally dividing each of the outer contour image and the inner contour image into N segments, and performing pairwise matching on each segment of outer contour image and each segment of inner contour image to obtain N image combinations; separately calculating a pixel density ratio of a segment of outer contour image to a segment of inner contour image in each image combination to obtain N pixel density ratios; and calculating the quality of the grayscale image of the tissue in the target region according to the pixel density ratios, and then describing same. Separately calculating a pixel density ratio of a segment of outer contour image to a segment of inner contour image in each image combination achieves the evaluation of the quality of a grayscale image of tissue in a target region.

Description

Grayscale image quality assessment method and device, electronic device and storage medium

Technical Field

The present disclosure relates to the field of data processing technology, and in particular to a method and device for grayscale image quality assessment, an electronic device, and a storage medium.

Background technique

At present, when performing tissue segmentation on a tissue grayscale image to obtain a target area tissue grayscale image, there is no method to evaluate the quality of the target area tissue grayscale image. Therefore, designing a method for evaluating the quality of the target area tissue grayscale image is an issue that needs to be urgently addressed.

Summary of the invention

The present disclosure provides a method and device for grayscale image quality assessment, an electronic device and a storage medium. The main purpose is to solve the problem that there is no method for assessing the grayscale image quality of the target area tissue. The main purpose is to achieve the assessment of the grayscale image quality of the target area tissue.

According to a first aspect of the present disclosure, a method for grayscale image quality assessment is provided, comprising:

The outer contour image and the inner contour image of the target area tissue grayscale image are calculated respectively;

Divide the outer contour image and the inner contour image into N segments respectively, and pair each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image;

Calculate the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations respectively, and obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel points to the total pixel points;

The grayscale image quality of the target area tissue is described by calculation according to the pixel density ratio.

Optionally, before respectively calculating the outer contour image and the inner contour image of the target area tissue grayscale image, the method includes:

Acquire a tissue grayscale image and a mask image, wherein the mask image is a binary image;

Remapping the grayscale interval of the tissue grayscale image to obtain an enhanced tissue grayscale image;

The enhanced tissue grayscale image is subjected to tissue segmentation based on the mask image to obtain the target area tissue grayscale image.

Optionally, the step of respectively calculating an outer contour image and an inner contour image of a target area tissue grayscale image comprises:

Dilate the target region tissue grayscale image based on the dilation kernel to obtain a first tissue grayscale image;

The first tissue grayscale image and the target area tissue grayscale image are subjected to differential calculation to obtain an outer contour image;

Corrosion is performed on the target area tissue grayscale image based on the corrosion kernel to obtain a second tissue grayscale image;

The second tissue grayscale image and the target area tissue grayscale image are differentially calculated to obtain an inner contour image.

Optionally, dividing the outer contour image and the inner contour image into N segments respectively includes:

Marking the segmentation position of the outer contour image and the inner contour image, wherein the segmentation position of the outer contour image corresponds to the segmentation position value of the inner contour image;

The outer contour image and the inner contour image are respectively divided into N segments based on the segmentation positions.

Optionally, pairing each segment of the outer contour image with each segment of the inner contour image in pairs comprises:

Calculate the centroid of each segment of the external contour image and the centroid of each segment of the internal contour image, and the calculated centroid is a description of the shape of each segment of the external contour image and each segment of the internal contour image;

If the similarity between the centroid of a segment of the external contour image and the centroid of a segment of the internal contour image is greater than a preset threshold, the segment of the external contour image and the segment of the internal contour image are paired.

Optionally, the remapping of the grayscale intervals of the tissue grayscale image to obtain an enhanced tissue grayscale image includes:

The grayscale values whose number of pixels in the tissue grayscale image meets a first preset range are widened, and the first preset range is the number range of pixels corresponding to the grayscale values that play a major role in the display of the tissue grayscale image; the grayscale values whose number of pixels in the tissue grayscale image meets a second preset range are merged, and the second preset range is the number range of pixels corresponding to the grayscale values that do not play a major role in the display of the tissue grayscale image;

The grayscale values after broadening and merging are remapped to the tissue grayscale image to obtain the enhanced tissue grayscale image.

