CN111105407B - A method, device, equipment and storage medium for evaluating the staining quality of pathological sections - Google Patents

Abstract

The embodiment of the invention discloses a pathological section dyeing quality evaluation method, a pathological section dyeing quality evaluation device, pathological section dyeing quality evaluation equipment and a storage medium. The method comprises the following steps: digitally scanning the dyed pathological section to obtain a medical image to be analyzed; performing feature recognition on the medical image to be analyzed to obtain a plurality of dyeing color values; and obtaining a dyeing standard value, and determining the dyeing quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of dyeing color values and the dyeing standard value. The invention has unified evaluation standard, adopts artificial intelligence to avoid subjective evaluation of pathologists or pathologists, ensures consistency of quality evaluation, is suitable for pathological section dyeing quality evaluation in the same laboratory, and is also suitable for pathological section dyeing quality evaluation among different laboratories.

Description

A method, device, equipment and storage medium for evaluating the staining quality of pathological sections

technical field

The invention relates to the technical field of quality evaluation, in particular to a method, device, equipment and storage medium for evaluating the quality of staining of pathological sections.

Background technique

Pathological technology is an important branch of pathology, the methodology in pathological research, and the basis of pathological diagnosis. Conventional pathology is the most important part of pathological technology, and any pathological diagnosis cannot be separated from it. Among them, immunohistochemical staining is an indispensable and important technique for modern pathological diagnosis techniques. The steps of immunohistochemical staining are cumbersome, and due to the operating techniques of different laboratories and technicians, the final effect of immunohistochemical staining may be completely incomplete. In the same laboratory, three different staining effects appear after three laboratory operators operate at different times, which may also have a serious impact on the results of the pathological diagnosis report in the later period.

At present, the quality control, whether within the same laboratory or between different laboratories, is often evaluated subjectively by pathologists or pathological technicians. On the one hand, everyone is not completely consistent with the standard of diagnostic quality, and most of them are subjective evaluations that are difficult to repeat; Reliable and accurate reviews. Therefore, the evaluation standards and results of each quality control are very unstable, which makes it difficult for the quality of immunohistochemical staining to achieve consistent staining quality in different laboratories. Therefore, it is particularly important to develop a method for evaluating the staining quality of pathological sections with uniform detection standards and suitable for both within the same laboratory and among different laboratories.

Contents of the invention

Based on this, it is necessary to address the above problems and propose a method, device, equipment and storage medium for evaluating the staining quality of pathological sections.

In the first aspect, the present invention provides a method for evaluating the staining quality of pathological sections, the method comprising:

Digitally scan the stained pathological sections to obtain medical images to be analyzed;

performing feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

A staining standard value is acquired, and the staining quality of the pathological section corresponding to the medical image to be analyzed is determined according to the multiple staining color values and the staining standard value.

In the second aspect, the present invention also proposes a device for evaluating the quality of staining of pathological sections, said device comprising:

The scanning module is used to digitally scan the stained pathological sections to obtain medical images to be analyzed;

A staining color value extraction module, configured to perform feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

The staining quality determination module is configured to acquire a staining standard value, and determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to a plurality of the staining color values and the staining standard value.

In the third aspect, the present invention also provides a storage medium storing a computer instruction program, and when the computer instruction program is executed by a processor, the processor executes the steps of any one of the methods described in the first aspect.

In a fourth aspect, the present invention also proposes a computer device, including at least one memory and at least one processor, the memory stores a computer instruction program, and when the computer instruction program is executed by the processor, the processing The device performs the steps of any one of the methods described in the first aspect.

In summary, the method for evaluating the staining quality of pathological sections of the present invention digitally scans the stained pathological sections to obtain medical images to be analyzed, and uses artificial intelligence to analyze the digitalized medical images to be analyzed, avoiding the need for pathologists or pathological technicians. The subjective evaluation ensures the consistency of quality evaluation; the feature recognition of the medical image to be analyzed is carried out to obtain multiple staining color values, obtain the staining standard value, and determine the corresponding medical image to be analyzed according to the multiple staining color values and staining standard values. The staining quality of the pathological sections, the method of identifying the staining color value is the same, and multiple staining color values and staining standard values are used for evaluation, the evaluation parameters are unified, the evaluation standard is unified, and artificial intelligence is used, so it is suitable for pathology in the same laboratory The evaluation of staining quality of slides is also suitable for the evaluation of staining quality of pathological slides between different laboratories. Therefore, the evaluation standard of the present invention is unified, the use of artificial intelligence avoids the subjective evaluation of pathologists or pathological technicians, ensures the consistency of quality evaluation, and is suitable for the evaluation of the staining quality of pathological sections in the same laboratory, and is also suitable for different laboratories. Evaluation of the staining quality of pathological sections.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

in:

Fig. 1 is a flow chart of the method for evaluating the quality of staining of pathological sections in an embodiment;

Fig. 2 is the flowchart of the identification staining color value of the pathological section staining quality evaluation method of Fig. 1;

Fig. 3 is a flow chart of identifying cell structure features of the pathological section staining quality evaluation method of Fig. 1;

Fig. 4 is the flow chart of calculating the color value of the pathological section staining quality evaluation method of Fig. 1;

Fig. 5 is a flow chart of determining the staining quality of the method for evaluating the staining quality of the pathological section in Fig. 1;

Fig. 6 is the flow chart of calculating the staining color difference of the pathological section staining quality evaluation method of Fig. 1;

Figure 7 is a flow chart of a method for evaluating the quality of staining of pathological sections in another embodiment;

Fig. 8 is the flow chart of analyzing unqualified reasons of the pathological section staining quality evaluation method of Fig. 1;

Fig. 9 is a structural block diagram of a pathological section staining quality evaluation device in an embodiment;

Figure 10 is a block diagram of a computer device in one embodiment.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

As shown in Figure 1, in one embodiment, a method for evaluating the quality of staining of pathological sections is proposed, the method comprising:

S102. Digitally scan the stained pathological section to obtain a medical image to be analyzed;

The pathological section refers to taking a lesion tissue of a certain size, making a pathological section with a histopathological method, and further examining the lesion with a microscope.

Traditional staining of pathological sections includes: HE staining, Bus staining, Wright Giemsa staining, collagen fiber staining (Masson, etc.), reticular fiber staining, elastic fiber staining, muscle tissue staining (hematoxylin phosphotungstic acid), fat staining (Sudan III), glycogen staining (PAS), mucus staining (PAS), etc. Immunochemical staining of pathological sections includes: immunohistochemical staining (immunohistochemical staining), immunofluorescent staining, etc., which are not specifically limited here. This application is exemplified by application to immunohistochemistry. It can be understood that the method of this application is also applicable to traditional staining and other immunochemical staining of pathological sections.

The digital scanning refers to digital scanning of stained pathological sections to obtain digital initial medical images. Digital scanning can be realized by using equipment such as a digital camera or a scanner, which is not specifically limited here as an example.

Wherein, the initial medical image may be directly used as the medical image to be analyzed, or an image obtained after correcting the initial medical image may be used as the medical image to be analyzed.

