Method for generating pathological diagnosis report for pathological diagnosis case, and computing system for performing same

Abstract

Provided are a method for generating a pathological diagnosis report for a pathological diagnosis case, composed of a plurality of biological tissue images, which are digital scan images respectively of a plurality of tissue specimens collected from the prostate of a given patient, and a computing system for performing same. According to an aspect of the present invention, the method includes a step of obtaining a diagnostic result for each of the plurality of biological tissue images, which includes the steps of: obtaining a diagnosis name of the tissue specimen corresponding to each biological tissue image, and a primary Gleason pattern and secondary Gleason pattern of the biological tissue image; and extracting a representative lesion area of the biological tissue image, which is a partial region representative of the biological tissue image, wherein the diagnostic part for the biological tissue image includes the diagnosis name of the tissue specimen corresponding to the biological tissue image, the primary Gleason pattern and secondary Gleason pattern of the biological tissue image, and an image of the representative lesion area of the biological tissue image overlaid with pixel-level diagnostic results.

Description

Method for generating a pathology diagnosis report for a pathology diagnosis case and a computing system for performing the same

[0001] The present invention relates to a method for generating a pathology diagnosis report for a pathology diagnosis case comprising a plurality of biological tissue images, each of which is a digital scan image of a plurality of tissue specimens collected from the prostate of a given patient, and a computing system for performing the same.

[0002]

[0003] In medicine, pathology, which involves interpreting actual specimens, is crucial for accurately diagnosing and predicting the prognosis of serious diseases. Conventional pathology diagnostic methods involve visual observation and interpretation of diagnostic pathology slides produced from specimens through an optical microscope by a pathologist. The dawn of digital pathology began with the use of a computer-connected microscope camera to convert pathology slides into digital images, which are then viewed and interpreted on a monitor. Recently, the advent of digital slide scanners has led to the widespread adoption of this method, which converts entire pathology slides into a single digital image, which is then viewed and interpreted on a computer monitor. Digital pathology-based pathology, which interprets scanned images on a monitor, is replacing the traditional method of visually examining specimen slides through an optical microscope.

[0004] Meanwhile, to diagnose serious diseases such as cancer, part or all of the tissue is collected, an image of the biological tissue is created, and histopathological examination is performed to determine the severity of the disease. There is an agreed-upon system for reporting the histological severity for each disease, and these systems grade and report the severity based on the morphological characteristics of the tissue. For example, in the case of prostate cancer, there is a grading system called the Gleason grading system, which classifies the tissue pattern into grades from 1 to 5 based on the morphological characteristics of the gland tissue, and grades the overall severity based on the proportion of each grade area in the entire tissue. In addition, breast cancer can be graded based on the histological grade.

[0005] Meanwhile, histological examinations are sometimes performed on multiple biopsy images from a single patient. For example, multiple cores are extracted from a prostate biopsy, each core is made into slides for histological analysis. In this case, multiple slides produced from multiple cores constitute a single pathological diagnostic case.

[0006] Pathology reports, which include diagnostic results from tissue images and a summary of the entire pathology case, are often utilized as tools for explaining these diagnostic results to patients or sharing them with other pathologists. Therefore, a method is needed to create a pathology report that effectively explains the diagnostic results from tissue images and summarizes the overall pathology case in a format that can be easily understood by other pathologists.

[0007] Additionally, for the purposes described above, the pathology report needs to be accompanied by images representing each biopsy tissue image or a pathology diagnosis case, and these representative images need to be annotated with severity grades such as Gleason pattern.

[0008] However, the whole slide image generated by the slide scanner needs to be scanned at a magnification of 200x or more for an accurate diagnosis, and the number of pixels in the image generated in this way reaches 2.4 billion when a 2cm x 3cm area is scanned 200x, and 9.6 billion when scanned 400x. Therefore, it is difficult to use the biological tissue image as is due to its enormous size, and a technology is needed to accurately extract the lesion area that can represent the biological tissue image or the lesion area that can represent the corresponding case among the numerous biological tissue images contained within the image.

[0009]

[0010] The technical task to be achieved by the present invention is to provide a method for generating a pathology diagnosis report in a form that can effectively convey the overall and specific diagnosis results of a pathology diagnosis case to a patient or other diagnostician, and a computing system for performing the same.

[0011] In addition, a method for effectively extracting a lesion area representing a biological tissue image and a computing system for performing the same are provided.

[0012] In addition, the present invention provides a method for extracting a lesion area representing a pathological diagnosis case composed of a plurality of biological tissue images, and a computing system for performing the same.

[0013]

[0014] According to one aspect of the present invention, there is provided a method for generating a pathology diagnosis report for a pathology diagnosis case comprising a plurality of biological tissue images, which are digital scan images of each of a plurality of tissue specimens collected from the prostate of a given patient, the method comprising: a step of a computing system obtaining the plurality of biological tissue images included in the pathology diagnosis case and a pixel-wise diagnosis result of each of the plurality of biological tissue images, wherein the pixel-wise diagnosis result of the biological tissue image includes a Gleason Pattern for each pixel constituting the biological tissue image; a step of the computing system obtaining, for each of the plurality of biological tissue images, a diagnosis result of the biological tissue image; a step of the computing system generating, for each of the plurality of biological tissue images, a diagnosis part of the pathology diagnosis report for the biological tissue image; and a step of the computing system generating, for each of the plurality of biological tissue images, a pathology diagnosis report which is an electronic document including a diagnosis part for each of the plurality of biological tissue images, wherein the step of obtaining the diagnosis result of the biological tissue image comprises: a step of obtaining a diagnosis name of a tissue specimen corresponding to the biological tissue image; A method is provided, comprising: a step of obtaining a first Gleason pattern and a second Gleason pattern of the biological tissue image when the diagnosis of the tissue sample is not benign; and a step of extracting a representative lesion area of ​​the biological tissue image, which is a representative portion of the biological tissue image, when the diagnosis of the tissue sample is not benign, wherein the diagnostic part for the biological tissue image includes a diagnosis of the tissue sample corresponding to the biological tissue image when the diagnosis of the tissue sample is benign, and further includes an image of the first Gleason pattern and the second Gleason pattern of the biological tissue image and a representative lesion area of ​​the biological tissue image in which a pixel-by-pixel diagnosis result is overlapped when the diagnosis of the tissue sample is not benign.

[0015] In one embodiment, the method further includes a step of obtaining information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of a plurality of zones that divide the prostate into a plurality of zones, and the diagnostic part for the biological tissue image may further include a prostate diagram in which a zone corresponding to each of the plurality of zones is divided and a zone corresponding to a site from which a tissue sample corresponding to the biological tissue image was collected is visually highlighted.

[0016] In one embodiment, the step of acquiring a diagnosis result of the biological tissue image includes the step of acquiring a length of a tissue specimen corresponding to the biological tissue image; and, if the diagnosis of the tissue specimen is not benign, the step of acquiring a length of a lesion included in the tissue specimen corresponding to the biological tissue image, a ratio of the lesion in the tissue specimen corresponding to the biological tissue image, and a ratio of each pattern on the Gleason grading system to the lesion included in the tissue specimen corresponding to the biological tissue image, wherein the diagnosis part for the biological tissue image further includes the length of the tissue specimen corresponding to the biological tissue image, and, if the diagnosis of the tissue specimen is not benign, may further include at least a portion of the biological tissue image in which the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, the ratio of each pattern on the Gleason grading system to the lesion included in the tissue specimen corresponding to the biological tissue image, and an outline of an area corresponding to a representative lesion image of the biological tissue image are expressed.

[0017] In one embodiment, the step of extracting a representative lesion area of ​​the biological tissue image may include the steps of: searching for a first partial area, among partial areas of the biological tissue image, in which the first Gleason pattern is most frequently included in the pixel-wise diagnosis result corresponding to the corresponding area, wherein the partial area of ​​the biological tissue image is a part of the biological tissue image and has a predefined shape and area; generating a modified pixel-wise diagnosis result by removing the pixel-wise diagnosis result corresponding to the first partial area from the pixel-wise diagnosis result of the biological tissue image; searching for a second partial area, among partial areas of the biological tissue image, in which the second Gleason pattern is most frequently included in the modified pixel-wise diagnosis result corresponding to the corresponding area; and determining the first partial area of ​​the biological tissue image and the second partial area of ​​the biological tissue image as the representative lesion area of ​​the biological tissue image.

[0018] In one embodiment, the method further comprises: a step in which the computing system obtains information about a site from which a tissue specimen corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of a plurality of regions in which the prostate is divided; a step in which the computing system obtains, for each of the plurality of regions, a diagnosis result for the region determined based on a diagnosis result of a biological tissue image corresponding to a tissue specimen collected from the region among the plurality of biological tissue images; and a step in which the computing system generates a summary part for the pathology diagnosis case, wherein the pathology diagnosis report further comprises the summary part, and the summary part for the pathology diagnosis case comprises: a summary table including a diagnosis result for each of the plurality of regions; and a prostate diagram of the pathology diagnosis case in which regions corresponding to each of the plurality of regions are divided, and each region is given a predetermined visual effect determined by the diagnosis result for the corresponding region.

[0019] In one embodiment, the diagnostic result for the area may include at least some of the following: a diagnosis of the area, a primary Gleason pattern and a secondary Gleason pattern of the area, a length of a tissue sample taken from the area, a length of a lesion included in a tissue sample taken from the area, a proportion of the tissue sample taken from the area that is occupied by the lesion, a number of tissue samples taken from the area, and pathological features found in the tissue samples taken from the area.

[0020] In one embodiment, the summary part for the pathology diagnosis case may further include a diagnosis overview including a diagnosis name representing the pathology diagnosis case, the number of multiple tissue samples collected from the prostate of the patient, the number of tissue samples in which lesions are found among the multiple tissue samples collected from the prostate of the patient, and the primary Gleason pattern and secondary Gleason pattern of the pathology diagnosis case.

[0021] In one embodiment, the method comprises: a step in which the computing system obtains information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of a plurality of regions of the prostate; a step in which the computing system obtains, for each of the plurality of regions, a diagnostic result for the region determined based on a diagnostic result of a biological tissue image corresponding to a tissue sample collected from the region among the plurality of biological tissue images; And the computing system further includes a step of generating a summary part for the pathology diagnosis case, and the pathology diagnosis report further includes the summary part, and the summary part for the pathology diagnosis case includes a summary table composed of summary information for each of the plurality of zones, and the summary information for the zone includes a diagnosis result for the zone and a bar diagram corresponding to each tissue specimen collected from the zone, and the bar diagram is composed of parts corresponding to each non-lesion area and lesion area distributed in the corresponding tissue specimen, and each part included in the bar diagram has a length proportional to the length of the area corresponding to the corresponding part, and a predetermined visual effect corresponding to a Gleason pattern of the area corresponding to the corresponding part can be applied.

[0022] In one embodiment, the method further comprises a step of the computing system generating a representative lesion image of the pathology diagnosis case, wherein the pathology diagnosis report further includes the representative lesion image, and the step of generating the representative lesion image of the pathology diagnosis case comprises: obtaining a first Gleason pattern and a second Gleason pattern of the pathology diagnosis case; searching for a first partial region, a second partial region, and a third partial region of each of the plurality of biological tissue images; and selecting a representative lesion image representing the pathology diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images, wherein the step of searching for the first partial region, the second partial region, and the third partial region of the biological tissue image comprises: searching for, among the partial regions of the biological tissue image, the first partial region in which the first Gleason pattern of the pathology diagnosis case is most abundantly included in a pixel-wise diagnosis result corresponding to the corresponding region, wherein the partial region of the biological tissue image is a part of the biological tissue image and has a predefined shape and area; A step of searching for a second partial region among the partial regions of the biological tissue image, wherein the pixel-wise diagnosis result corresponding to the corresponding region contains the largest number of secondary Gleason patterns of the pathological diagnosis case; A step of generating a modified pixel-wise diagnosis result by removing the pixel-wise diagnosis result corresponding to the first partial region from the pixel-wise diagnosis result of the biological tissue image;And, among the partial regions of the biological tissue image, a step of searching for a third partial region in which the second Gleason pattern of the pathology diagnosis case is most included in the modified pixel-unit diagnosis result corresponding to the corresponding region, and the step of selecting a representative lesion image representing the pathology diagnosis case may include a step of selecting a first representative lesion image in which the first Gleason pattern of the pathology diagnosis case is most included in the pixel-unit diagnosis corresponding to the corresponding region from among the first partial regions of each of the plurality of biological tissue images and the second partial regions of each of the plurality of biological tissue images; and a step of selecting a second representative lesion image in which the second Gleason pattern of the pathology diagnosis case is most included in the pixel-unit diagnosis corresponding to the corresponding region from among the first partial regions of each of the plurality of biological tissue images, the second partial regions of each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and the third partial regions of the biological tissue image including the first representative lesion image.

[0023] According to another aspect of the present invention, a computer program stored in a recording medium is provided for executing the above-described method in a computing system.

[0024] According to another aspect of the present invention, a computer-readable recording medium having recorded thereon a program for executing the above-described method in a computing system is provided.

