CN115497093A - Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier - Google Patents

Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier Download PDF

Info

Publication number
CN115497093A
CN115497093A CN202211143430.XA CN202211143430A CN115497093A CN 115497093 A CN115497093 A CN 115497093A CN 202211143430 A CN202211143430 A CN 202211143430A CN 115497093 A CN115497093 A CN 115497093A
Authority
CN
China
Prior art keywords
tumor
area
region
tumor infiltration
immune
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211143430.XA
Other languages
Chinese (zh)
Inventor
刘再毅
蔡茗
赵可
陈棋聪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong General Hospital
Original Assignee
Guangdong General Hospital
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong General Hospital filed Critical Guangdong General Hospital
Priority to CN202211143430.XA priority Critical patent/CN115497093A/en
Publication of CN115497093A publication Critical patent/CN115497093A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/698—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention discloses an immune grading method, a system and a storage medium for colorectal cancer IHC staining pattern tumor infiltration front, wherein the method comprises the following steps: obtaining an IHC staining pattern of the colorectal cancer; classifying the staining pattern by using a trained convolutional neural network classifier to obtain nine types of tissues which are respectively tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal gland, lymph aggregate, fat and background; combining nine tissue types into five types to fully automatically measure the tumor infiltration front and the tumor central area; performing cell segmentation and counting on the region to obtain the density of CD3 and CD8 positive cells, and then performing immune classification; according to the invention, the density of CD3 and CD8 positive cells in the tumor infiltration front and the tumor center area are quantified by automatically measuring the tumor infiltration front and the tumor center area, and the density of the CD3 and CD8 positive cells at the tumor infiltration front is evaluated as a prognostic factor, so that a pathologist is assisted to diagnose and treat a colorectal cancer patient.

Description

Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier
Technical Field
The invention belongs to the technical field of digital image processing, and particularly relates to an immune grading method, a system and a storage medium for colorectal cancer IHC staining pattern tumor infiltration front.
Background
Colorectal cancer is the third most common malignancy, with high morbidity and mortality. When malignant tumors become cancerous, changes in the tumor microenvironment can result. Tumor infiltrating lymphocytes are an important component of a solid tumor immune microenvironment and can be used for predicting the prognosis and treatment effect of solid tumors. CD3 and CD8 can be used as markers for colorectal cancer prognosis evaluation. If the relationship between the density of CD3 and CD8 positive cells in the tumor infiltration front region and the tumor center of the IHC staining pattern and the prognosis evaluation of the patient can be compared, the same effect as that of analyzing the whole section can be achieved by only analyzing the key region. The available variables with high prognostic value in the tumor infiltration front zone and the CD3 positive cells or the CD8 positive cells in the tumor center are selected, so that the conventional method for evaluating the CD3 and CD8 positive cells in all tissue areas in a staining map can be simplified, the workload of pathologists and the expenditure of patients can be greatly reduced, and the working efficiency is improved.
Disclosure of Invention
The invention mainly aims to overcome the defects of the prior art and provide an immune grading method, a system and a storage medium for a colorectal cancer IHC staining pattern tumor infiltration front.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for immuno-fractionation of tumor infiltration fronts in IHC staining patterns of colorectal cancer, comprising the steps of:
s1, automatically carrying out tissue classification on an IHC staining pattern of the colorectal cancer to obtain nine tissue types of a colorectal cancer canceration region, and combining the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor, normal, glandular, other and background regions;
s2, automatically segmenting tumor cells or dispersed cell clusters in a tumor infiltration front area, wherein the tumor infiltration front area is an area where a tumor area and a normal area are overlapped;
s3, automatically identifying a tumor infiltration front area and a tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section;
s4, segmenting CD3 and CD8 positive cells in the region, and determining the density of the CD3 and CD8 positive cells in the tumor infiltration front and the tumor central region to lay a foundation for the prognosis of the evaluation index;
s5, performing density immune grading on CD3 and CD8 positive cells in a tumor infiltration frontier area, and determining the immune grading of the colorectal cancer patient according to the density of the CD3 and CD8 positive cells in the tumor infiltration frontier area, wherein the immune grading is immune high grade and immune low grade.