S104. Perform feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

Wherein, cell structure feature identification is performed according to the medical image to be analyzed to obtain a cell nucleus image and a cytoplasm image; color value calculation is performed respectively according to the cell nucleus image and the cytoplasm image to obtain a plurality of staining color values.

It can be understood that the plurality of staining color values may simultaneously include the negative staining color value of the nucleus, the negative staining color value of the cytoplasm, and the positive staining color value of the nucleus, and may also include the negative staining color value of the nucleus and the negative staining color value of the cytoplasm. . The color value of the positive staining of the cytoplasm may also include the color value of the negative staining of the nucleus, the color value of the negative staining of the cytoplasm, the color value of the positive staining of the nucleus, and the color value of the positive staining of the cytoplasm.

Optionally, the color value refers to the numerical values of three red (R), green (G), and blue (B) color channels, also called RGB values, expressed as (Rx, Gx, Bx), and Rx is the red channel The value of , Gx is the value of the green channel, and Bx is the value of the blue channel, which is not specifically limited in this example.

The negative staining color value of the cell nucleus refers to the color value obtained by negatively staining the nucleus.

The negative staining color value of cytoplasm refers to the color value obtained by negative staining of cytoplasm.

The positive staining color value of the cell nucleus refers to the color value obtained by staining the cell nucleus positively.

The color value of positive staining of cytoplasm refers to the color value obtained by positive staining of cytoplasm.

The nucleus refers to the largest and most important cell structure in a eukaryotic cell, which is the regulatory center of cytogenetics and metabolism, and is one of the most significant signs that distinguish eukaryotic cells from prokaryotic cells.

Said cytoplasm refers to cytoplasm, which is a general term for all translucent, colloidal and granular substances surrounded by the cytoplasmic membrane except the nuclear region.

S106. Acquire a staining standard value, and determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and the staining standard value.

Optionally, the dyeing standard value may be a specific RGB value, or a range value.

Optionally, scoring the staining color value and the staining standard value corresponding to the staining color value to obtain a staining color value score, and performing a comprehensive score according to all the staining color value scores to obtain a pathological section staining comprehensive score, Acquiring a standard value of the comprehensive staining score, and comparing the standard value of the comprehensive staining score with the comprehensive staining score of the pathological section to determine the staining quality of the pathological section corresponding to the medical image to be analyzed.

Optionally, when the dyeing color value is within the range of the dyeing standard value corresponding to the dyeing color value, the evaluation result of the dyeing color value is qualified; when the dyeing color value is within the range corresponding to the dyeing color value If the staining standard value is out of the range, the staining color value evaluation result is unqualified; according to all the staining color value evaluation results, a comprehensive evaluation is performed to obtain the staining quality of the pathological section corresponding to the medical image to be analyzed.

The comprehensive evaluation is carried out according to the evaluation results of all the dyeing color values to obtain the dyeing quality of the pathological slices corresponding to the medical image to be analyzed, including: when all the evaluation results of the dyeing color values are all qualified, then compare with the The staining quality of the pathological section corresponding to the medical image to be analyzed is qualified, and when all the dyed color value evaluation results are partially unqualified, the staining quality of the pathological section corresponding to the medical image to be analyzed is unqualified; understandable Yes, other comprehensive evaluation methods can also be used, and this example is not specifically limited.

The staining standard value is the pathological slice with the best staining quality evaluated by an expert pathologist, and the color value obtained after digital scanning according to the pathological slice is obtained through repeated tests and can be used for evaluation. The reference standard for stain quality.

It can be understood that there are multiple dyeing standard values, and the dyeing standard values are in one-to-one correspondence with the dyeing color values. For example, the negative staining color value of the cell nucleus corresponds to a staining standard value, the negative staining color value of the cytoplasm corresponds to a staining standard value, the positive staining color value of the cell nucleus corresponds to a staining standard value, and the positive staining color value of the cytoplasm corresponds to a staining standard value, here Examples are not specifically limited.

Optionally, the staining standard value includes: a cell nucleus negative staining standard value corresponding to the cell nucleus negative staining color value, a cytoplasm negative staining standard value corresponding to the cytoplasm negative staining color value, a cell nucleus staining value corresponding to the cell nucleus positive staining color value Standard value of positive staining, standard value of positive staining of cytoplasm corresponding to the color value of positive staining of cytoplasm.

Optionally, the one-to-one correspondence may mean that the dyeing standard value and the dyeing color value corresponding to the dyeing standard value adopt the same dyeing method, or it may refer to the dyeing standard value and the color value corresponding to the dyeing standard value The staining color value of the same organ tissue and the same staining method can also refer to the staining standard value and the staining color value corresponding to the staining standard value using the same organ tissue, the same staining method and the same pathology, in This example is not specifically limited.

Optionally, the stained pathological slices refer to pathological slices that have completed all staining stages, and the staining standard value is also the staining standard value corresponding to the pathological slices that have completed all staining stages.

Optionally, the staining includes multiple staining stages, and the stained pathological slices are stained in one of the staining stages, and the staining standard value is also the staining standard value corresponding to the pathological slices stained in the staining stage. The staining quality evaluation of the stained pathological sections by stages can quickly locate the staining stage of the unqualified stained pathological sections, which is convenient for follow-up and timely resolution of corresponding problems.

The method for evaluating the staining quality of pathological sections in this embodiment digitally scans the stained pathological sections to obtain medical images to be analyzed, and analyzes the digitalized medical images to be analyzed by artificial intelligence, avoiding the subjective evaluation of pathologists or pathological technicians , to ensure the consistency of quality evaluation; perform feature recognition on the medical image to be analyzed, obtain multiple staining color values, obtain the staining standard value, and determine the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and staining standard values Staining quality, the method of identifying the staining color value is the same, multiple staining color values and staining standard values are used for evaluation, the evaluation parameters are unified, the evaluation standard is unified, and artificial intelligence is used, so it is suitable for the evaluation of the staining quality of pathological sections in the same laboratory , It is also suitable for the evaluation of the staining quality of pathological sections between different laboratories.

As shown in Figure 2, in one embodiment, the medical image to be analyzed is subjected to feature recognition to obtain a plurality of staining color values, including:

S202. Perform cell structural feature recognition according to the medical image to be analyzed to obtain a cell nucleus image and a cytoplasm image;

Wherein, the cell nucleus segmentation algorithm and the cytoplasm segmentation algorithm can be selected from the prior art to perform feature recognition on the cell structure in the medical image to be analyzed respectively, so as to obtain the cell nucleus image and the cytoplasm image. It can be understood that other algorithms can also be used to identify the features of the cell structure in the medical image to be analyzed, which is not specifically limited by taking an example here.

S204. Perform color value calculation according to the nucleus image and the cytoplasm image respectively to obtain a plurality of staining color values, and the plurality of staining color values include the negative staining color value of the nucleus, the negative staining color value of the cytoplasm, and the positive staining value of the nucleus Color value and/or cytoplasmic positive staining color value.