[0025] According to another aspect of the present invention, a computing system is provided, comprising: a processor; and a memory storing a computer program, wherein the computer program, when executed by the processor, causes the computing system to perform the method described in any one of claims 1 to 9.

[0026] According to another aspect of the present invention, there is provided a computing system for performing a method of generating a pathology diagnosis report for a pathology diagnosis case comprising a plurality of biological tissue images, which are digital scan images of each of a plurality of tissue specimens collected from a prostate of a given patient, the computing system comprising: an image acquisition module for acquiring the plurality of biological tissue images included in the pathology diagnosis case and pixel-wise diagnosis results of each of the plurality of biological tissue images, wherein the pixel-wise diagnosis results of the biological tissue images include a Gleason pattern for each pixel constituting the biological tissue image; an image diagnosis result acquisition module for acquiring a diagnosis result of the biological tissue image, for each of the plurality of biological tissue images, wherein the diagnosis result of the biological tissue image includes a diagnosis name of a tissue specimen corresponding to the biological tissue image, and further includes a first Gleason pattern and a second Gleason pattern of the biological tissue image when the diagnosis name of the tissue specimen is benign; a representative lesion area extraction module for extracting a representative lesion area of ​​the biological tissue image, which is a representative partial area of ​​the biological tissue image, when the diagnosis name of the tissue specimen is not benign, for each of the plurality of biological tissue images; A computing system is provided, comprising: a diagnostic part generation module for generating a diagnostic part for the biological tissue image of a pathology diagnosis report for each of the plurality of biological tissue images; and a report generation module for generating a pathology diagnosis report, which is an electronic document including a diagnostic part for each of the plurality of biological tissue images, wherein the diagnostic part for the biological tissue image further includes, when the diagnosis of the tissue sample is positive, a diagnostic name of a tissue sample corresponding to the biological tissue image, and, when the diagnosis of the tissue sample is not positive, an image of a representative lesion area of ​​the biological tissue image in which a first Gleason pattern and a second Gleason pattern and a pixel-by-pixel diagnostic result are overlapped.

[0027] In one embodiment, the computing system further includes a site information acquisition module that acquires information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions in which the prostate is divided, and the diagnostic part for the biological tissue image may further include a prostate diagram in which regions corresponding to each of the plurality of regions are divided and regions corresponding to the sites from which the tissue samples corresponding to the biological tissue images were collected are visually highlighted.

[0028] In one embodiment, the diagnosis result of the biological tissue image may further include the length of the tissue specimen corresponding to the biological tissue image, and if the diagnosis of the tissue specimen is not benign, may further include the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, and the ratio of each pattern on the Gleason grading system in the lesion included in the tissue specimen corresponding to the biological tissue image, and the diagnosis part for the biological tissue image may further include the length of the tissue specimen corresponding to the biological tissue image, and if the diagnosis of the tissue specimen is not benign, may further include the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, the ratio of each pattern on the Gleason grading system in the lesion included in the tissue specimen corresponding to the biological tissue image, and at least a portion of the biological tissue image in which an outline of an area corresponding to a representative lesion image of the biological tissue image is expressed.

[0029] In one embodiment, the representative lesion region extraction module may include a first search module that searches for a first partial region among the partial regions of the biological tissue image, wherein the first Gleason pattern is most frequently included in the pixel-wise diagnosis result corresponding to the corresponding region, wherein the partial region of the biological tissue image is a part of the biological tissue image and has a predefined shape and area; a removal module that removes the pixel-wise diagnosis result corresponding to the first partial region from the pixel-wise diagnosis result of the biological tissue image to generate a modified pixel-wise diagnosis result; a second search module that searches for a second partial region among the partial regions of the biological tissue image, wherein the second Gleason pattern is most frequently included in the modified pixel-wise diagnosis result corresponding to the corresponding region; and a determination module that determines the first partial region of the biological tissue image and the second partial region of the biological tissue image as the representative lesion region of the biological tissue image.

[0030] In one embodiment, the computing system may further include a site information acquisition module that acquires information about a site from which a tissue specimen corresponding to each of the plurality of biological tissue images is collected, wherein the site is one of the plurality of regions in which the prostate is divided; a region diagnosis result acquisition module that acquires, for each of the plurality of regions, a diagnosis result for the region determined based on a diagnosis result of a biological tissue image corresponding to a tissue specimen collected from the region among the plurality of biological tissue images; and a summary part generation module that generates a summary part for the pathology diagnosis case, wherein the pathology diagnosis report further includes the summary part, and the summary part for the pathology diagnosis case may include a summary table including a diagnosis result for each of the plurality of regions; and a prostate diagram of the pathology diagnosis case in which regions corresponding to each of the plurality of regions are divided, and each region is given a predetermined visual effect determined by the diagnosis result for the corresponding region.

[0031] In one embodiment, the computing system comprises: a site information acquisition module that acquires information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions of the prostate; a region diagnosis result generation module that acquires, for each of the plurality of regions, a diagnosis result for the region determined based on a diagnosis result of a biological tissue image corresponding to a tissue sample collected from the region among the plurality of biological tissue images; And further comprising a summary part generation module for generating a summary part for the pathology diagnosis case, wherein the pathology diagnosis report further comprises the summary part, and the summary part for the pathology diagnosis case includes a summary table composed of summary information for each of the plurality of zones, and the summary information for the zone includes a diagnosis result for the zone and a bar diagram corresponding to each tissue specimen collected from the zone, and the bar diagram is composed of parts corresponding to each non-lesion area and lesion area distributed in the corresponding tissue specimen, and each part included in the bar diagram has a length proportional to the length of the area corresponding to the corresponding part, and a predetermined visual effect corresponding to the Gleason pattern of the area corresponding to the corresponding part can be given.

[0032] In one embodiment, the computing system further includes a case representative lesion image generation module that generates a representative lesion image of the pathology diagnosis case, the pathology diagnosis report further includes the representative lesion image, and the case representative lesion image generation module includes: a case lesion pattern acquisition module that acquires a first Gleason pattern and a second Gleason pattern of the pathology diagnosis case; an area search module that searches for a first partial region, a second partial region, and a third partial region of the biological tissue image, respectively, for each of the plurality of biological tissue images; And a selection module for selecting a representative lesion image representing the pathological diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images, wherein the region search module includes: a first partial region search module for searching, among the partial regions of the biological tissue image, the first partial region in which the first Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-wise diagnosis result corresponding to the corresponding region; wherein the partial region of the biological tissue image is a part of the biological tissue image and is a region having a predefined shape and area; a second partial region search module for searching, among the partial regions of the biological tissue image, the second partial region in which the second Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-wise diagnosis result corresponding to the corresponding region; a modification module for generating a modified pixel-wise diagnosis result by removing the pixel-wise diagnosis result corresponding to the first partial region from the pixel-wise diagnosis result of the biological tissue image;And a third partial region search module that searches for a third partial region among the partial regions of the biological tissue image, in which the second Gleason pattern of the pathological diagnosis case is most included in the modified pixel unit diagnosis result corresponding to the corresponding region, and the selection module may include a first representative lesion image selection module that selects a first representative lesion image that includes the first Gleason pattern of the pathological diagnosis case most in the pixel unit diagnosis corresponding to the corresponding region, from among the first partial region of each of the plurality of biological tissue images and the second partial region of each of the plurality of biological tissue images; and a second representative lesion image selection module that selects a second representative lesion image that includes the second Gleason pattern of the pathological diagnosis case most in the pixel unit diagnosis corresponding to the corresponding region, from among the first partial region of each of the plurality of biological tissue images, the second partial region of each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and the third partial region of the biological tissue image including the first representative lesion image.

[0033]

[0034] According to the technical idea of ​​the present invention, a method for generating a pathology diagnosis report in a form that can effectively convey the overall and specific diagnosis results of a pathology diagnosis case to a patient or other diagnostician, and a computing system for performing the same are provided.

[0035] In addition, a method for effectively extracting a lesion area representing a biological tissue image and a computing system for performing the same can be provided.

[0036] In addition, a method for extracting a lesion region representing a pathological diagnosis case composed of a plurality of biological tissue images and a computing system for performing the method can be provided.

[0037] In particular, a method and a computing system for performing the method can be provided for detecting some areas in which a specific grade in a predetermined grading system for grading the severity of a disease such as cancer is most clearly expressed among biological tissue images, or for detecting some areas in which the histological classification of a lesion is most clearly expressed.

[0038]

[0039] In order to more fully understand the drawings cited in the detailed description of the present invention, a brief description of each drawing is provided.

[0040] FIG. 1 is a diagram for explaining a schematic system configuration for implementing a method for generating a pathology diagnosis report for a pathology diagnosis case according to an embodiment of the present invention.

[0041] FIG. 2 is a flowchart illustrating a method for generating a pathology diagnosis report according to one embodiment of the present invention.

[0042] FIG. 3 is a flowchart illustrating in more detail the process of generating a diagnostic part for a biological tissue image (i.e., step S120 of FIG. 2) by a computing system according to one embodiment of the present invention.

[0043] FIG. 4 is a flowchart illustrating in more detail the process of extracting a representative lesion from a biological tissue image (i.e., step S123 of FIG. 3) by a computing system according to one embodiment of the present invention.

[0044] Figure 5 is a drawing illustrating an example of a biological tissue image and a partial region of the biological tissue image.

[0045] Figure 6 is a diagram illustrating an initial part of the process of searching a partial region using a sliding window method.

[0046] FIG. 7(a) illustrates an example of a first partial region searched by a computing system according to an embodiment of the present invention, FIG. 7(b) illustrates an example of a pixel-by-pixel diagnosis result modified by removing a pixel-by-pixel diagnosis result corresponding to the first partial region from a pixel-by-pixel diagnosis result of a biological tissue image, and FIG. 7(c) illustrates an example of a second partial region searched by a computing system according to an embodiment of the present invention.

[0047] FIGS. 8A to 8D are drawings for explaining an example of a diagnostic part for a biological tissue image generated by a computing system according to one embodiment of the present invention.

[0048] FIG. 9 is a flowchart illustrating in more detail the process of generating a summary part for a pathology diagnosis case (i.e., step S130 of FIG. 2) by a computing system according to one embodiment of the present invention.

[0049] FIG. 10 is a diagram illustrating an example of a summary part for a pathology diagnosis case generated by a computing system according to one embodiment of the present invention.

[0050] FIGS. 11A and 11B are diagrams illustrating another example of a summary part for a pathology diagnosis case generated by a computing system according to one embodiment of the present invention.

[0051] FIG. 12 is a diagram illustrating an example of a method by which a computing system according to one embodiment of the present invention generates a bar diagram corresponding to a biological tissue image.

[0052] FIG. 13 is a flowchart illustrating in more detail the process of generating a representative lesion image (i.e., step S123 of FIG. 9) by a computing system according to one embodiment of the present invention.

[0053] Figure 14 is a diagram showing slide images corresponding to each of three biological tissues A, B, and C, and the number of pixels for each Gleason pattern of each slide image.

[0054] FIG. 15 is a drawing illustrating in more detail a process (i.e., step S230 of FIG. 10) in which the computing system searches for a first partial region, a second partial region, and a third partial region of a specific biological tissue image in one embodiment of the present invention.

[0055] FIG. 16(a) illustrates an example of a first partial region searched by a computing system according to an embodiment of the present invention, FIG. 16(b) illustrates an example of a second partial region searched by a computing system according to an embodiment of the present invention, FIG. 16(c) illustrates an example of a result of removing a pixel-by-pixel diagnosis result corresponding to the first partial region, and FIG. 16(d) illustrates an example of a third partial region searched by a computing system according to an embodiment of the present invention.

[0056] Figure 17 is a drawing illustrating step S240 of Figure 13 in more detail.

[0057] FIG. 18 is a diagram illustrating examples of the first partial region, the second partial region, and the third partial region searched in each of the biological tissue images, such as the example illustrated in FIG. 14.

[0058] Figure 19 is a drawing that illustrates the process of Figure 17 for easier understanding.

[0059] Figures 20 to 24 are block diagrams illustrating the logical configuration of a computing system according to one embodiment of the present invention.

[0060] FIG. 25 is a block diagram illustrating the physical configuration of a computing system according to one embodiment of the present invention.

[0061]

[0062]

[0063] The present invention is susceptible to various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention. In describing the present invention, detailed descriptions of related known technologies will be omitted if they are deemed to obscure the gist of the present invention.

[0064] Terms such as "first," "second," etc. may be used to describe various components, but these components should not be limited by these terms. Terms such as "first," "second," etc. do not denote a particular order and are used solely to distinguish one component from another.

[0065] The terminology used in this application is solely for the purpose of describing specific embodiments and is not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise.

[0066] In this specification, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0067] Additionally, in the present specification, when a component "transmits" data to another component, it means that the component may transmit the data directly to the other component, or may transmit the data to the other component via at least one other component. Conversely, when a component "directly transmits" data to another component, it means that the data is transmitted from the component to the other component without going through the other component.

[0068] Hereinafter, the present invention will be described in detail, focusing on embodiments thereof, with reference to the attached drawings. The same reference numerals in each drawing represent the same components.