Optionally, the calculating and describing the grayscale image quality of the target area tissue according to the pixel density ratio includes:

Calculate the average value of N pixel density ratios;

The grayscale image quality of the target area tissue is calculated based on the average value of the pixel density ratio.

According to a second aspect of the present disclosure, there is provided a grayscale image quality assessment device, comprising:

A first calculation unit is used to calculate and obtain an outer contour image and an inner contour image of a target area tissue grayscale image respectively;

a pairing unit, configured to divide the outer contour image and the inner contour image into N segments respectively, and pair each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image;

A second calculation unit is used to calculate the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, to obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel points;

A third calculation unit is configured to calculate a grayscale image quality describing the target area tissue according to the pixel density ratio.

Optionally, the device comprises:

An acquisition unit, used for acquiring a tissue grayscale image and a mask image, wherein the mask image is a binary image;

A remapping unit, used for remapping the grayscale interval of the tissue grayscale image to obtain an enhanced tissue grayscale image;

A segmentation unit is used to perform tissue segmentation on the enhanced tissue grayscale image based on the mask image to obtain the target area tissue grayscale image.

Optionally, the first computing unit includes:

An expansion module, used for expanding the target area tissue grayscale image based on the expansion kernel to obtain a first tissue grayscale image;

A first calculation module, used for performing a difference calculation between the first tissue grayscale image and the target area tissue grayscale image to obtain an outer contour image;

An erosion module, used for eroding the target area tissue grayscale image based on the erosion kernel to obtain a second tissue grayscale image;

The second calculation module is used to perform a difference calculation between the second tissue grayscale image and the target area tissue grayscale image to obtain an inner contour image.

Optionally, the pairing unit includes:

A calibration module, used for calibrating the segmentation position of the outer contour image and the inner contour image, wherein the segmentation position of the outer contour image corresponds to the segmentation position value of the inner contour image;

A segmentation module is used to segment the outer contour image and the inner contour image into N segments respectively based on the segmentation position.

Optionally, the pairing unit further includes:

A calculation module, used for calculating the centroid of each segment of the external contour image and the centroid of each segment of the internal contour image, wherein the calculated centroid is a description of the shape of each segment of the external contour image and each segment of the internal contour image;

The pairing module is used to pair the segment of the external contour image with the segment of the internal contour image when the similarity between the centroid of the segment of the external contour image and the centroid of the segment of the internal contour image is greater than a preset threshold.

Optionally, the remapping unit includes:

A stretching and merging module, for stretching the grayscale values whose number of pixels in the tissue grayscale image meets a first preset range, wherein the first preset range is the number range of pixels corresponding to the grayscale values that play a major role in displaying the tissue grayscale image; and merging the grayscale values whose number of pixels in the tissue grayscale image meets a second preset range, wherein the second preset range is the number range of pixels corresponding to the grayscale values that do not play a major role in displaying the tissue grayscale image;

The remapping module is used to remap the grayscale values after widening and merging to the tissue grayscale image to obtain the enhanced tissue grayscale image.

Optionally, the third computing unit includes:

A first calculation module, used for calculating an average value of N pixel density ratios;

The second calculation module is used to calculate the grayscale image quality of the target area tissue according to the average value of the pixel density ratio.

According to a third aspect of the present disclosure, there is provided an electronic device, including:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

The present disclosure provides a method and device, electronic device and storage medium for evaluating the quality of grayscale images. The main technical scheme includes: respectively calculating the outer contour image and the inner contour image of the target area tissue grayscale image; dividing the outer contour image and the inner contour image into N segments, and pairing each segment of the outer contour image with each segment of the inner contour image to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image; respectively calculating the pixel density ratio of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations to obtain N pixel density ratios, the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel point; and calculating the quality of the target area tissue grayscale image according to the pixel density ratio. Based on respectively calculating the pixel density ratio of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations, an evaluation score for the quality of the target area tissue grayscale image is obtained, thereby realizing the quality evaluation of the tissue grayscale image.