As shown in Figure 3, in one embodiment, the cell structure feature recognition is performed according to the medical image to be analyzed to obtain a cell nucleus image and a cytoplasmic image, including:

S302. Using a cell nucleus segmentation algorithm to segment cell nuclei according to the medical image to be analyzed to obtain a cell nucleus image;

Specifically, according to the medical image to be analyzed, a cell nucleus is segmented using a cell nucleus segmentation algorithm to obtain a cell nucleus image, and the number of the cell nucleus images is multiple. The cell nucleus segmentation algorithm can be selected from the prior art, which will not be repeated here.

S304. Segment cytoplasm according to the medical image to be analyzed using a cytoplasm segmentation algorithm to obtain a cytoplasm image.

Specifically, according to the medical image to be analyzed, the cytoplasm is segmented using a cytoplasm segmentation algorithm to obtain a cytoplasm image, and the number of the cytoplasm images is multiple. The cytoplasm segmentation algorithm can be selected from the prior art, which will not be repeated here.

As shown in Figure 4, in one embodiment, in one embodiment, the color value calculation is performed respectively according to the cell nucleus image and the cytoplasm image to obtain a plurality of staining color values, and a plurality of the staining colors Values include nuclear negative staining color values, cytoplasmic negative staining color values, nuclear positive staining color values, and/or cytoplasmic positive staining color values, including:

S402. Classify according to the color value of the nucleus image to obtain a negative staining image of the nucleus and a positive staining image of the nucleus;

Specifically, the color value of the cell nucleus image is positively stained and classified as a nucleus positively stained image, and the color value of the cell nucleus image is negatively colored is classified as a cell nucleus negatively stained image. For example, in immunohistochemistry, the positive staining of cell nuclei is dark brown, and the negative staining of cell nuclei is blue, which is not specifically limited in this example.

S404. Classify according to the color value of the cytoplasmic image, and obtain a cytoplasmic negative staining image and a cytoplasmic positive staining image;

Specifically, the color value of the cytoplasmic image is positively stained and classified as a cytoplasmic positive staining image, and the color value of the cytoplasmic image is negatively colored is classified as a cytoplasmic negative staining image.

S406. Perform color value calculation according to the negative staining image of the nucleus, the positive staining image of the nucleus, the negative staining image of the cytoplasm, and the positive staining image of the cytoplasm to obtain the negative staining color value of the nucleus and the negative staining color of the cytoplasm value, positive staining color value of nucleus, and positive staining color value of cytoplasm.

Specifically, the color value is calculated according to the negative staining image of the cell nucleus to obtain the color value of the negative staining of the nucleus; the color value is calculated according to the positive staining image of the cell nucleus to obtain the color value of the positive staining of the nucleus; the color is calculated according to the negative staining image of the cytoplasm. Calculate the color value of negative cytoplasmic staining; calculate the color value according to the image of positive cytoplasmic staining to obtain the color value of positive cytoplasmic staining.

Wherein, the color value calculation can calculate the average value of RGB of all pixels in the dyed image, can also extract the maximum value of RGB of all pixels in the dyed image, and can also extract the minimum value of RGB of all pixels in the dyed image ; It can be understood that the calculation of the color value can also use other algorithms, which are not specifically limited here.

Optionally, the dyeing color value and the dyeing standard value corresponding to the dyeing color value adopt the same color value calculation method, thereby improving the accuracy and consistency of dyeing quality evaluation.

As shown in Figure 5, in one embodiment, the determination of the staining quality of the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and the staining standard value includes:

S502. Scoring the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain a dyeing color value score;

Wherein, when the dyeing standard value is a specific RGB value, the difference between the dyeing color value and the dyeing standard value corresponding to the dyeing color value is calculated to obtain the dyeing color difference, and according to the dyeing Score the color difference to obtain the dyeing color value score; when the dyeing standard value is a range value, then when the dyeing color value is within the range value of the dyeing standard value corresponding to the dyeing color value, the dyeing color Value scoring is a full score, and when the dyeing color value is not within the range of the dyeing standard value corresponding to the dyeing color value, the dyeing color value score is obtained by calculating according to the preset scoring rules.

When the dyeing color value is not within the range value of the dyeing standard value corresponding to the dyeing color value, the dyeing color value score is calculated according to the preset scoring rules, including: calculating the dyeing color value corresponding to the dyeing color value The average value of the range value starting point and the end point of the range value of the standard value obtains the dyeing standard value center; when the dyeing color value is less than the dyeing standard value center, then the dyeing standard value corresponding to the dyeing color value Subtract the dyeing color value from the starting point of the range value of the range value to obtain a deviation value; when the dyeing color value is greater than the center of the dyeing standard value, subtract the dyeing color value corresponding to the dyeing color value The end point of the range value of the range value of the dyeing standard value is a deviation difference, and the dyeing color value score is calculated according to the deviation difference.

The calculating and obtaining the dyeing color value score according to the deviation difference includes: multiplying the deviation difference by a preset coefficient to obtain a deviation score, and subtracting the deviation score from the full score to obtain a dyeing color value score. It can be understood that other algorithms may also be used to calculate the dyeing color value score, which is not specifically limited by taking an example here.

S504. Carry out a comprehensive score according to all the staining color value scores, and obtain a comprehensive score for pathological section staining;

Wherein, all the staining color value scores may be weighted and summed to obtain a comprehensive score for staining of the pathological section. It can be understood that other algorithms may also be used for the comprehensive score, which is not specifically limited here as an example.

Optionally, when performing weighted summation of all the scores of the staining color values, weights may be set for the staining color values according to the pathology, weights may be set for the staining color values according to the staining method, or weights may be set for the staining color values according to the pathology. The pathological and staining methods set weights for the staining color values, which are not specifically limited in this example.

S506. Acquire a standard dyeing comprehensive score, and compare the staining comprehensive score with the pathological slide comprehensive score to determine the staining quality of the pathological slice corresponding to the medical image to be analyzed.

Optionally, the dyeing comprehensive scoring standard value may be a specific RGB value, or a range value.

Wherein, when the dyeing comprehensive score standard value is a specific RGB value, then the pathological slice corresponding to the medical image to be analyzed when the dyeing comprehensive score of the pathological section is greater than or equal to the staining comprehensive score standard value is If the staining quality is qualified, then the staining quality of the pathological section corresponding to the medical image to be analyzed is unqualified when the comprehensive staining score of the pathological section is less than the standard value of the comprehensive staining score; when the standard value of the comprehensive staining score is When the comprehensive staining score of the pathological section is within the range value of the standard value of the comprehensive staining score, the staining quality of the pathological section corresponding to the medical image to be analyzed is qualified, and the comprehensive staining score of the pathological section is If the staining comprehensive scoring standard value is out of the range, the staining quality of the pathological section corresponding to the medical image to be analyzed is unqualified.

Optionally, the weight of each staining comprehensive scoring standard value can be set according to the pathology, the staining method, or the pathology and the staining method, which is not specifically limited in this example.