[0069] FIG. 1 is a diagram for explaining a schematic system configuration for implementing a method for generating a pathology diagnosis report for a pathology diagnosis case according to an embodiment of the present invention (hereinafter referred to as “pathology diagnosis report generation method”).

[0070] Referring to FIG. 1, a method for generating a pathology diagnosis report according to the technical concept of the present invention can be performed by a computing system (100). The computing system (100) can generate a pathology diagnosis report for a pathology diagnosis case composed of a plurality of biological tissue images, which are digital scan images of each of a plurality of tissue specimens collected from a patient's prostate.

[0071] A biological tissue image may be an image generated from a slide of a pathology specimen tissue stained using a predetermined staining method. The pathology specimen tissue may be a biopsy taken from the prostate or a surgically resected biological tissue. In one embodiment, the pathology specimen tissue may be a biological tissue collected through a core needle biopsy. Meanwhile, the biological tissue image may be a digital slide image of a stained pathology specimen or a portion of a digital slide image. The pathology specimen slide may be a portion of a sliced ​​pathology specimen. The digital slide image of a pathology specimen may be generated by slicing a pathology specimen to produce a glass slide, staining the glass slide with a predetermined staining agent, and digitizing the glass slide.

[0072] A pathology diagnosis case may be composed of multiple slide images of biological tissues satisfying certain conditions. Typically, a pathology diagnosis case may be an image generated from each slide of multiple biological tissues collected from the prostate of a single patient (e.g., prostate tissue cores collected through biopsy). However, the technical concept of the present invention is not necessarily limited thereto. For example, a pathology diagnosis case may be composed of slide images of biological tissues generated from multiple biological tissues collected from a group of patients classified according to certain conditions (e.g., a group composed of multiple patients exhibiting the same symptoms).

[0073] Meanwhile, the pathology diagnosis report generated by the computing system (100) may be an electronic document, a form of digital information that can be stored or transmitted electronically. The pathology diagnosis report may be in various electronic document formats. For example, the pathology diagnosis report may be an electronic document in a non-public format that can be loaded by a dedicated reader application, such as PDF, MS Word, or HTML, or an image file.

[0074] The method for generating a pathology diagnosis report according to the technical concept of the present invention primarily includes diagnostic results for tissue specimens collected from the prostate, and the prostate will be described below as an example, but the technical concept of the present invention can of course be applied to tissue specimens collected from various biological organs other than the prostate. In this case, a biological organ is a collection of biological tissues that perform a specific function or action, and examples thereof include the prostate, kidney, lung, stomach, liver, heart, bladder, and breast.

[0075] In one embodiment, a computing system (100) may be installed on a predetermined server (10) to implement the technical idea of ​​the present invention. The server (10) refers to a data processing device having a computing capability for implementing the technical idea of ​​the present invention. Generally, a person skilled in the art will be able to easily infer that not only a data processing device that can be accessed by a client through a network, but also any device capable of performing a specific service, such as a personal computer or a mobile terminal, can be defined as a computing device.

[0076] According to one embodiment, the computing system (100) may need to directly determine at least some of the diagnostic results for a biological tissue image or a pathological diagnosis case. For example, according to one embodiment, the computing system (100) may need to directly determine the diagnosis name of a lesion included in a biological tissue image, a pixel-wise diagnostic result of the biological tissue image (e.g., a Gleason pattern for each pixel, etc.), a severity grade of the biological tissue image (e.g., a Gleason score, etc.), or other histological characteristics of the biological tissue image. In this case, the computing system (100) may use a pre-trained deep learning model (200). The deep learning model (200) may be an artificial neural network that receives a biological tissue image or a patch obtained by dividing a biological tissue image into a certain size as input, and outputs a pixel-wise diagnostic result of the input image or a result value for determining a severity grade or histological classification of the input image itself (e.g., a probability corresponding to each Gleason pattern, a probability corresponding to each severity grade, etc.).

[0077] The above deep learning model (200) is a neural network artificially constructed based on the operating principles of human neurons, including a multilayer perceptron model, and may refer to a set of information expressing a series of design specifications defining an artificial neural network. The above deep learning model (200) may include, but is not limited to, a convolutional neural network (CNN) widely known in the fields of artificial intelligence, machine learning, or deep learning.

[0078] The above deep learning model (200) may be a single model, but depending on the embodiment, it may be a set of multiple models, in which case each model may be an independent model that performs different tasks (e.g., a task of determining pixel-level diagnostic results, a task of determining a diagnosis name, a task of determining a Gleason score, etc.).

[0079] The server (10) including the computing system (100) may be a system that stores or applies results generated by the computing system (100) (i.e., generated pathology diagnosis reports, etc.). For example, the server (10) may be, but is not limited to, a diagnostic assistance system for providing information necessary for a doctor to diagnose a disease. The deep learning model (200) and the computing system (100) may be provided in one physical device, i.e., the server (10), but may also be provided in different physical devices depending on the embodiment, and various modifications may be possible as needed, as will be readily apparent to an average expert in the technical field of the present invention.

[0080] The user terminal (20) may be a data processing device with computing capabilities and may be equipped with a display device for displaying visual information, such as a pathology diagnosis report or a predetermined GUI generated by the computing system (100). The user terminal (20) may include, for example, a personal computer such as a desktop or laptop, as well as a mobile device such as a cell phone or tablet PC.

[0081] In one embodiment, the server (10) and / or the computing system (100) may communicate with a user terminal (20). For example, the user terminal (20) may transmit a biological tissue image, or a diagnostic result for a biological tissue image determined by a diagnostician, to the computing system (100), and may also receive a result generated from the computing system (100).

[0082] Meanwhile, in FIG. 1, an example is shown in which the computing system (100) is implemented in the form of a subsystem installed in a server (10), but it is obvious that, depending on the embodiment, the computing system (100) may be implemented as an independent single system. In this case, the computing system (100) may be a computing system that is a data processing device having a computing capability for implementing the technical idea of ​​the present invention, and may generally include not only a server that is a data processing device that can be accessed by a client through a network, but also a computing device such as a personal computer or a mobile terminal.

[0083] FIG. 2 is a flowchart illustrating a method for generating a pathology diagnosis report according to one embodiment of the present invention.

[0084] The computing system (100) can acquire multiple biological tissue images constituting a pathology diagnosis case (S100). The multiple biological tissue images may be digital scan images of each of multiple tissue samples collected from the prostate of a given patient.

[0085] The above-described biological tissue image may be a full slide image or a portion of a full slide image created by digitally scanning a slide of a tissue sample collected from the prostate through a biopsy or surgery. In one embodiment, the computing system (100) may receive the plurality of biological tissue images from the user terminal (20), or may acquire the plurality of biological tissue images from a database or storage device provided by the server (10) or the computing system (100). The sizes of the biological tissue images constituting a pathology diagnosis case may be the same.

[0086] The computing system (100) can generate a diagnostic part for each of the plurality of biological tissue images constituting the pathological diagnosis case (S110, S120).

[0087] According to an embodiment, the computing system (100) may further generate a summary part for the pathology diagnosis case (S130).

[0088] Thereafter, the computing system (100) can generate a pathology diagnosis report for the pathology diagnosis case, which includes a diagnostic part for each of the plurality of biological tissue images (S140). If the computing system (100) further performs step S130, the pathology diagnosis report may further include a summary part for the pathology diagnosis case.

[0089] FIG. 3 is a flowchart illustrating in more detail the process of generating a diagnostic part for a biological tissue image (i.e., step S120 of FIG. 2) by a computing system according to one embodiment of the present invention.

[0090] Referring to FIG. 3, the computing system (100) can obtain a pixel-by-pixel diagnosis result of the biological tissue image (S121). At this time, the pixel-by-pixel diagnosis result of the biological tissue image can include a Gleason pattern for each pixel constituting the biological tissue image.

[0091] The Gleason pattern is a representative grading system that indicates the severity of prostate cancer tissue, and is classified into benign or patterns from 1 to 5 depending on the histological differentiation. A classification of 1 indicates differentiation close to normal and low malignancy, whereas a score of 5 indicates the most malignant cancer. The Gleason pattern used in the present invention can be divided into grades 1 to 5 indicating prostate cancer and benign for each pixel, but in some cases, it can also be divided into grades 3 to 5 and benign.

[0092] The pixel-wise diagnosis result of the biological tissue image may be in the form of a two-dimensional array of the same size as the biological tissue image. For example, if the biological tissue image has a size of W pixels × H pixels, the pixel-wise diagnosis result of the biological tissue image may be a two-dimensional array of W × H, and each element of the array may be assigned a pixel-wise diagnosis result of the pixel corresponding to that element.

[0093] Each element of the array may be assigned a value representing the Gleason pattern if the pixel corresponding to that element corresponds to Gleason pattern 1 to 5, and a value representing positivity (e.g., 0) otherwise.

[0094] However, depending on the embodiment, each element of the array may be implemented such that if the pixel corresponding to the element does not belong to the tissue region, a value indicating that it is not a tissue region is assigned, and if it belongs to the tissue region, a pixel-by-pixel diagnostic result of the pixel corresponding to the element is assigned. For example, each element of the array may be assigned -1 if the pixel corresponding to the element belongs to the non-tissue region, 0 if it is positive, and otherwise a value corresponding to the Gleason pattern.

[0095] For convenience of explanation, below, an embodiment is described in which the same positive value (e.g., 0) is assigned to both cases in which a pixel belongs to a non-organized area and cases in which it is positive.

[0096] In one embodiment, the pixel-by-pixel diagnostic results of the biological tissue image may be input into the computing system together with the biological tissue image as a result of manual annotation by a pathologist.

[0097] According to an embodiment, the computing system (100) may analyze the biological tissue image to directly obtain a pixel-wise diagnosis result of the biological tissue image. In this case, the computing system (100) may obtain a pixel-wise diagnosis result of the biological tissue image using a pre-trained deep learning model (200). More specifically, the computing system (100) may input each of the biological tissue images or patches divided into a grid shape into an input layer of the deep learning model (200) and determine a Gleason pattern for each pixel of the biological tissue image based on an output value output from an output layer of the deep learning model (200). At this time, the deep learning model (200) may be an artificial neural network that has been trained in advance to determine a pixel-wise Gleason pattern of an input image, and may be an artificial neural network that has been trained in advance to receive an image through an input layer and output a probability that each pixel included in the input image corresponds to each Gleason pattern.

[0098] The computing system (100) can obtain a diagnosis of a tissue sample corresponding to the biological tissue image and a first Gleason pattern and a second Gleason pattern of the biological tissue image (S122).

[0099] The first Gleason pattern and the second Gleason pattern of the above biological tissue image are the same type of Gleason patterns as the Gleason pattern for each pixel included in the pixel-by-pixel diagnosis result of the above biological tissue image.

[0100] In one embodiment, the computing system (100) can obtain a Gleason score of the biological tissue image, and the Gleason score is composed of a primary Gleason pattern and a secondary Gleason pattern. The primary Gleason pattern and the secondary Gleason pattern may be classified as grades 1 to 5 and benign, or grades 3 to 5 and benign, depending on the embodiment. A Gleason score in which the primary Gleason pattern is a and the secondary Gleason pattern is b is typically expressed as 'a+b'. For example, if the Gleason score is expressed as 3+4, this indicates that the primary Gleason pattern is 3 and the secondary Gleason pattern is 4. In some cases, a and b may be the same value.

[0101] In one embodiment, the computing system (100) may obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image that are stored in advance in a storage device provided by the computing system (100) or the server (10), or may obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image from the user terminal (20).

[0102] Alternatively, according to an embodiment, the computing system (100) may analyze the biological tissue image or the pixel-by-pixel diagnostic results of the biological tissue image to obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image.

[0103] In one embodiment, the computing system (100) can calculate the proportion of each Gleason pattern in a biological tissue image and determine the first Gleason pattern and the second Gleason pattern of the biological tissue image based on the calculated proportion. More specifically, the computing system (100) can count the number of pixels for each Gleason pattern from the pixel-by-pixel diagnosis results of each biological tissue image constituting a pathology diagnosis case, and determine the top two Gleason patterns with the largest proportion as the first Gleason pattern and the second Gleason pattern.

[0104] In another embodiment, the computing system (100) may utilize a pre-trained deep learning model (200). The deep learning model (200) may be an artificial neural network pre-trained to receive an input image or a pixel-by-pixel diagnosis result of an image and determine the first Gleason pattern and the second Gleason pattern of the image, and may be an artificial neural network pre-trained to receive an image or a pixel-by-pixel diagnosis result of an image through an input layer and output a probability that the image corresponds to a predetermined Gleason pattern.

[0105] Meanwhile, the diagnosis of the tissue specimen corresponding to the biological tissue image may be any one of multiple predefined diagnosis names used for prostate cancer diagnosis. For example, the diagnosis names may be benign, indeterminate, malignant, other, etc. In the case of malignant, a detailed diagnosis name may be defined separately, and the detailed diagnosis names of prostate cancer may be acinar adenocarcinoma, ductal adenocarcinoma, small cell neuroendocrine carcinoma, isolated intraductal carcinoma, other malignancy, acinar adenocarcinoma with other type(s), ductal adenocarcinomawith other type(s), small cell neuroendocrine carcinoma with other type(s), etc.