It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

FIG1 is a schematic flow chart of a grayscale image quality assessment method provided by an embodiment of the present disclosure;

FIG2 is a schematic diagram of a relationship structure between an external contour image and an internal contour image provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of another structure of the relationship between the external contour image and the internal contour image provided by an embodiment of the present disclosure.

FIG4 is a schematic diagram of a process of tissue grayscale image segmentation provided by an embodiment of the present disclosure;

FIG5 is a schematic diagram of an original tissue grayscale image provided by an embodiment of the present disclosure;

FIG6 is a schematic diagram of a grayscale image of tissue before and after augmentation provided by an embodiment of the present disclosure;

FIG7 is a schematic diagram of a histogram corresponding to an original tissue grayscale image provided by an embodiment of the present disclosure;

FIG8 is a schematic diagram of a histogram corresponding to an enhanced tissue grayscale image provided by an embodiment of the present disclosure;

FIG9 is a schematic diagram of the structure of a grayscale image quality assessment device provided by an embodiment of the present disclosure;

FIG10 is a schematic diagram of the structure of another grayscale image quality assessment device provided by an embodiment of the present disclosure;

FIG. 11 is a schematic block diagram of an example electronic device 400 provided according to an embodiment of the present disclosure.

Detailed ways

The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

The following describes the grayscale image quality assessment method and device, electronic device and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

FIG1 is a schematic flow chart of a grayscale image quality assessment method provided in an embodiment of the present disclosure.

As shown in Figure 1, the method includes the following steps:

Step 101, respectively calculating and obtaining an outer contour image and an inner contour image of a target area tissue grayscale image.

As a refinement of the above-mentioned step 101, when implementing step 101, the outer contour image and the inner contour image of the target area tissue grayscale image can be obtained respectively based on matrix operation. In this embodiment, the outer contour image and the inner contour image are band-shaped annular contours, and the outer contour image can surround the inner contour image.

Step 102 , dividing the outer contour image and the inner contour image into N segments respectively, and pairing each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image.

In order to more intuitively show the relationship between the outer contour image and the inner contour image, Figure 2 is a schematic diagram of the relationship structure between an outer contour image and an inner contour image provided in an embodiment of the present disclosure, and Figure 3 is a schematic diagram of the relationship structure between another outer contour image and an inner contour image provided in an embodiment of the present disclosure. As shown in Figure 2, the outer contour image and the inner contour image are respectively divided into N segments, that is, the outer contour image is evenly divided into N segments, and the inner contour image is evenly divided into N segments. A segment is taken from the N segments of the outer contour image and paired with a segment in the N segments of the inner contour image to form an image combination. After the pairing is completed, N image combinations can be obtained.

Step 103, respectively calculate the pixel density ratio of a section of the outer contour image to a section of the inner contour image in each of the image combinations to obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a section of the outer contour image to a section of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel point.

As a refinement of the above step 103, before calculating the pixel density ratio, it is necessary to first calculate the pixel ratio of each segment of the outer contour image and each segment of the inner contour image. Calculating the pixel ratio of a segment of the outer contour image includes dividing the number of pixels in the segment of the outer contour image by the total number of pixels in the segment of the outer contour image. In this embodiment, the pixel points are pixels with grayscale values greater than 127. The method for calculating the pixel ratio of a segment of the inner contour image is consistent with the method for calculating the pixel ratio of a segment of the outer contour image, that is, dividing the number of pixels in the segment of the inner contour image by the total number of pixels in the segment of the inner contour image, and so on, and finally calculating the pixel ratios of all segments of the outer contour images and the pixel ratios of all segments of the inner contour images.

After completing the above-mentioned pixel ratio calculation, it is also necessary to calculate the ratio of the pixel ratio of a section of the outer contour image to the pixel ratio of a section of the inner contour image. The ratio is the pixel density ratio. The section of the outer contour image and the section of the inner contour image exist in an image combination, that is, the two are paired with each other. The calculation of the ratio of the pixel ratio of a section of the outer contour image to the pixel ratio of a section of the inner contour image in all image combinations is completed, and finally N pixel density ratios are obtained.