In this embodiment, by establishing an objective evaluation system and indicators, the accuracy and objectivity of the evaluation of the staining quality of pathological sections are improved, and it is no longer necessary to rely on professional pathologists for each evaluation, reducing the labor cost of evaluating the staining quality, and also It can avoid the subjectivity of different pathologists from affecting the accuracy of the evaluation, and it is also convenient to adopt a unified evaluation system in the same laboratory and between different laboratories, ensuring the consistency of quality evaluation.

In one embodiment, the scoring of the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain the dyeing color value score includes: calculating the dyeing color value, and the dyeing color value The difference before the corresponding dyeing standard value is obtained to obtain the dyeing color difference; scoring is performed according to the dyeing color difference to obtain the dyeing color value score.

As shown in Figure 6, in one embodiment, the dyed color value includes channel values of three channels, and the dyed standard value includes channel standard values of three channels;

The calculation of the difference between the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain the dyeing color difference includes:

S602. Calculate the channel difference between the channel value of each channel and the channel standard value corresponding to the channel value;

For example, when the color value adopts RGB, the channel value of the R channel of the dyed color value is subtracted from the channel value of the R channel of the dyed standard value corresponding to the dyed color value to obtain the R channel difference, and the The channel value of the G channel of the dyeing color value is subtracted from the channel value of the G channel of the dyeing standard value corresponding to the dyeing color value to obtain the G channel difference, and the channel value of the B channel of the dyeing color value is subtracted from the value The difference value of the B channel is obtained from the channel value of the B channel of the dyeing standard value corresponding to the dyeing color value, which is not specifically limited in this example.

S604. Perform absolute value calculation according to the channel difference to obtain the channel color difference;

For example, when RGB is used as the color value, the absolute value of the R channel difference is calculated to obtain the R channel color difference, the absolute value of the G channel difference is calculated to obtain the G channel color difference, and the absolute value of the B channel difference is calculated to obtain the B color difference. Channel color difference value, the R channel color difference value, G channel color difference value, and B channel color difference value are used as the channel color difference value.

S606. Perform weighted summation calculation according to the color difference values of the three channels to obtain the dyed color difference value.

For example, when RGB is used as the color value, the color difference value of the R channel, the color difference value of the G channel, and the color difference value of the B channel are weighted and summed to obtain the dyeing color difference value.

Optionally, the weight of the color difference value of each channel can be set according to pathology, or according to the coloring method, and can also be set according to pathology and coloring method, which is not specifically limited in this example.

In one embodiment, the scoring according to the dyeing color difference to obtain the dyeing color value score includes: dividing the dyeing color difference by a preset value to obtain the dyeing color value score. It can be understood that other algorithms can also be selected, for example, the dyeing color difference is directly used as the dyeing color value score, or the dyeing color difference is divided by 255 to obtain a difference index and 1 is subtracted from the difference The value index is used to obtain the dyeing color value score, which is not specifically limited in this example.

As shown in Figure 7, in one embodiment, a method for evaluating the quality of staining of pathological sections is also proposed, the method comprising:

S702. Digitally scan the stained pathological section to obtain an initial medical image;

Specifically, digital scanning is performed on the stained pathological sections to obtain digital initial medical images.

S704. Perform binarization processing on the initial medical image to obtain a binarized medical image;

Specifically, an image binarization algorithm is used on the initial medical image to obtain a binarized medical image.

Image binarization is the process of setting the grayscale value of pixels on the image to 0 or 255, that is, the process of presenting an obvious black and white effect to the entire image.

S706. Obtain the lowest color value from the binarized medical image to obtain the lowest binarized color value;

S708. Determine the lowest color value of the initial medical image corresponding to the binarized lowest color value according to the binarized lowest color value;

Specifically, the position of the corresponding pixel point is determined according to the binarized lowest color value, and the color value of the pixel point at the position before binarization is used as the initial medical image corresponding to the binarized lowest color value Minimum color value.

S710. Perform correction processing on the initial medical image according to the lowest color value of the initial medical image corresponding to the binarized lowest color value, to obtain the medical image to be analyzed;

Optionally, calculate the corrected color value according to the color value of white and the minimum color value of the initial medical image corresponding to the binarized minimum color value; Analyze medical images.

For example, when RGB is used as the color value, the channel value of the R channel of the lowest color value of the initial medical image corresponding to the binarized lowest color value is subtracted by 255 to obtain the corrected color value of the R channel, and subtracted by 255 The channel value of the G channel of the lowest color value of the initial medical image corresponding to the binarized lowest color value is obtained to obtain the corrected color value of the G channel, and the initial medical image corresponding to the binarized lowest color value is subtracted from 255 The channel value of the B channel of the lowest color value of the B channel is obtained to obtain the corrected color value of the B channel; the channel value of the R channel of all pixels of the initial medical image is subtracted from the corrected color value of the R channel, and the value of the initial medical image is The channel value of the G channel of all pixels minus the corrected color value of the G channel, the channel value of the B channel of all pixels of the initial medical image minus the corrected color value of the B channel, and the initial medical image after the subtraction is completed The image is used as the medical image to be analyzed, which is an example and is not specifically limited here.

The minimum color value of the initial medical image corresponding to the minimum color value of binarization refers to the background color, which is white under normal circumstances, and the RGB color value of white is (255,255,255). will change to another color.

S712. Perform feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

S714. Acquire a staining standard value, and determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard value.

In this embodiment, the medical image to be analyzed is obtained by correcting the initial medical image, and then the dyeing quality evaluation is performed on the medical image to be analyzed, so as to avoid the chromatic aberration caused by light during digital scanning, thereby further improving the quality of pathological sections. Accuracy of staining quality assessment.

In one embodiment, after the determination of the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard value, further includes: obtaining an evaluation information table, the The evaluation information table includes the laboratory identification corresponding to the stained pathological section, the dyer identification, and the dyeing process data; the evaluation information table, the medical image to be analyzed, a plurality of the dyeing color values, and the dyeing standard value . The staining quality of the pathological slice corresponding to the medical image to be analyzed is updated to the pathological slice staining database. Specifically, the evaluation information table input by the user is acquired, and then the evaluation information table corresponding to the stained pathological section, the medical image to be analyzed, a plurality of the staining color values, the staining standard value and the The staining quality of the pathological section corresponding to the medical image to be analyzed is added to the pathological section staining database.

The user may be a person who stains a pathological section, which is not specifically limited here as an example.

The dyeing process data includes reagent addition data, antibody addition data, and incubation conditions. The reagent addition data includes reagent name, time, and measurement. The antibody addition data includes antibody name, time, and measurement. For example, no specific limitation is made here. .

The dyer's identifier is used to uniquely identify a dyeing technician, which may be a name, ID, etc., and is not specifically limited here.

As shown in Figure 8, in one embodiment, the method also includes:

S802. Obtain the laboratory identification;

The laboratory identifier is used to uniquely identify a laboratory, and may be a laboratory name or a laboratory ID number, which is not specifically limited here.

S804. Obtain the evaluation information table corresponding to the unqualified staining quality of pathological slices, the medical image to be analyzed, multiple staining color values, and the staining standard value from the pathological slice staining database according to the laboratory identification. ;

S806. Perform unqualified cause analysis according to the evaluation information table, the medical image to be analyzed, multiple dyed color values, and the dyed standard value, to obtain unqualified cause data.