[0106] The computing system (100) can obtain a diagnosis name that is pre-stored in a storage device provided by the computing system (100) or the server (10), receive a diagnosis name from the user terminal (20), or determine a diagnosis name using a pre-learned deep learning model (200).

[0107] The computing system (100) can extract a representative lesion area of ​​the biological tissue image (S123). The representative lesion area is a representative portion of the biological tissue image, and a specific method for extracting it will be described later.

[0108] According to an embodiment, the computing system (100) may further obtain additional diagnostic results, and the additional diagnostic results may include the length of a tissue sample corresponding to a biological tissue image, the length of a lesion included in the tissue sample, the ratio of the lesion in the tissue sample, and the ratio of each Gleason pattern in the lesion included in the tissue sample corresponding to the biological tissue image (S124). In addition, depending on the embodiment, the additional diagnostic results may further include other pathological features (e.g., presence of intraductal carcinoma (IDC), presence of perineural invasion (PNI), presence of seminal vesicle invasion (SVI), presence of lymphovascular invasion (LVI), presence of extraprostatic extension (EPE), presence of cribriform glands, presence of inflammation, presence of high-grade PIN, presence of atypical intraductal proliferation (AIP), presence of atypical small acinar proliferation (ASAP), presence of small focus of atypical glands (ATYP), presence of hyperplasia, presence of post-treatment effect, etc.), and at least some of the diagnostician's notes.

[0109] The computing system (100) may receive all or part of the additional diagnosis results from the user terminal (20) or may be stored in advance in the storage device. Alternatively, the computing system (100) may obtain all or part of the additional diagnosis results using a predetermined algorithm or a pre-trained deep learning model (200). For example, the computing system (100) may determine the length of a tissue sample, the length of a lesion included in a tissue sample, the proportion of the lesion in the tissue sample, and the proportion of each Gleason pattern in a biological tissue image using a predetermined measurement algorithm, and may determine the presence of IDC, the presence of PNI, the presence of SVI, the presence of LVI, the presence of EPE, the presence of cribriform glands, the presence of inflammation, the presence of high-grade PIN, the presence of AIP, the presence of ASAP, the presence of ATYP, the presence of hyperplasia, the presence of post-treatment effect, etc. using the deep learning model (200), and may receive a diagnostician's note from the user terminal (20).

[0110] Meanwhile, according to an embodiment, the computing system (100) may further acquire information about a site from which a tissue sample corresponding to a biological tissue image was collected (S125). Here, the site is one of a plurality of predefined zones in which the prostate is divided. For example, the prostate may be divided into an apex, a mid, and a base in the vertical direction, and a left lateral, a left medial, a right medial, and a right lateral in the horizontal direction, thereby being divided into a total of 3×4=12 zones, and among the 12 zones, the zone from which the tissue sample was collected is the site of the tissue sample. Meanwhile, each zone may be assigned a unique identification number or identification symbol.

[0111] The computing system (100) can input information about a site from which a tissue sample corresponding to the biological tissue image was collected into the user terminal (20) or obtain the information from a storage device in which information about the site is stored in advance.

[0112] FIG. 4 is a flowchart illustrating in more detail the process of extracting a representative lesion from a biological tissue image (i.e., step S123 of FIG. 3) by a computing system according to one embodiment of the present invention.

[0113] Referring to FIG. 4, the computing system (100) can search for a first partial region among the partial regions of the biological tissue image, in which the first Gleason pattern is most frequently included in the pixel-unit diagnostic results corresponding to the corresponding region (S1231). At this time, the partial region of the biological tissue image may be a region having a predefined shape and area as a part of the biological tissue image. That is, the shape and area of ​​the partial region may be preset within the computing system (100).

[0114] Fig. 5 is a diagram illustrating an example of a biological tissue image and a partial region of the biological tissue image. The partial region (2) of the biological tissue image (1) may be any part of the biological tissue image (1). In the example of Fig. 5, the partial region (2) is a rectangular region having a predetermined size of w pixels × h pixels (w is a natural number such that w < W, and h is a natural number such that h < H).

[0115] Referring back to FIG. 4, the computing system (100) can search the first partial region using a sliding window method in which the shape and area of ​​the window are set to be the same as the partial region of the biological tissue image. For example, if the size of the partial region is set as in FIG. 4, the window can also be a rectangular shape having a size of w pixels × h pixels. In this case, the computing system (100) can calculate the number of pixels in the corresponding window having the first Gleason pattern by moving the rectangular window having the size of w × h by a predetermined sliding step (one or more pixels), and can determine the window that contains the largest number of the first Gleason patterns as the first partial region.

[0116] Thereafter, the computing system (100) can generate a modified pixel-unit diagnosis result by removing the pixel-unit diagnosis result corresponding to the first partial region from the pixel-unit diagnosis result of the biological tissue image (S1232).

[0117] Thereafter, the computing system (100) can search for a second partial region among the partial regions of the biological tissue image, in which the second Gleason pattern is most abundantly included in the modified pixel-unit diagnostic results corresponding to the corresponding region (S1233). It goes without saying that the sliding window method can also be used in the process in which the computing system (100) searches for the second partial region.

[0118] FIG. 6 is a diagram illustrating an initial part of a process for searching a partial region using a sliding window method. FIG. 6 illustrates a pixel-by-pixel diagnosis result and a window (bold box) for each pixel of a biological tissue image. In the example of FIG. 6, the computing system (100) scans the pixel-by-pixel diagnosis result for each pixel, which is classified as Gleason patterns 3 to 5 and positive (indicated as 0), in a 6×4 window. At this time, the computing system can calculate the number of primary Gleason patterns within the window by moving the window by one pixel. FIG. 6 illustrates only an initial part of this process. In FIGS. 6 (a), (b), and (c), a 6×4 window that has been moved by one pixel is indicated by a bold box. If the scan of one line is completed, the computing system (100) will calculate the number of primary Gleason patterns within the window by moving by one pixel again from the beginning of the next line.

[0119] Fig. 7(a) illustrates an example of a first partial region searched by the computing system (100). If the first Gleason pattern is 4, and the computing system searches the first partial region as described with reference to Fig. 6, the computing system (100) will determine that the region on the entire slide corresponding to the region (3-1) of Fig. 7(a) containing the largest number of the first Gleason pattern (i.e., pattern 4) is the first partial region (step S1231 of Fig. 3).

[0120] Thereafter, the computing system (100) can generate a modified pixel-by-pixel diagnosis result as shown in FIG. 7(b) by removing the pixel-by-pixel diagnosis result corresponding to the first partial region from the pixel-by-pixel diagnosis result of the biological tissue image (S1232 of FIG. 3). FIG. 7 illustrates an example of assigning 0, indicating positive, to the corresponding region in order to remove the pixel-by-pixel diagnosis result corresponding to the first partial region. However, depending on the embodiment, a value indicating non-tissue or a third value indicating that the corresponding region is a deleted region may be assigned to the corresponding region.

[0121] Thereafter, the computing system (100) can sequentially scan the modified pixel-by-pixel diagnostic results as in Fig. 7(b) in a 6×4 sized window to search for the second partial region containing the largest number of secondary Gleason patterns. If the secondary Gleason pattern is 3, the computing system (100) will determine that the region on the entire slide corresponding to the region (3-2) of Fig. 7(c) is the second partial region (step S1233 of Fig. 3).

[0122] Meanwhile, referring again to FIG. 3, the computing system (100) can generate a diagnostic part for a biological tissue image (S126). The diagnostic part for the generated biological tissue image is included in the pathology diagnosis report.

[0123] The diagnostic part for the above biological tissue image may include a diagnosis name of a tissue specimen corresponding to the biological tissue image, a first Gleason pattern and a second Gleason pattern of the biological tissue image, and an image of a representative lesion area of ​​the biological tissue image overlapping with a pixel-level diagnostic result.

[0124] According to an embodiment, the diagnostic part for the biological tissue image may further include a prostate diagram in which areas corresponding to each of the plurality of regions are distinguished and areas corresponding to sites from which tissue samples corresponding to the biological tissue image are collected are visually highlighted.

[0125] According to an embodiment, the diagnostic part for the biological tissue image may further include at least a portion of the biological tissue image in which the length of the tissue specimen corresponding to the biological tissue image, the length of the lesion tissue included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, the ratio of each Gleason pattern in the biological tissue image, and the outline of the area corresponding to the representative lesion image of the biological tissue image are expressed.

[0126] FIG. 8A is a diagram illustrating an example of a diagnostic part for a biological tissue image generated by a computing system (100) according to one embodiment of the present invention. That is, FIG. 8A is an example of a diagnostic part for a biological tissue image corresponding to a tissue specimen collected through a prostate biopsy. The diagnostic part (40) for the biological tissue image illustrated in FIG. 8A may include an overview section (41), an image section (42), and a text section (43).

[0127] FIG. 8b is an enlarged view of an overview section (41) of a diagnostic part (40) of the biological tissue image of FIG. 8a.

[0128] Referring to FIG. 8b, the overview section (41) may include information about the site from which a tissue sample corresponding to the biological tissue image was collected (specifically, the site identifier and location (41-1) and the site diagnosis (41-2)). In the example of FIG. 8b, the identifier of the site from which the tissue sample was collected is F, and the site location is the left medial apex. Additionally, in the example of FIG. 8b, the diagnosis of site F is Acinar Adenocarcinoma.

[0129] Meanwhile, the overview section (41) may include a diagnosis of a tissue specimen corresponding to the biological tissue image and a Gleason score (see 41-3) of the biological tissue image. In the example of FIG. 8b, the diagnosis of the tissue specimen is MALIGNANT, specifically, Acinar Adenocarcinoma, and the Gleason score is 4+5=9. According to an embodiment, the diagnosis part (41) for the biological tissue image may further include a ratio of each Gleason pattern in the tissue specimen (see 41-3). In addition, the overview section (41) may further include information (41-4) indicating which site (site B in the example of FIG. 8b) the tissue specimen corresponding to the biological tissue image was collected from.

[0130] Meanwhile, the above-described overview section (41) may further include a prostate diagram (41-5) in which areas corresponding to each of the plurality of zones are distinguished, and areas corresponding to sites where tissue samples corresponding to the biological tissue image are collected are visually highlighted. In the example of Fig. 8b, a prostate diagram (41-5) is illustrated that is divided into areas corresponding to a total of 12 zones.

[0131] Meanwhile, visually highlighting a specific area may mean that it has a visual effect that differs from the rest of the image. These visual effects may include changes in color, brightness, and / or saturation, the application of visual patterns, shadow effects, three-dimensional effects, or the application of special symbols.

[0132] In the example of Fig. 8b, the area (41-6) corresponding to site F, which is the site from which the tissue specimen corresponding to the biological tissue image was collected, is given a color corresponding to the diagnosis result (Acinar Ademocarcinoma) of the site in a darker color than the remaining areas, so that the reviewer of the report can visually recognize that site F is the site from which the tissue specimen was collected.

[0133] FIG. 8c is a drawing showing an enlarged image section (42) of the diagnostic part (40) of the biological tissue image of FIG. 8a.

[0134] Referring to FIG. 8c, the image section (42) may include images (42-1, 42-2) of representative lesion areas of the biological tissue image. A method for extracting representative lesion areas from a biological tissue image has been described above.

[0135] As illustrated in FIG. 8c, the pixel-level diagnostic results may be overlapped with the images (42-1, 42-2) of the representative lesion area of ​​the biological tissue image. More specifically, the pixel-level diagnostic results may be displayed in a predetermined color according to the Gleason pattern and overlapped with the image of the representative lesion area. For example, if the pixel-level diagnostic result is Gleason pattern 3, it may be colored yellow, if it is Gleason pattern 4, it may be colored orange, and if it is Gleason pattern 5, it may be colored red, and a certain level of transparency may be set so as to overlap with the image of the representative lesion area.

[0136] According to an embodiment, the diagnostic part (42) for the biological tissue image may further include the biological tissue image (42-3). The biological tissue image (42-3) may display an outline of a representative lesion area (42-4, 42-5), and pixel-level diagnostic results may be overlapped.

[0137] FIG. 8d is a drawing showing an enlarged view of the text section (43) of the diagnostic part (40) of the biological tissue image of FIG. 8a.

[0138] Referring to FIG. 8d, the text section (43) may include the length of the tissue specimen corresponding to the biological tissue image, the length of the lesion tissue included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image (43-1), and in some cases, may further include histological characteristics of the pathological specimen excluding the diagnosis name and Gleason score (43-2) and / or notes entered by a diagnostician (43-3).