Step 104: Calculate the grayscale image quality of the target area tissue according to the pixel density ratio.

As a refinement of the above step 104, the calculation of describing the grayscale image quality of the target area tissue based on the pixel density ratio includes but is not limited to the following implementation methods, for example: substituting the average value of the pixel density ratio into a preset function to calculate a numerical value describing the grayscale image quality of the target area tissue, and the preset function can be a linear function or a nonlinear function.

In order to facilitate understanding of the above-mentioned detailed contents, this embodiment provides an exemplary explanation in combination with a formula. For example, the average value of the effective pixel density ratio is x. When x is greater than 0 and less than 200, it can be substituted into formula (1) to obtain a numerical value describing the grayscale image quality of the target area tissue. Formula (1) is as follows:

F(x)＝100*x^0.7(0<x<200) Formula (1)

F(x)＝0(x<＝0) Formula (2)

F(x)＝100(x>＝200) Formula (3)

The above formula is only for illustrative purposes and can be replaced by any function. The embodiments of the present disclosure do not limit the formula.

The method for evaluating the quality of grayscale images provided by the present disclosure mainly includes the following technical solutions: respectively calculating the outer contour image and the inner contour image of the grayscale image of the target area tissue; respectively dividing the outer contour image and the inner contour image into N segments, and pairing each segment of the outer contour image with each segment of the inner contour image to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image; respectively calculating the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations to obtain N pixel density ratios, the pixel density ratio being the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, the pixel proportion being the ratio of the pixel point to the total pixel point; and calculating and describing the quality of the grayscale image of the target area tissue according to the pixel density ratio. Based on respectively calculating the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, an evaluation score for the quality of the grayscale image of the target area tissue is obtained, thereby realizing the quality evaluation of the grayscale image of the tissue.

FIG4 is a schematic diagram of a process of tissue grayscale image segmentation provided by an embodiment of the present disclosure. As shown in FIG4 ,

Step 201: Acquire a tissue grayscale image and a mask image, wherein the mask image is a binary image.

A tissue grayscale image to be segmented is obtained, and a mask image for performing tissue segmentation on the tissue grayscale image is obtained, wherein the mask image is a binary image, that is, the grayscale value of pixels in the mask image is 0 or 255.

Step 202: remap the grayscale interval of the tissue grayscale image to obtain an enhanced tissue grayscale image.

As a refinement of step 202, the main purpose of step 202 is to enhance the clarity of the tissue grayscale image. By remapping the grayscale, the tissue grayscale image is highlighted and the outline of the blurred area is made clearer, so as to finally obtain a clearer tissue grayscale image.

Step 203: performing tissue segmentation on the enhanced tissue grayscale image based on the mask image to obtain the target area tissue grayscale image.

Perform tissue segmentation on the area not covered by the mask image to obtain a tissue grayscale image of the target area.

As a refinement of the above embodiment, when executing step 101 to respectively calculate the outer contour image and the inner contour image of the target area tissue grayscale image, the following implementation methods can be adopted but are not limited to, for example: based on the expansion kernel, the target area tissue grayscale image is expanded to obtain a first tissue grayscale image; the first tissue grayscale image and the target area tissue grayscale image are differentially calculated to obtain an outer contour image; based on the erosion kernel, the target area tissue grayscale image is eroded to obtain a second tissue grayscale image; the second tissue grayscale image and the target area tissue grayscale image are differentially calculated to obtain an inner contour image.

The expansion kernel is a matrix constructed according to the size of the target area tissue grayscale image. If the target area tissue grayscale image is larger, the constructed matrix is larger and has more elements. The expansion kernel is used to expand the highlight area of the target area tissue grayscale image to obtain a first tissue grayscale image with an area larger than the target area tissue grayscale image. The expansion is actually a convolution calculation of the expansion kernel and the target area tissue grayscale image. Then, the obtained first tissue grayscale image is subjected to a differential calculation with the target area tissue grayscale image to obtain an outer contour image.