The failure cause analysis includes reagent addition metering, reagent addition time, reagent addition order, antibody addition metering, antibody addition time, and antibody addition order, which are not specifically limited by examples.

In one embodiment, after the unqualified cause analysis is performed according to the evaluation information table, the medical image to be analyzed, a plurality of the dyed color values and the dyed standard value, and the unqualified cause data is obtained, further The method includes: obtaining a list of improvement suggestions; obtaining improvement suggestions from the list of improvement suggestions according to the unqualified cause data, and obtaining a list of laboratory improvement suggestions. Specifically, the unqualified cause data is retrieved from the list of improvement suggestions, and matched to obtain a list of laboratory improvement suggestions.

The list of improvement suggestions is a rebuilt library established by expert pathologists after comprehensive evaluation from multiple stained pathological sections.

In this embodiment, the laboratory improvement suggestion list is obtained through data analysis, which is beneficial for the laboratory to improve the operation specification, inspection specification, and training system of the laboratory according to the laboratory improvement suggestion list.

As shown in Figure 9, in one embodiment, a device for evaluating the quality of staining of pathological sections is also proposed, the device comprising:

A scanning module 902, configured to digitally scan the stained pathological sections to obtain medical images to be analyzed;

A staining color value extraction module 904, configured to perform feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

The staining quality determining module 906 is configured to acquire a staining standard value, and determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and the staining standard value.

The apparatus for evaluating the quality of staining of pathological sections in this embodiment digitally scans the stained pathological sections to obtain medical images to be analyzed, and uses artificial intelligence to analyze the digitalized medical images to be analyzed, avoiding the subjective evaluation of pathologists or pathological technicians , to ensure the consistency of quality evaluation; perform feature recognition on the medical image to be analyzed, obtain multiple staining color values, obtain the staining standard value, and determine the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and staining standard values Staining quality, the method of identifying the staining color value is the same, multiple staining color values and staining standard values are used for evaluation, the evaluation parameters are unified, the evaluation standard is unified, and artificial intelligence is used, so it is suitable for the evaluation of the staining quality of pathological sections in the same laboratory , It is also suitable for the evaluation of the staining quality of pathological sections between different laboratories.

In one embodiment, the scanning module 902 includes a digitized scanning submodule and a color correction submodule;

The digital scanning sub-module is used to digitally scan the stained pathological section to obtain an initial medical image;

The color correction sub-module is used to perform binarization processing on the initial medical image to obtain a binarized medical image, obtain the lowest color value from the binarized medical image, and obtain the lowest binarized color value, Determine the lowest color value of the initial medical image corresponding to the binarized lowest color value according to the binarized lowest color value; Correction processing is performed on the initial medical image to obtain the medical image to be analyzed.

In one embodiment, the device also includes:

The data update module is used to obtain the evaluation information table, the evaluation information table includes the laboratory identification corresponding to the stained pathological section, the dyer identification, and the dyeing process data, and the evaluation information table, the medical image to be analyzed, A plurality of the staining color values, the staining standard value, and the staining quality of the pathological slice corresponding to the medical image to be analyzed are updated to the pathological slice staining database.

In one embodiment, the device also includes:

The laboratory quality control module is used to obtain the laboratory identification, and obtain the evaluation information table corresponding to the unqualified staining quality of the pathological section, the medical image to be analyzed, A plurality of the dyeing color values and the dyeing standard values are analyzed according to the evaluation information table, the medical image to be analyzed, a plurality of the dyeing color values and the dyeing standard values, and the unqualified cause data.

Figure 10 shows a diagram of the internal structure of a computer device in one embodiment. Specifically, the computer device may be a terminal or a server. As shown in FIG. 10, the computer device includes a processor, a memory, and a network interface connected through a system bus. Wherein, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and also stores a computer program. When the computer program is executed by the processor, the processor can realize the method for evaluating the staining quality of the pathological section. A computer program may also be stored in the internal memory, and when the computer program is executed by the processor, the processor may execute the method for evaluating the staining quality of the pathological section. Those skilled in the art can understand that the structure shown in Figure 10 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this 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, a method for evaluating the staining quality of a pathological section provided in the present application can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in FIG. 10 . The memory of the computer equipment can store various program templates of a pathological slide dyeing quality evaluation device. For example, scanning module 902 , dyeing color value extraction module 904 , dyeing quality determination module 906 .

In one embodiment, the present invention also provides a storage medium, which stores a computer instruction program, and when the computer instruction program is executed by a processor, the processor implements the following method steps when executed:

Digitally scan the stained pathological sections to obtain medical images to be analyzed;

performing feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

A staining standard value is acquired, and the staining quality of the pathological section corresponding to the medical image to be analyzed is determined according to the multiple staining color values and the staining standard value.

In the method steps of this embodiment, the stained pathological sections are digitally scanned to obtain medical images to be analyzed, and the digitalized medical images to be analyzed are analyzed by artificial intelligence, which avoids the subjective evaluation of pathologists or pathological technicians, and ensures the quality Consistency of evaluation; perform feature recognition on the medical image to be analyzed, obtain multiple staining color values, obtain staining standard values, determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and staining standard values, and identify The method of obtaining the staining color value is the same, and multiple staining color values and staining standard values are used for evaluation, the evaluation parameters are unified, the evaluation standard is unified, and artificial intelligence is used, so it is suitable for the evaluation of the staining quality of pathological sections in the same laboratory, and is also suitable for different Interlaboratory evaluation of staining quality of pathological slides.

In one embodiment, performing feature recognition on the medical image to be analyzed to obtain multiple staining color values includes: performing cell structure feature recognition according to the medical image to be analyzed to obtain a nucleus image and a cytoplasmic image; according to the cell nucleus The image and the cytoplasmic image are respectively subjected to color value calculation to obtain a plurality of staining color values, and the plurality of staining color values include the negative staining color value of the cell nucleus, the negative staining color value of the cytoplasm, the positive staining color value of the cell nucleus and/or the color value of the cell nucleus. Plasma positive staining color value.

In one embodiment, the identification of cell structure features based on the medical image to be analyzed to obtain a nucleus image and a cytoplasmic image includes: segmenting a cell nucleus using a nucleus segmentation algorithm based on the medical image to be analyzed to obtain a cell nucleus image; According to the medical image to be analyzed, a cytoplasmic segmentation algorithm is used to segment the cytoplasm to obtain a cytoplasmic image.

In one embodiment, the color value calculation is performed respectively according to the nucleus image and the cytoplasm image to obtain a plurality of staining color values, and the plurality of staining color values include the negative staining color value of the nucleus and the negative staining value of the cytoplasm. The color value, the positive staining color value of the nucleus and/or the positive staining color value of the cytoplasm include: classifying according to the color value of the nucleus image to obtain the negative staining image of the nucleus and the positive staining image of the nucleus; according to the color of the cytoplasmic image Values are classified to obtain cytoplasm negative staining images and cytoplasm positive staining images; according to the negative staining image of the nucleus, the positive staining image of the nucleus, the negative staining image of the cytoplasm, and the positive staining image of the cytoplasm respectively, color Calculate the color value of the negative staining of the nucleus, the negative staining color value of the cytoplasm, the positive staining color value of the nucleus, and the positive staining color value of the cytoplasm.