[0139] Meanwhile, since a lesion may not appear in the corresponding tissue image when the diagnosis of the tissue specimen corresponding to the biological tissue image is benign, the computing system (100) according to an embodiment of the present invention may not acquire a diagnosis result related to a lesion when the diagnosis of the tissue specimen corresponding to the biological tissue image is benign, and the diagnosis part of the biological tissue image in which the lesion does not appear may not include a diagnosis result related to a lesion. For example, when the diagnosis of the tissue specimen corresponding to the biological tissue image is benign, the computing system (100) may not acquire the first Gleason pattern and the second Gleason pattern of the biological tissue image, the length of the lesion included in the tissue specimen, the proportion of the lesion in the tissue specimen, the proportion of each Gleason pattern among the lesions included in the tissue specimen corresponding to the biological tissue image, the representative lesion image, etc., and the diagnosis part of the biological tissue image may not include such information.

[0140] FIG. 9 is a flowchart illustrating in more detail the process of generating a summary part for a pathology diagnosis case (i.e., step S130 of FIG. 2) by a computing system according to one embodiment of the present invention.

[0141] Referring to FIG. 9, the computing system (100) can obtain diagnostic results for each zone of the prostate (S121, S122). For example, as described above, the prostate may be pre-divided into 12 zones, in which case the computing system (100) can obtain diagnostic results for each of the 12 zones.

[0142] In one embodiment, the diagnostic result for the area may include at least some of the following: a diagnosis of the area, a primary Gleason pattern and a secondary Gleason pattern of the area, a length of a tissue sample collected from the area, a length of a lesion included in a tissue sample collected from the area, a proportion of the tissue sample collected from the area that is occupied by the lesion, a number of tissue samples collected from the area, a number of tissue samples in which a lesion is found among the tissue samples collected from the area, and pathological features found in the tissue samples collected from the area.

[0143] Meanwhile, according to an embodiment, if the diagnosis of the area is positive, the computing system (100) may not obtain a diagnosis result unrelated to the lesion, i.e., the first Gleason pattern and the second Gleason pattern of the area, the length of the lesion included in the tissue specimen collected from the area, the proportion of the lesion in the tissue specimen collected from the area, the number of tissue specimens in which the lesion was found among the tissue specimens collected from the area, etc.

[0144] In one embodiment, the computing system (100) can obtain at least some of the diagnostic results of each region of the prostate that are previously stored in a storage device provided by the computing system (100) or the server (10).

[0145] In another embodiment, the computing system (100) may determine at least some of the diagnostic results of each zone based on the diagnostic results of tissue samples collected from that zone.

[0146] For example, the computing system (100) may determine the most frequent diagnosis among the diagnosis names of the tissue specimens collected from the corresponding area or the result of merging the diagnosis names of the tissue specimens collected from the corresponding area as the diagnosis name of the corresponding area, and may determine the top two Gleason patterns that occupy the largest proportion among the tissue specimens collected from the corresponding area as the first Gleason pattern and the second Gleason pattern of the corresponding area, or may determine the first Gleason pattern and the second Gleason pattern of the tissue specimen with the most severe lesion (e.g., the highest Gleason score) among the tissue specimens collected from the corresponding area as the first Gleason pattern and the second Gleason pattern of the corresponding area. Additionally, for example, the computing system (100) may calculate the sum of the lengths of each tissue sample collected from the area, the sum of the lengths of lesions included in each tissue sample collected from the area, or the sum of the areas of lesions included in each tissue sample collected from the area compared to the sum of the areas of each tissue sample collected from the area, as a ratio of lesions to the tissue sample collected from the area.

[0147] Meanwhile, in some embodiments, the computing system (100) may select a lesion region representing a pathology diagnosis case including multiple biological tissue images and generate a representative lesion image of the pathology diagnosis case (S123). The lesion region may be a subregion of the biological tissue image having a predetermined shape and area. A specific method for generating a representative lesion image of the pathology diagnosis case will be described later.

[0148] Meanwhile, the computing system (100) can generate a summary part for a pathology diagnosis case to be included in a pathology diagnosis report (S124).

[0149] In one embodiment, the summary part for the pathology diagnosis case may include a summary table including diagnosis results for each of a plurality of regions that divide the prostate. In this case, the diagnosis results for the region may include at least some of the following: a diagnosis name for the region, a primary Gleason pattern and a secondary Gleason pattern for the region, a length of a tissue sample collected from the region, a length of a lesion included in a tissue sample collected from the region, a proportion of the tissue sample collected from the region that is occupied by the lesion, a number of tissue samples collected from the region, and pathological features found in the tissue samples collected from the region.

[0150] In one embodiment, the summary part for the pathology diagnosis case may include a prostate diagram of the pathology diagnosis case in which each of the plurality of regions is divided into regions corresponding to each of the plurality of regions, and each region is given a predetermined visual effect determined by the diagnosis result for the corresponding region.

[0151] In one embodiment, the summary part for the pathology diagnosis case may further include a diagnosis overview including a diagnosis name representing the pathology diagnosis case, the number of multiple tissue samples collected from the prostate of the patient, the number of tissue samples in which lesions were found among the multiple tissue samples collected from the prostate of the patient, and the primary Gleason pattern and secondary Gleason pattern of the pathology diagnosis case.

[0152] In one embodiment, the summary part for the pathology diagnosis case includes a summary table composed of summary information for each of the plurality of zones, the summary information for the zone includes a diagnosis result for the zone and a bar diagram corresponding to each tissue sample collected from the zone, the bar diagram being composed of parts corresponding to each non-lesioned area and lesioned area distributed in the corresponding tissue sample, and each part included in the bar diagram having a length proportional to the length of the area corresponding to the corresponding part, and a predetermined visual effect corresponding to a Gleason pattern of the area corresponding to the corresponding part can be provided.

[0153] FIG. 10 is a diagram illustrating an example of a summary part for a pathology diagnosis case generated by a computing system (100) according to an embodiment of the present invention. FIG. 10 is an example of a summary part for a pathology diagnosis case composed of biological tissue images corresponding to tissue specimens collected through a prostate biopsy. The summary part (50) for the pathology diagnosis case illustrated in FIG. 10 may include an overview section (51), a prostate diagram (52), and a summary table (53).

[0154] The above-mentioned overview section (51) may include a diagnosis representing the above-mentioned pathological diagnosis case (e.g., Acinar Adenocarcinoma in the example of FIG. 10). In one embodiment, the computing system (100) may determine the diagnosis with the highest frequency among the respective diagnosis names of the plurality of biological tissue images constituting the case as the diagnosis name of the case. Alternatively, the computing system (100) may determine the diagnosis with the highest frequency among the respective diagnosis names of the plurality of regions as the diagnosis name of the case.

[0155] Additionally, the above overview section (51) may further include the number of tissue specimens having the same diagnosis as the diagnosis representing the above pathological diagnosis case and the highest Gleason score.

[0156] The above prostate diagram (52) is divided into areas corresponding to each of the multiple zones that define the prostate, and each area can be provided with a predetermined visual effect determined by the diagnostic results for the corresponding zone. The visual effect can be a graphic effect recognizable to the naked eye, and can include things such as color, brightness, saturation, visual patterns, shadow effects, three-dimensional effects, or the assignment of special symbols.

[0157] The above summary part (50) may further include information (52-1) on the mapping relationship between the visual effects given to each area of ​​the prostate diagram and the diagnostic results of the area.

[0158] The prostate diagram (52) illustrated in the example of Fig. 10 is divided into 12 regions, and each region is assigned a unique color according to the diagnostic result of the tissue specimen corresponding to the region. For example, the region corresponding to region A with a benign diagnostic result is assigned green, the region corresponding to regions K and L with an indeterminate diagnostic result is assigned yellow, the region corresponding to regions B, D, E, F, J, G, and H with a malignant diagnostic result is assigned red, and the region corresponding to region I with an other diagnostic result is assigned gray. The region corresponding to region C from which no tissue specimen has been collected may be assigned white.

[0159] Meanwhile, the summary table (53) may display the identification symbol and location of each zone (53-1), diagnosis (53-2), Gleason score (53-3), length of lesion (53-4), length of tissue specimen (53-5), proportion of lesion in tissue specimen (53-6), and number of tissue specimens collected from the zone (53-7) in the form of a table.

[0160] FIG. 11a is a diagram illustrating another example of a summary part for a pathology diagnosis case generated by a computing system (100) according to one embodiment of the present invention. FIG. 11a is also an example of a summary part for a pathology diagnosis case composed of biological tissue images corresponding to tissue specimens collected through a prostate biopsy.

[0161] Referring to FIG. 11a, the summary part (60) for the pathology diagnosis case may include a summary table (61) and may further include representative lesion images (62-1, 62-2) of the pathology diagnosis case generated in step S123 of FIG. 9.

[0162] The summary table (61) may include the diagnosis results for each zone that divides the prostate. In the case of the summary table (62) of Fig. 11a, the diagnosis results for the A left lower (Left Base) zone, the B right lower (Right Base) zone, the C left middle (Left Mid) zone, and the D right middle (Right Base) zone are included.

[0163] In some embodiments, the summary part (60) for the pathology diagnosis case may further include a prostate diagram (63) in which each region is indicated, allowing the reviewer to recognize where the region is located in the prostate.

[0164] Figure 11b is an enlarged view of the summary table (61) of Figure 11a.

[0165] Referring to FIG. 11b, as described above, the summary table (61) may include diagnostic results for each zone (e.g., 61-1 to 61-5).

[0166] The diagnostic results by region may include the diagnosis of the region (e.g., 61-6), the Gleason score (e.g., 61-7), and / or the proportion of lesions within the tissue of each Gleason pattern (e.g., 61-8).

[0167] Additionally, the diagnostic results for each zone may include the diagnostic results of each of the tissue samples collected from the zone (e.g., 61-9 to 61-11). For example, the diagnostic result (61-1) for the A Right Mid zone may include the diagnostic results (61-9 to 61-11) for each of the three tissue samples collected from the zone, and the diagnostic result (61-2) for the B Right Apex zone may include the diagnostic results of each of the three tissue samples collected from the zone.

[0168] Meanwhile, the diagnostic results of an individual tissue sample may include the diagnosis of the tissue sample (e.g., 61-12), a bar diagram corresponding to the tissue sample (e.g., 61-13), and the length of the lesion contained in the tissue sample, the length of the tissue sample, the proportion of the tissue sample occupied by the lesion, and the pathological features found in the tissue sample (see 61-13).

[0169] The above bar diagram is composed of parts corresponding to each non-lesion area and lesion area distributed in the corresponding tissue specimen, and each part included in the bar diagram has a length proportional to the length of the area corresponding to the part, and a predetermined visual effect corresponding to the Gleason pattern of the area corresponding to the part can be provided. In the case of the bar diagram of Fig. 11b (e.g., 61-13), the part corresponding to the lesion area is provided with a color mapped to the Gleason pattern of the part.

[0170] FIG. 12 is a diagram illustrating an example of a method for generating a bar diagram corresponding to a biological tissue image by a computing system (100) according to an embodiment of the present invention. The computing system (100) can determine a line segment (6) crossing both ends of a tissue sample (4) included in the biological tissue image. The line segment (6) may be, but is not limited to, the longest line segment among countless line segments crossing the tissue sample or the line segment that includes the largest number of lesion areas, and the like, and the method for selecting any one of the line segments crossing the tissue sample may vary.

[0171] Meanwhile, the computing system (100) can generate a bar diagram (6) having a length proportional to the length of the line segment (6), identify lesion-passing portions passing through the lesion area among the line segments (6), and assign a color mapped to the Gleason pattern of the lesion area to a portion on the bar diagram corresponding to each identified lesion-passing portion. In the example of Fig. 12, a portion (5-1) on the bar diagram corresponding to a line segment passing through the lesion area (4-1) in the tissue specimen (4) is assigned a yellow color corresponding to the Gleason pattern of the lesion area (4-1), and a portion (5-2) on the bar diagram corresponding to a line segment passing through the lesion area (4-2) in the tissue specimen (4) is assigned a red color corresponding to the Gleason pattern of the lesion area (4-2).

[0172] FIG. 13 is a flowchart illustrating in more detail the process of generating a representative lesion image (i.e., step S123 of FIG. 9) by a computing system (100) according to one embodiment of the present invention.

[0173] Referring to FIG. 13, the computing system (100) can obtain the first Gleason pattern and the second Gleason pattern of the pathology diagnosis case (S210). The first Gleason pattern and the second Gleason pattern of the pathology diagnosis case are the same type of Gleason patterns as the Gleason patterns for each pixel included in the pixel-by-pixel diagnosis results of the biological tissue image. In one embodiment, the computing system (100) can calculate the ratio of each Gleason pattern in all biological tissue images constituting the pathology diagnosis case and determine the first Gleason pattern and the second Gleason pattern of the pathology diagnosis case based on the calculated ratio.

[0174] More specifically, the computing system (100) can count the number of pixels for each Gleason pattern from the pixel-by-pixel diagnosis results of each biological tissue image constituting the pathology diagnosis case, and add up the number of pixels for each Gleason pattern for all biological tissue images to calculate the ratio of each Gleason pattern in all biological tissue images constituting the pathology diagnosis case. Thereafter, the computing system (100) can determine the Gleason pattern with the largest total number of pixels within the case as the primary Gleason pattern, and determine the Gleason pattern with the next largest total number of pixels as the secondary Gleason pattern.