The corrosion process is consistent with the expansion process. The corrosion kernel is a matrix constructed according to the size of the target area tissue grayscale image. The larger the target area tissue grayscale image is, the larger the constructed matrix is and the more elements are. The corrosion kernel is used to reduce the highlight area of the target area tissue grayscale image to obtain a second tissue grayscale image with an area smaller than the target area tissue grayscale image. The corrosion is actually a convolution calculation between the corrosion kernel and the target area tissue grayscale image. Then, the obtained second tissue grayscale image is subjected to a differential calculation with the target area tissue grayscale image to obtain an inner contour image.

As a refinement of the above embodiment, when executing step 102 to divide the outer contour image and the inner contour image into N segments respectively, the following implementation methods can be adopted but are not limited to, for example: calibrating the segmentation positions of the outer contour image and the inner contour image, the segmentation positions of the outer contour image and the segmentation position values of the inner contour image correspond to each other; and dividing the outer contour image and the inner contour image into N segments respectively based on the segmentation positions.

As a refinement of the above embodiment, the calibration of the segmentation position includes: taking the first pixel point A in the outer contour image as the starting point, and dividing it into N segments along the contour line. Searching for the point B closest to point A in the inner contour image as the starting point, and dividing it into N segments along the contour line. At a certain level, the outer contour image and the inner contour image can be divided according to the number of pixels, and the contour line refers to treating the outer contour image and the inner contour image as a line without width for easy segmentation.

In some embodiments, the inner contour and the outer contour may be divided by, but not limited to, a preset ratio division, a preset length division, etc.

As a refinement of the above embodiment, when performing the pairing of each segment of the outer contour image with each segment of the inner contour image in pair in step 102, the following implementation methods may be adopted but are not limited to, for example: calculating the centroid of each segment of the outer contour image and the centroid of each segment of the inner contour image, the centroid calculated is the description of the shape of each segment of the outer contour image and each segment of the inner contour image; if the similarity between the centroid of a segment of the outer contour image and the centroid of a segment of the inner contour image is greater than a preset threshold, the segment of the outer contour image is paired with the segment of the inner contour image. Pairing the segment of the outer contour image with the segment of the inner contour image based on the centroid is essentially pairing the segment of the outer contour image with the segment of the inner contour image with the shape having the highest similarity to form an image combination.

As a refinement of the above embodiment, when executing the grayscale interval remapping of the tissue grayscale image described in step 202 to obtain an enhanced tissue grayscale image, the following implementation methods can be adopted but are not limited to, for example: widening the grayscale values whose number of pixels in the tissue grayscale image meets a first preset range, and the first preset range is the number range of pixels corresponding to the grayscale values that play a major role in the display of the tissue grayscale image; merging the grayscale values whose number of pixels in the tissue grayscale image meets a second preset range, and the second preset range is the number range of pixels corresponding to the grayscale values that do not play a major role in the display of the tissue grayscale image; remapping the widened and merged grayscale values to the tissue grayscale image to obtain the enhanced tissue grayscale image.

The purpose of the above steps is to enhance the clarity of the tissue grayscale image by expanding certain grayscale values to make the highlight area of the tissue grayscale image larger and by merging certain grayscale values to make the outline of the tissue grayscale image more obvious.

In the specific implementation process, the enhanced tissue grayscale image can be implemented in the following ways, but not limited to:

What you need to know is that the grayscale is divided into 256 blocks to draw the histogram. If it is a 16-bit image, 1 bin contains 256 grayscale levels, and if it is an 8-bit image, 1 bin contains only 1 grayscale level.