As a preferred technical solution, the step S1 specifically includes:
s11, obtaining IHC staining images marked with tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal gland, lymph aggregate, fat and background and unmarked IHC staining images;
s12, training a classifier by using the labeled IHC staining image and the unlabeled IHC staining image, and obtaining segmentation images of nine tissue types by the classifier in a mode of classifying a sliding window;
s13, in order to determine a tumor infiltration frontier region, merging the segmentation maps of the nine tissue types to obtain five classifications of a tumor region, a normal region, a gland region, other regions and a background region; the tumor area comprises tumor necrosis, tumor stroma and tumor epithelial area, and mucus; the normal region includes fat and muscle; the glandular region comprises normal glands; the other regions include lymph aggregates; the background area includes a background.
As a preferred technical solution, the step S2 specifically includes:
s21, converting the IHC staining images of the five classifications into gray images from RGB images;
s22, filtering the gray level image by adopting two-dimensional Gaussian smoothing to reduce image noise and details;
s23, determining a global threshold by using an Otsu method, setting a minimum value 0 and a maximum value 255, and automatically searching an optimal threshold for calculation by using the Otsu method; carrying out binarization processing on the gray level image, dividing the image after binarization processing into a black background and a white interested area, calculating the area of each connected area according to the area of the pixel, arranging the connected areas in a descending order, and reserving the most significant area as the interested area;
s24, under the condition that the overall position and the shape of the black-white image after the binarization processing are kept unchanged, filling small cracks in the black-white image after the binarization processing by adopting expansion and corrosion form closing operation, effectively removing isolated small points, burrs and smoothing a boundary;
and S25, taking the overlapped area of the tumor area and the normal tissue area as a tumor infiltration front.
As a preferred technical solution, step S3 specifically includes:
performing dilation and erosion morphological closing operation on a tumor region and a normal tissue region, obtaining a local maximum value through dilation, firstly defining a convolution kernel B1 and having a separately defined reference point, performing convolution on the convolution kernel B1 and the image A1, calculating the maximum value of pixels in the coverage area of the convolution kernel B1, and assigning the maximum value to pixels specified by the reference point; performing convolution on the convolution kernel B2 and the image A2, calculating the minimum value of pixels in the coverage area of the convolution kernel B2, and assigning the minimum value to the pixels specified by the reference point; and finally, automatically determining the overlapped part of the two parts.
Preferably, before the division of the CD3 and CD8 positive cells in the region in step S4, the method further comprises the following steps:
will have undergone morphological closing operationThe post-image is a DAB channel image I after color deconvolution DAB Separating separately, filtering the image with two-dimensional Gaussian smooth kernel with standard deviation of sigma to obtain gray image I after Gaussian blur DAB2 Using a mask to obtain a gray image I with background region removed DAB3 。
As a preferred technical solution, the dividing of the CD3, CD8 positive cells in the region specifically comprises:
s41, using a stepping local threshold segmentation method to I DAB3 The cell nucleus in the image is segmented, the initial window width W is set as 77 pixels, and a preset contrast threshold value T is set d Is set to 15, for I DAB3 Performing binarization processing to obtain a binarization mask M1, and pairing I with M1 DAB2 Masking operation to obtain I DAB4 Morphological features are extracted for all connected domains within M1: pixel area and compactness; for I DAB4 Extracting gray features: mean and contrast; setting the first-time segmentation conditions as follows: a connected domain with the pixel area less than 200, or the contrast less than 0.04, or the gray mean value more than 200, then storing the connected domain with the pixel area less than 2000 and the compactness more than 0.93 as N1, and storing the connected domain which does not meet the conditions as M2, and carrying out next segmentation;
s42, second segmentation; if M2 is empty, the step is skipped, all pixel point values of M2 are set to be 0, if M2 is not empty, M2 is used for carrying out masking operation on IDAB2, and I is obtained DAB5 Adjusting the size W of the local window to 47 pixels, keeping the contrast threshold unchanged, and performing local threshold segmentation to obtain M3; dividing M3 by using a watershed algorithm with a foreground mark, setting a minimum value parameter H to be 3 to obtain M4, repeating the morphological characteristic dividing step, keeping a connected domain with the compactness of more than 0.95 and the area of less than 1000 pixel points as N2, and keeping a connected domain which does not meet the condition as M5;
and S43, performing third segmentation, if M5 is null, skipping the step, and setting the pixel point values of all the N3 pixels to be 0, and if M5 is not null, repeating the operation of the previous step on M5, wherein the difference is that: the size W of a local window of the bernsen segmentation is set to be 17 pixels, and the middle pole of the watershed algorithm with the foreground markerThe small value H is set to 1, the morphological operation is skipped to obtain N3, and the final obtained binary result of the immune cell is: n is a radical of DAB ＝N1|N2|N3。