[0175] Fig. 14 is a diagram showing slide images corresponding to three biological tissues A, B, and C, respectively (each slide image is annotated with a Gleason pattern in a different color) and the number of pixels for each Gleason pattern in each slide image. In the entire case of Fig. 14, in the case of Gleason pattern 3, a total of 35 (=20+15) pixels are counted, in the case of Gleason pattern 4, a total of 80 (=35+40+5) pixels are counted, and in the case of Gleason pattern 5, a total of 0 pixels are counted, so the computing system (100) can determine Gleason pattern 4 as the first Gleason pattern and Gleason pattern 3 as the second Gleason pattern.

[0176] Meanwhile, in another embodiment, the computing system (100) may obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image that are stored in advance in a storage device provided by the computing system (100) or the server, or may obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image from the user terminal (20).

[0177] Or, according to an embodiment, the computing system (100) may analyze the biological tissue image or the pixel-wise diagnosis result of the biological tissue image to obtain the first Gleason pattern and the second Gleason pattern of the biological tissue image. At this time, the computing system (100) may use a pre-trained deep learning model (200). The deep learning model (200) may be an artificial neural network that has been pre-trained to receive an input image or a pixel-wise diagnosis result of an image and determine the first Gleason pattern and the second Gleason pattern of the corresponding image, and may be an artificial neural network that has been pre-trained to receive an image or a pixel-wise diagnosis result of an image through an input layer and output a probability that the corresponding image corresponds to a predetermined Gleason pattern.

[0178] Referring again to FIG. 13, the computing system (100) can search for a first partial region, a second partial region, and a third partial region of each of the plurality of biological tissue images included in the pathology diagnosis case (S220, S230).

[0179] FIG. 15 is a drawing illustrating in more detail the process (i.e., step S230 of FIG. 10) in which the computing system (100) searches for the first partial region, the second partial region, and the third partial region of a specific biological tissue image in one embodiment of the present invention.

[0180] Referring to FIG. 15, the computing system (100) can search for a first partial region among the partial regions of the biological tissue image, in which the first Gleason pattern is most frequently included in the pixel-unit diagnostic results corresponding to the corresponding region (S231). At this time, the partial region of the biological tissue image may be a region having a predefined shape and area as a part of the biological tissue image. That is, the shape and area of ​​the partial region may be preset within the computing system (100).

[0181] The computing system (100) can search the first partial region in a sliding window manner in which the shape and area of ​​the window are set to be the same as the partial region of the biological tissue image. For example, if the partial region and the window are rectangular in shape with a size of w pixels × h pixels, the computing system (100) can calculate the number of pixels in the corresponding window having the first Gleason pattern by moving the rectangular window having the size of w × h by a predetermined sliding step (one or more pixels), and can determine the window containing the largest number of the first Gleason patterns as the first partial region.

[0182] The computing system (100) can search for a second partial region among the partial regions of the biological tissue image, in which the pixel-by-pixel diagnostic results corresponding to the corresponding region contain the largest number of the second Gleason pattern (S232). It goes without saying that the sliding window method can also be used in the process in which the computing system (100) searches for the second partial region.

[0183] Thereafter, the computing system (100) can generate a modified pixel-unit diagnosis result by removing the pixel-unit diagnosis result corresponding to the first partial region from the pixel-unit diagnosis result of the biological tissue image (S233).

[0184] Thereafter, the computing system (100) can search for a third partial region among the partial regions of the biological tissue image, in which the second Gleason pattern is most abundant in the modified pixel-unit diagnostic results corresponding to the corresponding region (S234). It goes without saying that the sliding window method can also be used in the process in which the computing system (100) searches for the second partial region.

[0185] Fig. 16(a) illustrates an example of a first partial region searched by the computing system (100). If the first Gleason pattern is 4, the computing system (100) will determine that the region on the biological tissue image corresponding to the region (4-1) of Fig. 16(a) containing the largest number of the first Gleason pattern (i.e., pattern 4) is the first partial region (step S231 of Fig. 15).

[0186] Fig. 16(b) illustrates an example of a second partial region searched by the computing system (100). If the second Gleason pattern is 3, the computing system (100) will determine that the region on the biological tissue image corresponding to the region (4-2) of Fig. 16(b) containing the largest number of second Gleason patterns (i.e., pattern 3) is the second partial region (step S232 of Fig. 15).

[0187] Thereafter, the computing system (100) can generate a modified pixel-by-pixel diagnosis result as shown in FIG. 16(c) by removing the pixel-by-pixel diagnosis result corresponding to the first partial region from the pixel-by-pixel diagnosis result of the biological tissue image (S233 of FIG. 15). FIG. 16 illustrates an example of assigning 0 indicating positive to the region in order to remove the pixel-by-pixel diagnosis result corresponding to the first partial region, but depending on the embodiment, a value indicating non-tissue or a third value indicating that the region is a deleted region may be assigned to the region.

[0188] Thereafter, the computing system (100) can sequentially scan the modified pixel-by-pixel diagnostic results, such as those in FIG. 16(c), in a 6×4 sized window to search for the third partial region containing the largest number of secondary Gleason patterns. Since the secondary Gleason pattern is 3, the computing system (100) will determine that the region on the biological tissue image corresponding to the region (4-3) in FIG. 16(d) is the third partial region (step S234 in FIG. 15).

[0189] Referring again to FIG. 13, the computing system (100) can select a representative lesion image representing a pathological diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images searched through the previous process (S240).

[0190] Figure 17 is a drawing illustrating step S240 of Figure 13 in more detail.

[0191] Referring to FIG. 17, the computing system (100) can select, among the first partial region of each of the plurality of biological tissue images and the second partial region of each of the plurality of biological tissue images, a partial region that contains the largest number of the first Gleason pattern of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding region as a first representative lesion image (S241).

[0192] In addition, the computing system (100) can select a second representative lesion image that includes the largest number of secondary Gleason patterns of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding area among the first partial area of ​​each of the plurality of biological tissue images, the second partial area of ​​each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and the third partial area of ​​the biological tissue image including the first representative lesion image (S242).

[0193] The first representative lesion image and the second representative lesion image selected as above are representative lesion images of the pathological diagnosis case. The computing system (100) can output the first representative lesion image and the second representative lesion image in the form of separate image files and store them in a storage device provided by the computing system (100) or the server (10). Alternatively, the computing system can output / store information that can identify the first representative lesion image and the second representative lesion image (e.g., coordinates and sizes of reference points on a biological tissue image, etc.).

[0194] FIG. 18 is a diagram showing examples of a first partial region, a second partial region, and a third partial region searched in each of the biological tissue images, such as the example illustrated in FIG. 14. In FIG. 18(a), P_A1, P_B1, and P_C1 represent first partial images searched in biological tissue images A, B, and C, respectively, in FIG. 18(b), S1_A1, and S1_C1 represent second partial images searched in biological tissue images A, C, respectively, and in FIG. 18(c), S2_A1, and S2_C1 represent third partial images searched in biological tissue images A, C, respectively.

[0195] An example of the process of FIG. 17 is explained with reference to FIG. 18 as follows.

[0196] As shown in FIG. 18, when the first partial region, the second partial region, and the third partial region of each biological tissue image are searched, the computing system (100) can select P_A1, which is the partial region that contains the most first Gleason pattern (i.e., pattern 4) in the pixel unit diagnosis corresponding to the corresponding region among P_A1, P_B1, P_C1 of FIG. 18(a) and S1_A1, S1_C1 of FIG. 18(b), as the first representative lesion image (S241).

[0197] In addition, the computing system (100) may select, as a first representative lesion image, a first partial region (P_A1, P_B1, P_C1) of each of a plurality of biological tissue images, a second partial region (S1_C1) of each of the remaining biological tissue images excluding the biological tissue image (i.e., biological tissue image A) including the first representative lesion image (P_A1) among the plurality of biological tissue images, and a third partial region (S2_A1) of the biological tissue image (i.e., biological tissue image A) including the first representative lesion image (P_A1), a partial region S2_A1 that includes the second Gleason pattern (i.e., pattern 3) in the pixel unit diagnosis corresponding to the corresponding region (S242).

[0198] A diagram illustrating the above process more easily is shown in Fig. 19. Fig. 19(a) shows candidates for the first representative lesion image (i.e., P_A1, P_B1, P_C1, S1_A1, S1_C1) and that P_A1 was selected as the first representative lesion image. Fig. 19(b) shows candidates for the second representative lesion image (i.e., P_A1, P_B1, P_C1, S2_A1, S1_C1) and that S2_A1 was selected as the second representative lesion image.

[0199] Figures 20 to 24 are block diagrams illustrating the logical configuration of a computing system (100) according to one embodiment of the present invention.

[0200] The computing system (100) may refer to a logical configuration equipped with hardware resources and / or software necessary to implement the technical idea of ​​the present invention, and does not necessarily refer to a single physical component or device. That is, the computing system (100) may refer to a logical combination of hardware and / or software provided to implement the technical idea of ​​the present invention, and, if necessary, may be implemented as a set of logical configurations for implementing the technical idea of ​​the present invention by being installed in devices spaced apart from each other and performing their respective functions. In addition, the computing system (100) may refer to a set of configurations that are separately implemented for each function or role for implementing the technical idea of ​​the present invention. Each configuration of the computing system (100) may be located on different physical devices or may be located on the same physical device. In addition, depending on the implementation example, the combination of software and / or hardware constituting each component of the computing system (100) may also be located on different physical devices, and the configurations located on different physical devices may be organically combined with each other to implement each of the modules.

[0201] Furthermore, the term "module" in this specification may refer to a functional and structural combination of hardware for implementing the technical concepts of the present invention and software for operating the hardware. For example, the module may refer to a logical unit of a given code and hardware resources for executing the given code, and it is readily apparent to an average expert in the technical field of the present invention that it does not necessarily refer to physically connected code or a single type of hardware.

[0202] Referring to FIG. 20, the computing system (100) may include an image acquisition module (110), an image diagnosis result acquisition module (120), a representative lesion area extraction module (130), a site information acquisition module (140), a region diagnosis result acquisition module (150), a case representative lesion image generation module (160), a diagnosis part generation module (170), a summary part generation module (180), and a report generation module (190). Depending on the embodiment of the present invention, some of the above-described components may not necessarily correspond to components essential to the implementation of the present invention, and further, depending on the embodiment, the computing system (100) may include more components than this. For example, the computing system (100) may further include a communication module (not shown) for communicating with an external device, a storage module (not shown) for storing data, a control module (not shown) for controlling components and resources of the computing system (100), etc.

[0203] The image acquisition module (110) can acquire the plurality of biological tissue images included in the pathology diagnosis case and the pixel-wise diagnosis results of each of the plurality of biological tissue images. Here, the pixel-wise diagnosis results of the biological tissue images can include a Gleason pattern for each pixel constituting the biological tissue image. The image diagnosis result acquisition module (120) can acquire the diagnosis results of the biological tissue images for each of the plurality of biological tissue images, and the diagnosis results of the biological tissue images can include a diagnosis name of a tissue specimen corresponding to the biological tissue image, a first Gleason pattern of the biological tissue image, and a second Gleason pattern.

[0204] The above representative lesion area extraction module (130) can extract a representative lesion area of ​​the biological tissue image, which is a representative portion of the biological tissue image, for each of the plurality of biological tissue images.

[0205] The above diagnostic part generation module (170) can generate a diagnostic part for each of the plurality of biological tissue images in a pathology diagnosis report. At this time, the diagnostic part for the biological tissue image can include a diagnosis name of a tissue specimen corresponding to the biological tissue image, a first Gleason pattern and a second Gleason pattern of the biological tissue image, and an image of a representative lesion area of ​​the biological tissue image in which pixel-by-pixel diagnostic results overlap.

[0206] The above report generation module (190) can generate a pathology diagnosis report, which is an electronic document including a diagnosis part for each of the plurality of biological tissue images.

[0207] In one embodiment, the computing system (100) may further include a site information acquisition module that acquires information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions in which the prostate is divided, and the diagnostic part for the biological tissue image may further include a prostate diagram in which regions corresponding to each of the plurality of regions are divided and regions corresponding to the sites from which tissue samples corresponding to the biological tissue images were collected are visually highlighted.

[0208] In one embodiment, the diagnosis result of the biological tissue image may further include the length of the tissue specimen corresponding to the biological tissue image, the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, and the ratio of each Gleason pattern in the biological tissue image, and the diagnosis part for the biological tissue image may further include the length of the tissue specimen corresponding to the biological tissue image, the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the ratio of the lesion in the tissue specimen corresponding to the biological tissue image, the ratio of each Gleason pattern in the biological tissue image, and at least a portion of the biological tissue image in which the outline of the area corresponding to the representative lesion image of the biological tissue image is expressed.