In one embodiment, the staining standard value includes: a negative staining standard value for the nucleus, a negative staining value for the cytoplasm, a positive staining value for the nucleus, and a positive staining value for the cytoplasm.

In one embodiment, the determining the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard value includes: combining the staining color value, the Scoring the staining standard value corresponding to the staining color value to obtain a staining color value score; performing a comprehensive score according to all the staining color value scores to obtain a comprehensive staining score for pathological sections; obtaining a staining comprehensive scoring standard value, according to the staining comprehensive scoring standard value and the pathological section staining comprehensive score to determine the staining quality of the pathological section corresponding to the medical image to be analyzed.

In one embodiment, the scoring of the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain the dyeing color value score includes: calculating the dyeing color value, and the dyeing color value The difference before the corresponding dyeing standard value is obtained to obtain the dyeing color difference; scoring is performed according to the dyeing color difference to obtain the dyeing color value score.

In one embodiment, the dyeing color value includes channel values of three channels, and the dyeing standard value includes channel standard values of three channels; The difference before the dyeing standard value is obtained to obtain the dyeing color difference, including: separately calculating the channel difference between the channel value of each channel and the channel standard value corresponding to the channel value; performing absolute value calculation according to the channel difference to obtain the channel Color difference: performing weighted summation calculation according to the color difference of the three channels to obtain the dyeing color difference.

In one embodiment, the scoring according to the dyeing color difference to obtain the dyeing color value score includes: dividing the dyeing color difference by a preset value to obtain the dyeing color value score.

In one embodiment, the digital scanning of the stained pathological section to obtain the medical image to be analyzed includes: digitally scanning the stained pathological section to obtain an initial medical image; performing binarization processing on the initial medical image , to obtain a binarized medical image; obtain the lowest color value from the binarized medical image to obtain the lowest binarized color value; The corresponding lowest color value of the initial medical image; correcting the initial medical image according to the lowest color value of the initial medical image corresponding to the binarized lowest color value to obtain the medical image to be analyzed.

In one embodiment, the correcting the initial medical image according to the lowest color value of the initial medical image corresponding to the lowest binarized color value to obtain the medical image to be analyzed includes:

calculating a corrected color value according to the white color value and the minimum color value of the initial medical image corresponding to the binarized minimum color value; obtaining the medical image to be analyzed according to the initial medical image and the corrected color value.

In one embodiment, after the determination of the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard values, further includes: obtaining an evaluation information table, the The evaluation information table includes the laboratory identification corresponding to the stained pathological section, the dyer identification, and the dyeing process data; the evaluation information table, the medical image to be analyzed, a plurality of the staining color values, and the staining standard value . The staining quality of the pathological slice corresponding to the medical image to be analyzed is updated to the pathological slice staining database.

In one embodiment, the method further includes: acquiring the laboratory identification; acquiring the evaluation information table corresponding to the unqualified staining quality of the pathological sections from the pathological section staining database according to the laboratory identification, the waiting list Analyzing the medical image, the multiple dyeing color values and the dyeing standard value; performing unqualified cause analysis according to the evaluation information table, the medical image to be analyzed, multiple dyeing color values and the dyeing standard value , to get the unqualified cause data.

In one embodiment, after the unqualified cause analysis is performed according to the evaluation information table, the medical image to be analyzed, a plurality of the dyed color values and the dyed standard value, and the unqualified cause data is obtained, further The method includes: obtaining a list of improvement suggestions; obtaining improvement suggestions from the list of improvement suggestions according to the unqualified cause data, and obtaining a list of laboratory improvement suggestions.

In one embodiment, the present invention also proposes a computer device, including at least one memory and at least one processor, the memory stores a program of computer instructions, and when the program of computer instructions is executed by the processor, the Said processor executes and implements the following method steps:

Digitally scan the stained pathological sections to obtain medical images to be analyzed;

performing feature recognition on the medical image to be analyzed to obtain a plurality of staining color values;

A staining standard value is acquired, and the staining quality of the pathological section corresponding to the medical image to be analyzed is determined according to the multiple staining color values and the staining standard value.

In the method steps of this embodiment, the stained pathological sections are digitally scanned to obtain medical images to be analyzed, and the digitalized medical images to be analyzed are analyzed by artificial intelligence, which avoids the subjective evaluation of pathologists or pathological technicians, and ensures the quality Consistency of evaluation; perform feature recognition on the medical image to be analyzed, obtain multiple staining color values, obtain staining standard values, determine the staining quality of the pathological section corresponding to the medical image to be analyzed according to the multiple staining color values and staining standard values, and identify The method of obtaining the staining color value is the same, and multiple staining color values and staining standard values are used for evaluation, the evaluation parameters are unified, the evaluation standard is unified, and artificial intelligence is used, so it is suitable for the evaluation of the staining quality of pathological sections in the same laboratory, and is also suitable for different Interlaboratory evaluation of staining quality of pathological slides.

In one embodiment, performing feature recognition on the medical image to be analyzed to obtain multiple staining color values includes: performing cell structure feature recognition according to the medical image to be analyzed to obtain a nucleus image and a cytoplasmic image; according to the cell nucleus The image and the cytoplasmic image are respectively subjected to color value calculation to obtain a plurality of staining color values, and the plurality of staining color values include the negative staining color value of the cell nucleus, the negative staining color value of the cytoplasm, the positive staining color value of the cell nucleus and/or the color value of the cell nucleus. Plasma positive staining color value.

In one embodiment, the identification of cell structure features based on the medical image to be analyzed to obtain a nucleus image and a cytoplasmic image includes: segmenting a cell nucleus using a nucleus segmentation algorithm based on the medical image to be analyzed to obtain a cell nucleus image; According to the medical image to be analyzed, a cytoplasmic segmentation algorithm is used to segment the cytoplasm to obtain a cytoplasmic image.

In one embodiment, the color value calculation is performed respectively according to the nucleus image and the cytoplasm image to obtain a plurality of staining color values, and the plurality of staining color values include the negative staining color value of the nucleus and the negative staining value of the cytoplasm. The color value, the positive staining color value of the nucleus and/or the positive staining color value of the cytoplasm include: classifying according to the color value of the nucleus image to obtain the negative staining image of the nucleus and the positive staining image of the nucleus; according to the color of the cytoplasmic image Values are classified to obtain cytoplasm negative staining images and cytoplasm positive staining images; according to the negative staining image of the nucleus, the positive staining image of the nucleus, the negative staining image of the cytoplasm, and the positive staining image of the cytoplasm respectively, color Calculate the color value of the negative staining of the nucleus, the negative staining color value of the cytoplasm, the positive staining color value of the nucleus, and the positive staining color value of the cytoplasm.