As a preferred technical solution, in step S5, the positive cell density immune classification of the tumor infiltration front edge CD3 and CD8 specifically comprises:
s51, calculating the number of CD3 and CD8 positive cells in the tumor infiltration frontier area, and normalizing the result, D' = (D) i -D min )/(D max -D min ) Di is the normalized score of IHC staining pattern of a certain colorectal cancer patient, D max And D min Respectively obtaining the maximum score and the minimum score of the IHC staining graph of colorectal cancer patients in the cohort after normalization;
s52, when the prediction performance of the cell density variable is evaluated, the continuity of the variable is kept to avoid the influence of cut-off setting on the result, a Cox proportion risk model is established through the indexes of the survival state, age, sex and survival time OS of the patient to calculate the risk ratio of the prediction OS of each variable model, and simultaneously Pearson correlation analysis, multi-factor and single-factor logistic regression analysis are adopted to select the quantity characteristic P<0.05 data evaluation, comparison between two groups X 2 Checking, namely determining an optimal interception point by adopting a two-classification and three-classification method;
s53, immune classification; according to the optimal binary classification cut-off point determined in the step S52, the number of CD3 and CD8 positive cells in the tumor infiltration frontier area is set as CD CT High and CD CT Two Low groups, all patients in the cohort were immuno-graded, and group CD was assigned if the number of CD3, CD8 positive cells in the tumor infiltration frontal area in the IHC staining profile of patients was below the cut-off point CT Low, group CD if the number of CD3, CD8 positive cells in the tumor infiltration front area in the IHC stain profile of the patient is higher than the cut-off point CT -High; dividing the number of CD3 and CD8 positive cells in the front zone of tumor infiltration into CD according to the two optimal cut-off points of the three classifications determined in the step S52 CT -High、CD CT -Intermediate、CD CT Low three groups, if the number of CD3, CD8 positive cells in the tumor infiltration front zone in the IHC staining pattern of the patient is lower than the first cutThe breakpoint is the group CD CT Low, group CD if the number of CD3 positive cells in the tumor infiltration front area in the IHC stain profile of the patient is lower than the first cut-off point and lower than the second cut-off point CT Intermediate, group CD if the number of CD3, CD8 positive cells in the front zone of tumor infiltration in the IHC staining pattern of the patient is higher than the second cut-off point CT -High。
In a second aspect, the invention further provides an immune classification system of a tumor infiltration front of a colorectal cancer IHC staining pattern, which comprises a tissue classification module, a region segmentation module, a region identification module, a cell segmentation module and an immune classification module;
the tissue classification module is used for automatically performing tissue classification on the colorectal cancer IHC staining chart to obtain nine tissue types of colorectal cancer canceration areas, and combining the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor region, normal region, glandular region, other and background regions;
the region segmentation module is used for automatically segmenting tumor cells or dispersed cell clusters in a tumor infiltration frontier region, wherein the tumor infiltration frontier region is a region where a tumor region is overlapped with a normal region;
the area identification module is used for automatically identifying a tumor infiltration front area and a tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section;
the cell segmentation module is used for segmenting CD3 and CD8 positive cells in the region, determining the density of the CD3 and CD8 positive cells in the tumor infiltration front and the tumor center region, and laying a foundation for the prognosis of evaluation indexes;
the immune grading module is used for performing immune grading on the densities of the positive cells CD3 and CD8 at the tumor infiltration front edge, and determining the immune grading of the colorectal cancer patient according to the densities of the positive cells CD3 and CD8 at the tumor infiltration front edge, wherein the immune grading is immune high grade and immune low grade.
In a third aspect, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores computer program instructions executable by the at least one processor to cause the at least one processor to perform the method for immune classification of a tumor infiltration front of a colorectal cancer IHC stain profile.
In a fourth aspect, the present invention further provides a computer readable storage medium storing a program, wherein the program, when executed by a processor, implements the method for immune classification of tumor infiltration front of IHC stain map of colorectal cancer.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1) The invention can accurately divide the tumor infiltration frontier area and the tumor area, and provides a basis for subsequent manual analysis and automatic analysis.
2) According to the invention, the CD3 and CD8 related variables of the tumor infiltration front area and the tumor central area are transversely compared, so that the immune grading of the CD3 and CD8 positive cell density of the tumor infiltration front area can be determined to be a new prognostic factor independent of TNM staging.