[0209] In one embodiment, the computing system (100) may further include a site information acquisition module (140) that acquires information about a site from which a tissue specimen corresponding to each of the plurality of biological tissue images was collected. Here, the site is one of the plurality of regions in which the prostate is divided. Meanwhile, the computing system (100) may further include a region diagnosis result acquisition module (150) that acquires a diagnosis result for each of the plurality of regions based on a diagnosis result of a biological tissue image corresponding to a tissue specimen collected from the region among the plurality of biological tissue images, and a summary part generation module (180) that generates a summary part for the pathology diagnosis case. In this case, the pathology diagnosis report may further include the summary part, and the summary part for the pathology diagnosis case may include a prostate diagram of the pathology diagnosis case in which a summary table including a diagnosis result for each of the plurality of regions and a region corresponding to each of the plurality of regions are divided, and each region is provided with a predetermined visual effect determined by the diagnosis result for the corresponding region.

[0210] In one embodiment, the diagnostic results for the area may include at least some of the following: a diagnosis of the area, a primary Gleason pattern and a secondary Gleason pattern of the area, a length of a tissue sample taken from the area, a length of a lesion included in a tissue sample taken from the area, a proportion of the tissue sample taken from the area that is occupied by the lesion, a number of tissue samples taken from the area, and pathological features found in the tissue samples taken from the area.

[0211] In one embodiment, the summary part for the pathology diagnosis case may further include a diagnosis overview including a diagnosis name representing the pathology diagnosis case, the number of multiple tissue samples collected from the prostate of the patient, the number of tissue samples in which lesions were found among the multiple tissue samples collected from the prostate of the patient, and the primary Gleason pattern and secondary Gleason pattern of the pathology diagnosis case.

[0212] In one embodiment, the summary part for the pathology diagnosis case includes a summary table composed of summary information for each of the plurality of zones, the summary information for the zone includes a diagnosis result for the zone and a bar diagram corresponding to each tissue sample collected from the zone, the bar diagram is composed of parts corresponding to each non-lesion area and lesion area distributed in the corresponding tissue sample, each part included in the bar diagram has a length proportional to the length of the area corresponding to the part, and a predetermined visual effect corresponding to a Gleason pattern of the area corresponding to the part can be applied.

[0213] Fig. 21 is a block diagram showing a specific configuration of a representative lesion area extraction module (130) according to one embodiment of the present invention.

[0214] Referring to FIG. 21, the representative lesion area extraction module (130) may include a first search module (131), a removal module (132), a second search module (133), and a judgment module (134).

[0215] The first search module (131) can search for a first partial region among the partial regions of the biological tissue image, in which the first Gleason pattern is most frequently included in the pixel-unit diagnostic results corresponding to the corresponding region. Here, the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area.

[0216] The above removal module (132) can generate a modified pixel unit diagnosis result by removing the pixel unit diagnosis result corresponding to the first partial region from the pixel unit diagnosis result of the biological tissue image.

[0217] The second search module (133) can search for a second partial region among the partial regions of the biological tissue image, in which the second Gleason pattern is most included in the modified pixel unit diagnosis result corresponding to the corresponding region.

[0218] The above judgment module (134) can determine the first partial region of the biological tissue image and the second partial region of the biological tissue image as representative lesion regions of the biological tissue image.

[0219] Fig. 22 is a block diagram showing a specific configuration of a case representative lesion image generation module (160) according to one embodiment of the present invention.

[0220] Referring to FIG. 22, the case representative lesion image generation module (160) may include a case lesion pattern acquisition module (161), an area search module (162), and a selection module (163).

[0221] The above case lesion pattern acquisition module (161) can acquire the first Gleason pattern and the second Gleason pattern of the above pathological diagnosis case.

[0222] The above region search module (162) can search for a first partial region, a second partial region, and a third partial region of each of the plurality of biological tissue images included in the pathology diagnosis case, and the above selection module (163) can select and output a representative lesion image representing the pathology diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images.

[0223] Figure 23 is a block diagram showing a specific configuration of an area search module (162) according to one embodiment of the present invention.

[0224] Referring to FIG. 23, the search module (162) may include a first partial area search module (1621), a second partial area search module (1622), a modification module (1623), and a third partial area search module (1624).

[0225] The first partial region search module (1621) can search for the first partial region among the partial regions of the biological tissue image, in which the first Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-unit diagnosis results corresponding to the corresponding region. At this time, the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area.

[0226] In one embodiment, the first partial region search module (1621) can search the first partial region in a sliding window manner in which the shape and area of ​​the window are set to be the same as the partial region of the biological tissue image.

[0227] The second partial region search module (1622) can search for the second partial region among the partial regions of the biological tissue image, in which the second Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-level diagnosis results corresponding to the corresponding region. At this time, the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area.

[0228] In one embodiment, the second partial region search module (1622) can search the second partial region in a sliding window manner in which the shape and area of ​​the window are set to be the same as the partial region of the biological tissue image.

[0229] The above correction module (1623) can generate a corrected pixel-unit diagnosis result by removing a pixel-unit diagnosis result corresponding to the first partial region from the pixel-unit diagnosis result of the biological tissue image.

[0230] The third partial region search module (1624) can search for a third partial region among the partial regions of the biological tissue image, in which the second Gleason pattern of the pathological diagnosis case is most included in the modified pixel unit diagnosis result corresponding to the region.

[0231] In one embodiment, the third partial region search module (1624) can search the third partial region in a sliding window manner in which the shape and area of ​​the window are set to be the same as the partial region of the biological tissue image.

[0232] Figure 24 is a block diagram showing a specific configuration of a selection module (163) according to one embodiment of the present invention.

[0233] Referring to FIG. 24, the selection module (163) may include a first representative lesion image selection module (1631), a second representative lesion image selection module (1632), and a representative lesion image storage module (1633).

[0234] The first representative lesion image selection module (1631) can select a first representative lesion image that contains the largest number of first Gleason patterns of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding region among the first partial region of each of the plurality of biological tissue images and the second partial region of each of the plurality of biological tissue images.

[0235] The second representative lesion image selection module (1632) may select a second representative lesion image that includes the largest number of secondary Gleason patterns of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding region among the first partial region of each of the plurality of biological tissue images, the second partial region of each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and the third partial region of the biological tissue image including the first representative lesion image.

[0236] The representative lesion image storage module (1633) may store the first representative lesion image and the second representative lesion image as representative lesion images representing the pathological diagnosis case. For example, the representative lesion image storage module (1633) may store the first representative lesion image and the second representative lesion image in a predetermined storage device connected to the computing system (100).

[0237] Meanwhile, the above-described content is about the process of extracting a representative lesion image corresponding to the first Gleason pattern (i.e., the first representative lesion image) and a representative lesion image corresponding to the second Gleason pattern (i.e., the second representative lesion image), but it goes without saying that the lesion image extraction method according to the technical idea of ​​the present invention can also be applied to a method of extracting three or more representative lesion images.

[0238] Meanwhile, depending on the implementation example, the computing system (100) may include a processor and a memory that stores a program executed by the processor. In this case, the computing system (100) may have a configuration as illustrated in FIG. 25. FIG. 25 is a diagram illustrating the physical configuration of the computing system (100) according to an embodiment of the present invention.

[0239] The above computing system (100) may be equipped with a memory (102) in which a program for implementing the technical idea of ​​the present invention is stored, and a processor (101) for executing the program stored in the memory (102).

[0240] An average expert in the technical field of the present invention will be able to easily infer that the processor (101) may be named by various names such as CPU, APU, mobile processor, etc., depending on the implementation example of the computing system (100). The processor may include a single-core CPU or a multi-core CPU. In addition, the computing system (100) may be implemented by organically combining a plurality of physical devices, and in this case, an average expert in the technical field of the present invention will be able to easily infer that the computing system (100) of the present invention may be implemented by providing at least one processor (101) for each physical device.

[0241] The above memory (102) stores the program and may be implemented as any type of storage device that the processor can access to run the program. The memory (102) may include a high-speed random access memory and may also include non-volatile memory such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Access to the memory by the processor and other components may be controlled by a memory controller. In addition, depending on the hardware implementation example, the memory (102) may be implemented as a plurality of storage devices rather than a single storage device. In addition, the memory (102) may include a temporary storage device as well as a main memory device. In addition, it may be implemented as a volatile memory or a non-volatile memory, and may be defined to mean all types of information storage means that are implemented so that the program can be stored and run by the processor.

[0242] The above program, when executed by the processor (101), can cause the computing system (100) to perform the above-described pathology diagnosis report generation method.

[0243] Meanwhile, the method according to an embodiment of the present invention may be implemented in the form of computer-readable program commands and stored on a computer-readable recording medium, and the control program and target program according to an embodiment of the present invention may also be stored on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system.

[0244] The program commands recorded on the recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the software field.

[0245] Examples of computer-readable storage media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Additionally, the computer-readable storage media can be distributed over network-connected computer systems so that the computer-readable code can be stored and executed in a distributed manner.

[0246] Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a device that processes information electronically, such as a computer, using an interpreter.

[0247] The hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

[0248] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

[0249] The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

[0250]

[0251] The present invention can be used in a method for generating a pathology diagnosis report for a pathology diagnosis case and a computing system for performing the same.

[0252]

Claims

1. A method for generating a pathology diagnosis report for a pathology diagnosis case comprising multiple biological tissue images, each of which is a digital scan image of multiple tissue samples collected from the prostate of a given patient, A step of the computing system obtaining the plurality of biological tissue images included in the pathology diagnosis case and the pixel-wise diagnosis results of each of the plurality of biological tissue images, wherein the pixel-wise diagnosis results of the biological tissue images include a Gleason Pattern for each pixel constituting the biological tissue images; A step in which the computing system obtains a diagnosis result of the biological tissue image for each of the plurality of biological tissue images; The computing system generates a diagnostic part for each of the plurality of biological tissue images in a pathology diagnosis report; and The computing system comprises a step of generating a pathology diagnosis report, which is an electronic document including a diagnostic part for each of the plurality of biological tissue images, The step of obtaining the diagnostic results of the above biological tissue image is: A step of obtaining a diagnosis name of a tissue specimen corresponding to the above biological tissue image; If the diagnosis of the above tissue sample is not benign, a step of acquiring the first Gleason pattern and the second Gleason pattern of the biological tissue image; and If the diagnosis of the above tissue sample is not positive, a step of extracting a representative lesion area of ​​the above tissue image, which is a representative part of the above tissue image, is included. The diagnostic part for the above biological tissue image is, If the diagnosis of the above tissue sample is positive, the diagnosis of the tissue sample corresponding to the above biological tissue image is included, A method further comprising an image of a representative lesion area of ​​the biological tissue image, in which the first Gleason pattern and the second Gleason pattern of the biological tissue image and the pixel-level diagnostic result overlap, when the diagnosis of the above tissue sample is not positive.

2. In the first paragraph, the method, A step of obtaining information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of zones in which the prostate is divided, The diagnostic part for the above biological tissue image is, A method further comprising a prostate diagram in which an area corresponding to each of the plurality of regions is distinguished and an area corresponding to a site from which a tissue sample corresponding to the biological tissue image is collected is visually highlighted.

3. In paragraph 1, The step of obtaining the diagnostic results of the above biological tissue image is: A step of obtaining the length of a tissue specimen corresponding to the above biological tissue image; and If the diagnosis of the above tissue sample is not benign, a step of obtaining the length of the lesion included in the tissue sample corresponding to the biological tissue image, the proportion of the lesion in the tissue sample corresponding to the biological tissue image, and the proportion of each pattern in the Gleason grading system in the lesion included in the tissue sample corresponding to the biological tissue image is included. The diagnostic part for the above biological tissue image is, Further including the length of the tissue specimen corresponding to the above biological tissue image, A method further comprising at least a portion of the biological tissue image in which the length of the lesion included in the tissue sample corresponding to the biological tissue image, the proportion of the lesion in the tissue sample corresponding to the biological tissue image, the proportion of each pattern in the Gleason grading system in the lesion included in the tissue sample corresponding to the biological tissue image, and the outline of the area corresponding to the representative lesion image of the biological tissue image are expressed, if the diagnosis of the biological tissue sample is not benign.

4. In paragraph 1, The step of extracting the representative lesion area of ​​the above biological tissue image is: A step of searching for a first partial region among the partial regions of the biological tissue image, wherein the first Gleason pattern is most included in the pixel-unit diagnosis result corresponding to the region, wherein the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area; A step of generating a modified pixel-unit diagnosis result by removing a pixel-unit diagnosis result corresponding to the first partial region from the pixel-unit diagnosis result of the above biological tissue image; A step of searching for a second partial region among the partial regions of the above biological tissue image, in which the second Gleason pattern is most included in the modified pixel unit diagnosis result corresponding to the corresponding region; and A method comprising a step of determining a first partial region of the biological tissue image and a second partial region of the biological tissue image as representative lesion regions of the biological tissue image.

5. In the first paragraph, the method, A step in which the computing system obtains information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions in which the prostate is divided; The computing system, for each of the plurality of zones, A step of obtaining a diagnostic result for the area determined based on the diagnostic result of a biological tissue image corresponding to a tissue sample collected from the area among the plurality of biological tissue images; and The computing system further includes a step of generating a summary part for the pathology diagnosis case, The above pathology diagnosis report further includes the above summary part, The summary part for the above pathological diagnosis case is: A summary table including diagnostic results for each of the above multiple zones; and A method including a prostate diagram of the pathological diagnosis case, wherein each of the plurality of regions is divided into regions corresponding to each of the regions, and each region is given a predetermined visual effect determined by the diagnosis result for the corresponding region.