In the scenario, take the 256-bin statistical histogram as an example, and search the histogram from low point to high point: from the histogram 0bin to 255bin, traverse each bin in the histogram. If the value of this bin, that is, val, meets the condition of imgsize/5000<val<imgsize/10, it is a qualified value. On the contrary, the search from high point to low point is from the histogram 255bin to 0bin, find the value that meets the condition of imgsize/5000<val<imgsize/10, and stop searching. Among them, imgsize refers to the total number of pixels of the image, the bin is the gray value block, and the value of the bin, that is, val, is the number of pixels corresponding to each bin.

In order to more intuitively demonstrate the effects of the tissue grayscale image before and after enhancement, Figure 5 is a schematic diagram of an original tissue grayscale image provided in an embodiment of the present disclosure, and Figure 6 is a schematic diagram of a tissue grayscale image before and after enhancement provided in an embodiment of the present disclosure. The tissue grayscale image shown in Figure 6 is the effect after the tissue grayscale image of Figure 5 is enhanced.

At the same time, in order to facilitate understanding of the enhancement process of the tissue grayscale image, Figure 7 is a schematic diagram of a histogram corresponding to an original tissue grayscale image provided in an embodiment of the present disclosure, and Figure 8 is a schematic diagram of a histogram corresponding to an enhanced tissue grayscale image provided in an embodiment of the present disclosure. It can be seen from Figures 7 and 8 that the number of pixels and the corresponding grayscale values in the histogram corresponding to the enhanced tissue image are more discrete, and the selection of the above-mentioned bin value can refer to Figure 7.

As a refinement of the above embodiment, when executing step 104 to calculate the grayscale image quality of the target area tissue according to the pixel density ratio, the following implementation methods can be adopted but are not limited to, for example: calculating the average value of N pixel density ratios; calculating the grayscale image quality of the target area tissue according to the average value of the pixel density ratio.

The N pixel density ratios are added and then divided by N to obtain an average value of the pixel density ratios. The quality of the tissue grayscale image is determined according to the size of the average value. In the embodiment of the present disclosure, N is a positive integer.

In summary, the embodiments of the present disclosure can achieve the following effects:

1. Based on respectively calculating the pixel density ratio of a section of the outer contour image and a section of the inner contour image in each of the image combinations, an evaluation score for the quality of the tissue grayscale image of the target area is obtained, thereby realizing the quality evaluation of the tissue grayscale image.

2. When performing the quality assessment of the tissue grayscale image based on this embodiment, no manual supervision is required.

3. The influence of noise on the evaluation results can be reduced by dividing the inner contour image and the outer contour image into two segments and then calculating the average value of their pixel density ratio.

Corresponding to the above-mentioned grayscale image quality assessment method, the present invention also provides a grayscale image quality assessment device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

FIG9 is a schematic diagram of the structure of a grayscale image quality assessment device provided by an embodiment of the present disclosure, as shown in FIG9 , comprising:

The first calculation unit 31 is used to calculate and obtain the outer contour image and the inner contour image of the target area tissue grayscale image respectively;

A pairing unit 32, configured to divide the outer contour image and the inner contour image into N segments respectively, and pair each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image;

A second calculation unit 33 is used to calculate the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, to obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel points;

The third calculation unit 34 calculates the grayscale image quality of the target area tissue according to the pixel density ratio.

The device for evaluating the quality of grayscale images provided by the present disclosure includes: respectively calculating the outer contour image and the inner contour image of the grayscale image of the target area tissue; respectively dividing the outer contour image and the inner contour image into N segments, and pairing each segment of the outer contour image with each segment of the inner contour image to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image; respectively calculating the pixel density ratio of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations to obtain N pixel density ratios, the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel point; and calculating the quality of the grayscale image of the target area tissue according to the pixel density ratio. Based on respectively calculating the pixel density ratio of a segment of the outer contour image and a segment of the inner contour image in each of the image combinations, an evaluation score for the quality of the grayscale image of the target area tissue is obtained, thereby realizing the quality evaluation of the grayscale image of the tissue.