In one embodiment, the staining standard value includes: a negative staining standard value for the nucleus, a negative staining value for the cytoplasm, a positive staining value for the nucleus, and a positive staining value for the cytoplasm.

In one embodiment, the determining the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard value includes: combining the staining color value, the Scoring the staining standard value corresponding to the staining color value to obtain a staining color value score; performing a comprehensive score according to all the staining color value scores to obtain a comprehensive staining score for pathological sections; obtaining a staining comprehensive scoring standard value, according to the staining comprehensive scoring standard value and the pathological section staining comprehensive score to determine the staining quality of the pathological section corresponding to the medical image to be analyzed.

In one embodiment, the scoring of the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain the dyeing color value score includes: calculating the dyeing color value, and the dyeing color value The difference before the corresponding dyeing standard value is obtained to obtain the dyeing color difference; scoring is performed according to the dyeing color difference to obtain the dyeing color value score.

In one embodiment, the dyeing color value includes channel values of three channels, and the dyeing standard value includes channel standard values of three channels; The difference before the dyeing standard value is obtained to obtain the dyeing color difference, including: separately calculating the channel difference between the channel value of each channel and the channel standard value corresponding to the channel value; performing absolute value calculation according to the channel difference to obtain the channel Color difference: performing weighted summation calculation according to the color difference of the three channels to obtain the dyeing color difference.

In one embodiment, the scoring according to the dyeing color difference to obtain the dyeing color value score includes: dividing the dyeing color difference by a preset value to obtain the dyeing color value score.

In one embodiment, the digital scanning of the stained pathological section to obtain the medical image to be analyzed includes: digitally scanning the stained pathological section to obtain an initial medical image; performing binarization processing on the initial medical image , to obtain a binarized medical image; obtain the lowest color value from the binarized medical image to obtain the lowest binarized color value; The corresponding lowest color value of the initial medical image; correcting the initial medical image according to the lowest color value of the initial medical image corresponding to the binarized lowest color value to obtain the medical image to be analyzed.

In one embodiment, the correcting the initial medical image according to the lowest color value of the initial medical image corresponding to the lowest binarized color value to obtain the medical image to be analyzed includes:

calculating a corrected color value according to the white color value and the minimum color value of the initial medical image corresponding to the binarized minimum color value; obtaining the medical image to be analyzed according to the initial medical image and the corrected color value.

In one embodiment, after the determination of the staining quality of the pathological section corresponding to the medical image to be analyzed according to the plurality of staining color values and the staining standard values, further includes: obtaining an evaluation information table, the The evaluation information table includes the laboratory identification corresponding to the stained pathological section, the dyer identification, and the dyeing process data; the evaluation information table, the medical image to be analyzed, a plurality of the staining color values, and the staining standard value . The staining quality of the pathological slice corresponding to the medical image to be analyzed is updated to the pathological slice staining database.

In one embodiment, the method further includes: acquiring the laboratory identification; acquiring the evaluation information table corresponding to the unqualified staining quality of the pathological sections from the pathological section staining database according to the laboratory identification, the waiting list Analyzing the medical image, the multiple dyeing color values and the dyeing standard value; performing unqualified cause analysis according to the evaluation information table, the medical image to be analyzed, multiple dyeing color values and the dyeing standard value , to get the unqualified reason data.

In one embodiment, after the unqualified cause analysis is performed according to the evaluation information table, the medical image to be analyzed, a plurality of the dyed color values and the dyed standard value, and the unqualified cause data is obtained, further The method includes: obtaining a list of improvement suggestions; obtaining improvement suggestions from the list of improvement suggestions according to the unqualified cause data, and obtaining a list of laboratory improvement suggestions.

It should be noted that the above-mentioned method for evaluating the quality of staining of pathological sections, a device for evaluating the quality of staining of pathological sections, storage media, and computer equipment belong to a general inventive concept, a method for evaluating the quality of staining of pathological sections, and a method for evaluating the quality of staining of pathological sections. The contents in the embodiments of the quality evaluation device, storage medium and computer equipment are applicable to each other.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized through computer programs to instruct related hardware, and the programs can be stored in a non-volatile computer-readable storage medium When the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

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 express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. 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 (17)

1. A method for evaluating the staining quality of a pathological section, the method comprising:

digitally scanning the dyed pathological section to obtain a medical image to be analyzed;

performing feature recognition on the medical image to be analyzed to obtain a plurality of dyeing color values;

obtaining a dyeing standard value, and determining the dyeing quality of a pathological section corresponding to the medical image to be analyzed according to a plurality of dyeing color values and the dyeing standard value;

Performing feature recognition on the medical image to be analyzed to obtain a plurality of dyeing color values, wherein the feature recognition comprises the following steps:

performing cell structure feature recognition according to the medical image to be analyzed to obtain a cell nucleus image and a cell plasma image,

respectively calculating color values according to the cell nucleus image and the cell plasma image to obtain a plurality of dyeing color values, wherein the plurality of dyeing color values comprise cell nucleus negative dyeing color values, cell plasma negative dyeing color values, cell nucleus positive dyeing color values and/or cell plasma positive dyeing color values;

the staining standard values include: nuclear negative staining standard value, cytoplasmic negative staining standard value, nuclear positive staining standard value, and cytoplasmic positive staining standard value.

2. The method for evaluating the quality of staining of a pathological section according to claim 1, wherein the staining standard value and the staining color value corresponding to the staining standard value are the same, or,

the dyeing standard value and the dyeing color value corresponding to the dyeing standard value adopt the tissues of the same organ and the same dyeing method, or,

the dyeing standard value and the dyeing color value corresponding to the dyeing standard value adopt tissues of the same organ, the same dyeing method and the same pathology.

3. The method for evaluating the staining quality of pathological sections according to claim 1, wherein the step of performing cell structure feature recognition according to the medical image to be analyzed to obtain a nuclear image and a cytoplasm image comprises the steps of:

dividing cell nuclei by a cell nucleus segmentation algorithm according to the medical image to be analyzed to obtain a cell nucleus image;

and dividing the cytoplasm according to the medical image to be analyzed by adopting a cytoplasm dividing algorithm to obtain a cytoplasm image.

4. The pathological section staining quality evaluation method according to claim 1, wherein the calculating of the color values from the nuclear image and the cytoplasmic image, respectively, to obtain a plurality of staining color values, the plurality of staining color values including a nuclear negative staining color value, a cytoplasmic negative staining color value, a nuclear positive staining color value, and/or a cytoplasmic positive staining color value, comprises:

classifying according to the color value of the cell nucleus image to obtain a cell nucleus negative staining image and a cell nucleus positive staining image;

classifying according to the color value of the cytoplasm image to obtain a cytoplasm negative staining image and a cytoplasm positive staining image;

And calculating color values according to the cell nucleus negative staining image, the cell nucleus positive staining image, the cell plasma negative staining image and the cell plasma positive staining image respectively to obtain a cell nucleus negative staining color value, a cell plasma negative staining color value, a cell nucleus positive staining color value and a cell plasma positive staining color value.