6. In paragraph 5, The diagnostic results for the above area are: A method comprising at least some of the following: a diagnosis of the area, a primary Gleason pattern and a secondary Gleason pattern of the area, a length of a tissue sample taken from the area, a length of a lesion included in a tissue sample taken from the area, a proportion of a lesion in a tissue sample taken from the area, a number of tissue samples taken from the area, and pathological features found in a tissue sample taken from the area.

7. In paragraph 5, The summary part for the above pathological diagnosis case is: A method further comprising a diagnosis overview including a diagnosis name representing the above pathological diagnosis case, the number of multiple tissue samples collected from the prostate of the patient, the number of tissue samples in which lesions are found among the multiple tissue samples collected from the prostate of the patient, and the first Gleason pattern and the second Gleason pattern of the above pathological diagnosis case.

8. In the first paragraph, the method, A step in which the computing system obtains information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions in which the prostate is divided; The computing system, for each of the plurality of zones, A step of obtaining a diagnostic result for the area determined based on the diagnostic result of a biological tissue image corresponding to a tissue sample collected from the area among the plurality of biological tissue images; and The computing system further comprises a step of generating a summary part for the pathology diagnosis case, The above pathology diagnosis report further includes the above summary part, The summary part for the above pathological diagnosis case is: Includes a summary table consisting of summary information for each of the above multiple zones, Summary information for the above area is: Includes diagnostic results for the above area and a bar diagram corresponding to each tissue sample collected from the above area, The above bar diagram, A method in which each portion included in the bar diagram is composed of a portion corresponding to each non-lesion area and lesion area distributed in the corresponding tissue specimen, and each portion has a length proportional to the length of the area corresponding to the portion, and a predetermined visual effect corresponding to the Gleason pattern of the area corresponding to the portion is given.

9. In the first paragraph, the method, The computing system further comprises a step of generating a representative lesion image of the pathological diagnosis case, The above pathology diagnosis report further includes the representative lesion image, The step of generating a representative lesion image of the above pathological diagnosis case is: A step of obtaining the first Gleason pattern and the second Gleason pattern of the above pathological diagnosis case; For each of the plurality of biological tissue images, a step of searching a first partial region, a second partial region, and a third partial region of the biological tissue image; and Including a step of selecting a representative lesion image representing the pathological diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images, The step of exploring the first part region, the second part region, and the third part region of the above biological tissue image is: A step of searching for a first partial region among the partial regions of the biological tissue image, wherein the first Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-unit diagnosis result corresponding to the region, wherein the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area; A step of searching for the second partial region among the partial regions of the above biological tissue image, in which the second Gleason pattern of the pathological diagnosis case is most included in the pixel-unit diagnosis result corresponding to the corresponding region; A step of generating a modified pixel-by-pixel diagnosis result by removing the pixel-by-pixel diagnosis result corresponding to the first partial region from the pixel-by-pixel diagnosis result of the biological tissue image; and A step of searching for the third partial region among the partial regions of the above biological tissue image, wherein the second Gleason pattern of the pathological diagnosis case is most included in the modified pixel unit diagnosis result corresponding to the corresponding region, The step of selecting a representative lesion image representing the above pathological diagnosis case is: A step of selecting a first representative lesion image that contains the largest number of the first Gleason pattern of the pathological diagnosis case in the pixel unit diagnosis corresponding to the region among the first partial region of each of the plurality of biological tissue images and the second partial region of each of the plurality of biological tissue images; and A method comprising the step of selecting a second representative lesion image that includes the largest number of secondary Gleason patterns of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding region among a first partial region of each of the plurality of biological tissue images, a second partial region of each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and a third partial region of the biological tissue image including the first representative lesion image.

10. A computer program stored on a recording medium for executing the method described in any one of claims 1 to 9 on a computing system.

11. A computer-readable recording medium having recorded thereon a program for executing the method described in any one of claims 1 to 9 on a computing system.

12. As a computing system, a processor; and a memory for storing a computer program, The above computer program, A computing system that, when executed by the processor, causes the computing system to perform the method described in any one of claims 1 to 9.

13. A computing system for performing a method of generating a pathology diagnosis report for a pathology diagnosis case comprising a plurality of biological tissue images, each of which is a digital scan image of a plurality of tissue specimens collected from the prostate of a given patient, An image acquisition module that acquires the plurality of biological tissue images included in the above pathology diagnosis case and the pixel-by-pixel diagnosis results of each of the plurality of biological tissue images, wherein the pixel-by-pixel diagnosis results of the biological tissue images include a Gleason pattern for each pixel constituting the biological tissue images; For each of the plurality of biological tissue images, an image diagnosis result acquisition module that acquires a diagnosis result of the biological tissue image, wherein the diagnosis result of the biological tissue image includes a diagnosis name of a tissue sample corresponding to the biological tissue image, and further includes a first Gleason pattern and a second Gleason pattern of the biological tissue image when the diagnosis name of the tissue sample is benign; For each of the plurality of biological tissue images, a representative lesion area extraction module that extracts a representative lesion area of ​​the biological tissue image, which is a representative part of the biological tissue image, when the diagnosis of the tissue sample is not positive; For each of the plurality of biological tissue images, a diagnostic part generation module that generates a diagnostic part for the biological tissue image of the pathology diagnosis report; and Includes a report generation module that generates a pathology diagnosis report, which is an electronic document including a diagnostic part for each of the plurality of biological tissue images, The diagnostic part for the above biological tissue image is, If the diagnosis of the above tissue sample is positive, the diagnosis of the tissue sample corresponding to the above biological tissue image is included, A computing system further comprising an image of a representative lesion area of ​​the biological tissue image in which the first Gleason pattern and the second Gleason pattern of the biological tissue image and the pixel-level diagnostic result overlap, when the diagnosis of the above tissue sample is not positive.

14. In the 13th paragraph, the computing system, A site information acquisition module for acquiring information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images was collected, wherein the site is one of the plurality of regions in which the prostate is divided, The diagnostic part for the above biological tissue image is, A computing system further comprising a prostate diagram in which an area corresponding to each of the plurality of regions is distinguished, and an area corresponding to a site from which a tissue sample corresponding to the biological tissue image is collected is visually highlighted.

15. In paragraph 13, The diagnostic results of the above biological tissue images are: Further including the length of the tissue specimen corresponding to the above biological tissue image, If the diagnosis of the above tissue specimen is not benign, the length of the lesion included in the tissue specimen corresponding to the biological tissue image, the proportion of the lesion in the tissue specimen corresponding to the biological tissue image, and the proportion of each pattern in the Gleason grading system in the lesion included in the tissue specimen corresponding to the biological tissue image are further included. The diagnostic part for the above biological tissue image is, Further including the length of the tissue specimen corresponding to the above biological tissue image, A computing system further comprising at least a portion of the biological tissue image in which, when the diagnosis of the above tissue sample is not benign, the length of the lesion included in the tissue sample corresponding to the biological tissue image, the proportion of the lesion in the tissue sample corresponding to the biological tissue image, the proportion of each pattern in the Gleason grading system in the lesion included in the tissue sample corresponding to the biological tissue image, and the outline of the area corresponding to the representative lesion image of the biological tissue image are expressed.

16. In the 13th paragraph, the representative lesion area extraction module, A first search module that searches for a first partial region among the partial regions of the biological tissue image, wherein the first Gleason pattern is most frequently included in the pixel-unit diagnosis results corresponding to the corresponding region, wherein the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area; A removal module that removes a pixel-by-pixel diagnosis result corresponding to the first partial region from the pixel-by-pixel diagnosis result of the above biological tissue image to generate a modified pixel-by-pixel diagnosis result; A second search module that searches for a second partial region among the partial regions of the above biological tissue image, in which the second Gleason pattern is most included in the modified pixel unit diagnosis result corresponding to the corresponding region; and A computing system including a judgment module that judges a first partial region of the biological tissue image and a second partial region of the biological tissue image as representative lesion regions of the biological tissue image.

17. In the 13th paragraph, the computing system, A site information acquisition module that acquires information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images is collected, wherein the site is one of the plurality of regions in which the prostate is divided; For each of the plurality of regions, a region diagnosis result acquisition module that acquires a diagnosis result for the region determined based on the diagnosis result of a biological tissue image corresponding to a tissue sample collected from the region among the plurality of biological tissue images; and Further comprising a summary part generation module that generates a summary part for the above pathology diagnosis case, The above pathology diagnosis report further includes the above summary part, The summary part for the above pathological diagnosis case is: A summary table including diagnostic results for each of the above multiple zones; and A computing system including a prostate diagram of the pathological diagnosis case, wherein each of the plurality of regions is divided into regions corresponding to each of the regions, and each region is given a predetermined visual effect determined by the diagnosis result for the corresponding region.

18. In paragraph 17, The diagnostic results for the above area are: A computing system comprising at least some of the following: a diagnosis of the above area, a primary Gleason pattern and a secondary Gleason pattern of the above area, a length of a tissue sample taken from the above area, a length of a lesion included in a tissue sample taken from the above area, a proportion of the tissue sample taken from the above area, a number of tissue samples taken from the above area, and pathological features found in the tissue samples taken from the above area.

19. In paragraph 17, The summary part for the above pathological diagnosis case is: A computing system further comprising a diagnosis name representing the above pathology diagnosis case, the number of multiple tissue samples collected from the prostate of the patient, the number of tissue samples in which lesions are found among the multiple tissue samples collected from the prostate of the patient, and a diagnosis summary including the first Gleason pattern and the second Gleason pattern of the above pathology diagnosis case.

20. In paragraph 13, the computing system, A site information acquisition module that acquires information about a site from which a tissue sample corresponding to each of the plurality of biological tissue images is collected, wherein the site is one of the plurality of regions in which the prostate is divided; For each of the plurality of regions, a region diagnosis result generation module that obtains a diagnosis result for the region determined based on the diagnosis result of a biological tissue image corresponding to a tissue sample collected from the region among the plurality of biological tissue images; and Further comprising a summary part generation module that generates a summary part for the above pathology diagnosis case, The above pathology diagnosis report further includes the above summary part, The summary part for the above pathological diagnosis case is: Includes a summary table consisting of summary information for each of the above multiple zones, Summary information for the above area is: Includes diagnostic results for the above area and a bar diagram corresponding to each tissue sample collected from the above area, The above bar diagram, A computing system comprising a bar diagram comprising a portion corresponding to each non-lesion area and lesion area distributed in a corresponding tissue sample, wherein each portion included in the bar diagram has a length proportional to the length of the area corresponding to the portion, and a predetermined visual effect corresponding to the Gleason pattern of the area corresponding to the portion is applied.

21. In paragraph 13, the computing system, The computing system further includes a case representative lesion image generation module that generates a representative lesion image of the pathological diagnosis case, The above pathology diagnosis report further includes the representative lesion image, The representative lesion image generation module for the above case is A case lesion pattern acquisition module for acquiring the first Gleason pattern and the second Gleason pattern of the above pathological diagnosis case; For each of the plurality of biological tissue images, an area search module that searches for a first partial area, a second partial area, and a third partial area of ​​the biological tissue image; and Including a selection module for selecting a representative lesion image representing the pathological diagnosis case from among the first partial region, the second partial region, and the third partial region of each of the plurality of biological tissue images, The above area exploration module, A first partial region search module that searches for the first partial region among the partial regions of the biological tissue image, wherein the first Gleason pattern of the pathological diagnosis case is most frequently included in the pixel-unit diagnosis result corresponding to the region, wherein the partial region of the biological tissue image is a region that is a part of the biological tissue image and has a predefined shape and area; A second partial region search module that searches for the second partial region among the partial regions of the above biological tissue image, wherein the pixel unit diagnosis result corresponding to the region contains the most secondary Gleason patterns of the above pathological diagnosis case; A modification module that generates a modified pixel-by-pixel diagnosis result by removing the pixel-by-pixel diagnosis result corresponding to the first partial region from the pixel-by-pixel diagnosis result of the above biological tissue image; and Among the partial regions of the above biological tissue image, a third partial region search module is included that searches for the third partial region in which the second Gleason pattern of the pathological diagnosis case is most included in the modified pixel unit diagnosis result corresponding to the corresponding region. The above selection module is, A first representative lesion image selection module that selects a first representative lesion image that contains the largest number of first Gleason patterns of the pathological diagnosis case in pixel unit diagnosis corresponding to the corresponding region among the first partial region of each of the plurality of biological tissue images and the second partial region of each of the plurality of biological tissue images; and A computing system including a second representative lesion image selection module that selects a second representative lesion image that includes the largest number of second Gleason patterns of the pathological diagnosis case in the pixel unit diagnosis corresponding to the corresponding region among a first partial region of each of the plurality of biological tissue images, a second partial region of each of the remaining biological tissue images excluding the biological tissue image including the first representative lesion image among the plurality of biological tissue images, and a third partial region of the biological tissue image including the first representative lesion image.

Images