Further, in a possible implementation of this embodiment, FIG10 is a schematic diagram of the structure of another grayscale image quality assessment device provided by an embodiment of the present disclosure. As shown in FIG10 , the device includes:

An acquisition unit 35, used for acquiring a tissue grayscale image and a mask image, wherein the mask image is a binary image;

A remapping unit 36, configured to remap the grayscale interval of the tissue grayscale image to obtain an enhanced tissue grayscale image;

The segmentation unit 37 is used to perform tissue segmentation on the enhanced tissue grayscale image based on the mask image to obtain the target area tissue grayscale image.

Furthermore, in a possible implementation of this embodiment, as shown in FIG10 , the first calculating unit 31 includes:

An expansion module 311 is used to expand the target area tissue grayscale image based on the expansion kernel to obtain a first tissue grayscale image;

A first calculation module 312 is used for performing a difference calculation between the first tissue grayscale image and the target area tissue grayscale image to obtain an outer contour image;

An erosion module 313, configured to erode the target region tissue grayscale image based on the erosion kernel to obtain a second tissue grayscale image;

The second calculation module 314 is used to perform a difference calculation between the second tissue grayscale image and the target area tissue grayscale image to obtain an inner contour image.

Furthermore, in a possible implementation of this embodiment, as shown in FIG10 , the pairing unit 32 includes:

A calibration module 321 is used to calibrate the segmentation position of the outer contour image and the inner contour image, wherein the segmentation position of the outer contour image corresponds to the segmentation position value of the inner contour image;

The segmentation module 322 is used to segment the outer contour image and the inner contour image into N segments respectively based on the segmentation positions.

Furthermore, in a possible implementation of this embodiment, as shown in FIG10 , the pairing unit 32 further includes:

A calculation module 323, used to calculate the centroid of each segment of the external contour image and the centroid of each segment of the internal contour image, the calculated centroid is a description of the shape of each segment of the external contour image and each segment of the internal contour image;

The pairing module 324 is configured to pair a segment of the external contour image with a segment of the internal contour image when the similarity between the centroid of a segment of the external contour image and the centroid of a segment of the internal contour image is greater than a preset threshold.

Furthermore, in a possible implementation of this embodiment, as shown in FIG10 , the remapping unit 36 includes:

The stretching and merging module 361 is used to stretch the grayscale values whose number of pixels in the tissue grayscale image meets a first preset range, wherein the first preset range is the number range of pixels corresponding to the grayscale values that play a major role in displaying the tissue grayscale image; and to merge the grayscale values whose number of pixels in the tissue grayscale image meets a second preset range, wherein the second preset range is the number range of pixels corresponding to the grayscale values that do not play a major role in displaying the tissue grayscale image;

The remapping module 362 is used to remap the grayscale values after stretching and merging to the tissue grayscale image to obtain the enhanced tissue grayscale image.

Furthermore, in a possible implementation of this embodiment, as shown in FIG10 , the third calculation unit 34 includes:

A first calculation module 341 is used to calculate an average value of N pixel density ratios;

The second calculation module 342 is used to calculate the grayscale image quality of the target area tissue according to the average value of the pixel density ratio.

It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and the principle is the same, which is no longer limited in this embodiment.

According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

FIG. 11 shows a schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and/or required herein.

As shown in FIG. 11 , the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 into a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I/O (Input/Output) interface 405 is also connected to the bus 404.

Multiple components in the device 400 are connected to the I/O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc.

The communication unit 409 allows the device 400 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The computing unit 401 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a grayscale image quality assessment method.

For example, in some embodiments, the grayscale image quality assessment method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 408 .

In some embodiments, part or all of the computer program can be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409.

When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned grayscale image quality assessment method in any other appropriate manner (e.g., by means of firmware).

Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Array), ASICs (Application-Specific Integrated Circuit), ASSPs (Application Specific Standard Product), SOCs (System On Chip), CPLDs (Complex Programmable Logic Device), computer hardware, firmware, software, and/or combinations thereof.

These various embodiments may include being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions/operations specified in the flow chart and/or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or an LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer.

Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server for a distributed system, or a server combined with a blockchain.