5. The method according to claim 1, wherein determining the quality of staining of the pathological section corresponding to the medical image to be analyzed from the plurality of staining color values and the staining standard value comprises:

scoring the dyeing color value and a dyeing standard value corresponding to the dyeing color value to obtain a dyeing color value score;

comprehensively scoring according to all the staining color value scores to obtain pathological section staining comprehensive scores;

and obtaining a comprehensive dyeing score standard value, and comparing according to the comprehensive dyeing score standard value and the comprehensive pathological section dyeing score to determine the dyeing quality of the pathological section corresponding to the medical image to be analyzed.

6. The method for evaluating the staining quality of a pathological section according to claim 5, wherein scoring the staining color value and the staining standard value corresponding to the staining color value to obtain a staining color value score comprises:

When the dyeing standard value is an RGB value, calculating the dyeing color value and a difference value before the dyeing standard value corresponding to the dyeing color value to obtain a dyeing color difference value;

scoring according to the dyeing color difference value to obtain a dyeing color value score;

and when the dyeing standard value is a range value, the dyeing color value score is full when the dyeing color value is within the range value of the dyeing standard value corresponding to the dyeing color value, and when the dyeing color value is not within the range value of the dyeing standard value corresponding to the dyeing color value, the dyeing color value score is calculated according to a preset scoring rule.

7. The method according to claim 6, wherein calculating a dyeing color value score according to a preset scoring rule when the dyeing color value is not within a range of dyeing standard values corresponding to the dyeing color value, comprises:

calculating the average value of the range value starting point and the end point of the range value of the dyeing standard value corresponding to the dyeing color value to obtain a dyeing standard value center;

when the dyeing color value is smaller than the center of the dyeing standard value, subtracting the dyeing color value from the range value starting point of the range value of the dyeing standard value corresponding to the dyeing color value to obtain a deviation difference value;

And when the dyeing color value is larger than the dyeing standard value center, subtracting the range value end point of the range value of the dyeing standard value corresponding to the dyeing color value from the dyeing color value to obtain a deviation difference value, and calculating according to the deviation difference value to obtain a dyeing color value score.

8. The method for evaluating the staining quality of a pathological section according to claim 6, wherein the staining color value comprises a channel number value of three channels, and the staining standard value comprises a channel standard value of three channels;

the calculating the difference between the dyeing color value and the dyeing standard value corresponding to the dyeing color value to obtain a dyeing color difference value comprises the following steps:

respectively calculating a channel difference value between the channel value of each channel and a channel standard value corresponding to the channel value;

calculating an absolute value according to the channel difference value to obtain a channel color difference value;

and carrying out weighted summation calculation according to the three channel color differences to obtain a dyeing color difference.

9. The method for evaluating the staining quality of a pathological section according to claim 6, wherein the scoring according to the staining color difference value to obtain a staining color value score comprises:

Dividing the dyeing color difference value by a preset numerical value to obtain a dyeing color value score;

or alternatively, the first and second heat exchangers may be,

scoring the dyeing color difference value as a dyeing color value;

or alternatively, the first and second heat exchangers may be,

dividing the dyeing color difference value by 255 to obtain a difference index, and subtracting the difference index from 1 to obtain a dyeing color value score.

10. The method for evaluating the staining quality of a pathological section according to any one of claims 1 to 9, wherein the digitally scanning the stained pathological section to obtain a medical image to be analyzed comprises:

digitally scanning the dyed pathological section to obtain an initial medical image;

performing binarization processing on the initial medical image to obtain a binarized medical image;

acquiring a color value with the lowest numerical value from the binarized medical image to obtain a binarized lowest color value;

determining a lowest color value of the initial medical image corresponding to the binarized lowest color value according to the binarized lowest color value;

and correcting the initial medical image according to the minimum color value of the initial medical image corresponding to the binarized minimum color value to obtain the medical image to be analyzed.

11. The pathological section staining quality evaluation method according to claim 10, wherein the performing correction processing on the initial medical image according to the lowest color value of the initial medical image corresponding to the binarized lowest color value to obtain the medical image to be analyzed comprises:

Calculating a corrected color value according to the color value of the white and the lowest color value of the initial medical image corresponding to the binarized lowest color value; and obtaining the medical image to be analyzed according to the initial medical image and the corrected color value.

12. The method according to any one of claims 1 to 9, characterized by further comprising, after said determining the quality of staining of a pathological section corresponding to the medical image to be analyzed from a plurality of the staining color values and the staining standard values:

acquiring an evaluation information table, wherein the evaluation information table comprises laboratory marks, dyeing person marks and dyeing process data corresponding to dyed pathological sections;

updating the evaluation information table, the medical image to be analyzed, a plurality of dyeing color values, the dyeing standard values and the dyeing quality of pathological sections corresponding to the medical image to be analyzed to a pathological section dyeing database.

13. The pathological section staining quality evaluation method according to claim 12, wherein the method further comprises:

acquiring the laboratory identification;

acquiring the evaluation information table, the medical image to be analyzed, a plurality of dyeing color values and the dyeing standard values corresponding to unqualified dyeing quality of the pathological section from a pathological section dyeing database according to the laboratory mark;

And carrying out unqualified reason analysis according to the evaluation information table, the medical image to be analyzed, the plurality of dyeing color values and the dyeing standard value to obtain unqualified reason data.

14. The method according to claim 13, wherein after performing failure cause analysis based on the evaluation information table, the medical image to be analyzed, the plurality of the dyeing color values, and the dyeing standard value, obtaining failure cause data, further comprising:

acquiring an improvement suggestion list;

and acquiring an improvement suggestion from the improvement suggestion list according to the unqualified reason data, and obtaining a laboratory improvement suggestion list.

15. A pathological section staining quality evaluation apparatus, characterized in that the apparatus comprises:

the scanning module is used for digitally scanning the dyed pathological section to obtain a medical image to be analyzed;

the dyeing color value extraction module is used for carrying out feature recognition on the medical image to be analyzed to obtain a plurality of dyeing color values;

the dyeing quality determining module is used for obtaining a dyeing standard value and determining the dyeing quality of the pathological section corresponding to the medical image to be analyzed according to a plurality of dyeing color values and the dyeing standard value;

The dyeing color value extraction module is specifically configured to:

performing cell structure feature recognition according to the medical image to be analyzed to obtain a cell nucleus image and a cell plasma image, and performing color value calculation according to the cell nucleus image and the cell plasma image to obtain a plurality of dyeing color values, wherein the plurality of dyeing color values comprise a cell nucleus negative dyeing color value, a cell plasma negative dyeing color value, a cell nucleus positive dyeing color value and/or a cell plasma positive dyeing color value;

the staining standard values include: nuclear negative staining standard value, cytoplasmic negative staining standard value, nuclear positive staining standard value, and cytoplasmic positive staining standard value.

16. A storage medium storing a program of computer instructions which, when executed by a processor, cause the processor to perform the steps of the method of any one of claims 1 to 14.

17. A computer device comprising at least one memory, at least one processor, the memory storing a program of computer instructions that, when executed by the processor, cause the processor to perform the steps of the method of any of claims 1 to 14.