It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning/deep learning, big data processing technology, knowledge graph technology, and other major directions.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

A method for grayscale image quality assessment, comprising:

The outer contour image and the inner contour image of the target area tissue grayscale image are calculated respectively;

Divide the outer contour image and the inner contour image into N segments respectively, and pair each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image;

Calculate the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations respectively, and obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel points to the total pixel points;

The grayscale image quality of the target area tissue is described by calculation according to the pixel density ratio.
The method according to claim 1 is characterized in that, before respectively calculating the outer contour image and the inner contour image of the target area tissue grayscale image, it comprises:

Acquire a tissue grayscale image and a mask image, wherein the mask image is a binary image;

Remapping the grayscale interval of the tissue grayscale image to obtain an enhanced tissue grayscale image;

The enhanced tissue grayscale image is subjected to tissue segmentation based on the mask image to obtain the target area tissue grayscale image.
The method according to claim 1, characterized in that the step of respectively calculating the outer contour image and the inner contour image of the target area tissue grayscale image comprises:

Dilate the target region tissue grayscale image based on the dilation kernel to obtain a first tissue grayscale image;

The first tissue grayscale image and the target area tissue grayscale image are subjected to differential calculation to obtain an outer contour image;

Corrosion is performed on the target area tissue grayscale image based on the corrosion kernel to obtain a second tissue grayscale image;

The second tissue grayscale image and the target area tissue grayscale image are differentially calculated to obtain an inner contour image.
The method according to claim 1, characterized in that the step of dividing the outer contour image and the inner contour image into N segments respectively comprises:

Marking the segmentation position of the outer contour image and the inner contour image, wherein the segmentation position of the outer contour image corresponds to the segmentation position value of the inner contour image;

The outer contour image and the inner contour image are respectively divided into N segments based on the segmentation positions.
The method according to claim 1, characterized in that pairing each segment of the outer contour image with each segment of the inner contour image in pairs comprises:

Calculate the centroid of each segment of the external contour image and the centroid of each segment of the internal contour image, and the calculated centroid is a description of the shape of each segment of the external contour image and each segment of the internal contour image;

If the similarity between the centroid of a segment of the external contour image and the centroid of a segment of the internal contour image is greater than a preset threshold, the segment of the external contour image and the segment of the internal contour image are paired.
The method according to claim 2, characterized in that the grayscale interval remapping of the tissue grayscale image to obtain an enhanced tissue grayscale image comprises:

The grayscale values whose number of pixels in the tissue grayscale image meets a first preset range are widened, and the first preset range is the number range of pixels corresponding to the grayscale values that play a major role in the display of the tissue grayscale image; the grayscale values whose number of pixels in the tissue grayscale image meets a second preset range are merged, and the second preset range is the number range of pixels corresponding to the grayscale values that do not play a major role in the display of the tissue grayscale image;

The grayscale values after broadening and merging are remapped to the tissue grayscale image to obtain the enhanced tissue grayscale image.
The method according to claim 1, characterized in that the step of calculating the grayscale image quality of the target area tissue according to the pixel density ratio comprises:

Calculate the average value of N pixel density ratios;

The grayscale image quality of the target area tissue is calculated based on the average value of the pixel density ratio.
A grayscale image quality assessment device, comprising:

A first calculation unit is used to calculate and obtain an outer contour image and an inner contour image of a target area tissue grayscale image respectively;

a pairing unit, configured to divide the outer contour image and the inner contour image into N segments respectively, and pair each segment of the outer contour image with each segment of the inner contour image in pairs to obtain N image combinations, each of which includes a segment of the outer contour image and a segment of the inner contour image;

A second calculation unit is used to calculate the pixel density ratio of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, to obtain N pixel density ratios, wherein the pixel density ratio is the ratio of the pixel proportion of a segment of the outer contour image to a segment of the inner contour image in each of the image combinations, and the pixel proportion is the ratio of the pixel point to the total pixel points;

A third calculation unit is configured to calculate a grayscale image quality describing the target area tissue according to the pixel density ratio.
An electronic device, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.
A computer program product, characterized in that it comprises a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1 to 7.