3) The density of CD3 and CD8 positive cells in the tumor infiltration frontier region is combined with clinical data to carry out prognostic analysis on the disease-free survival period of a patient, and compared with the method without adding the prognostic factor provided by the invention, the C-index of the corresponding model is remarkably improved and is similar to the model result value of the combined analysis of the CD3 and CD8 positive cells. The survival of the patients can be predicted by the density of CD3 and CD8 positive cells in the tumor infiltration frontier area, wherein the CD with high density CT High is closely associated with longer survival, low density CD CT Low is closely related to shorter lifetime.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of an embodiment of the present invention of an immune classification method of colorectal cancer IHC staining pattern tumor infiltration front;
FIG. 2 is a block diagram of an immune grading system of IHC staining pattern tumor infiltration front of colorectal cancer according to an embodiment of the present invention.
Fig. 3 is a block diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
As shown in FIG. 1, the present embodiment relates to a method for immune grading tumor infiltration front of colorectal cancer IHC staining pattern, comprising the following steps:
s1, automatically classifying tissues by an IHC staining chart to obtain nine tissue types in the colorectal cancer canceration area, and subdividing and combining the nine tissue types into five categories on the basis.
Further, the nine classification and the five classification steps of the cancerous region are as follows:
s1.1, IHC staining patterns with labeling of tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphoid aggregates, fat, and background and unlabeled IHC staining patterns were obtained.
S1.2, training a classifier by using the labeled and unlabeled graphs, wherein the classifier obtains the segmentation graphs of the nine tissue types in a mode of classifying the sliding window.
S1.3, in order to determine a tumor infiltration frontier region, merging segmentation maps of the nine tissue types to obtain five classifications of a tumor region, a normal region, a gland region, other regions and a background region; the tumor area comprises tumor necrosis, tumor stroma and tumor epithelial area, and mucus; the normal region includes fat and muscle; the glandular region comprises normal glands; the other regions include lymph aggregates; the background area includes a background.
S2, automatically segmenting tumor cells or scattered cell clusters in a tumor infiltration front area, wherein the tumor infiltration front area is an area where a tumor area and a normal area are overlapped.
Further, the specific steps of automatically identifying the tumor infiltration front area and the tumor center are as follows:
and S2.1, converting the five-classification dyeing images into gray images from RGB images.
And S2.2, filtering the gray level image by adopting two-dimensional Gaussian smoothing with the standard deviation of 10 so as to reduce image noise and details.
And S2.3, determining a global threshold value by using an Otsu method, carrying out binarization on the image obtained in the previous step, and dividing the image into a black background and a white interested area. And calculating the area of each connected domain according to the area of the pixel, arranging the connected domains, and reserving the most remarkable region as an interested region.
More specifically, a minimum value 0 and a maximum value 255 are set, and the Otsu method automatically searches for an optimal threshold value for calculation; and carrying out binarization processing on the gray level image, dividing the image after binarization processing into a black background and a white interested area, calculating the area of each connected area according to the area of the pixel, arranging the connected areas in a descending order, and reserving the most significant area as the interested area.
And S2.4, under the condition that the overall position and shape of the black-white image after the binarization processing are kept unchanged, filling small cracks in the black-white image after the binarization processing by adopting expansion and corrosion form closing operation, effectively removing isolated small points and burrs, and smoothing the boundary.
S2.5, taking the overlapped area of the tumor area and the normal tissue area as the tumor infiltration front.
S3, automatically identifying the tumor infiltration front area and the tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section, wherein the specific corresponding positions are as follows:
s31, performing dilation and erosion morphological closing operation on a tumor region and a normal tissue region, and obtaining a local maximum value through dilation, firstly defining a convolution kernel B and having a separately defined reference point. And (4) convolving the kernel B with the image A, calculating the maximum value of the pixel of the coverage area of the kernel B, and assigning the maximum value to the pixel specified by the reference point. The calculation formula is as follows:
Figure BDA0003854644330000091
and S32, performing corrosion operation, defining a convolution kernel B and having a separately defined reference point. And (4) convolving the kernel B with the image A, calculating the minimum value of the pixels in the coverage area of the kernel B, and assigning the minimum value to the pixels specified by the reference points. The calculation formula is as follows:
Figure BDA0003854644330000101
and S33, automatically determining the overlapped part of the two parts, wherein the width of the tumor infiltration front is 500 μm in the embodiment.
S4, segmenting CD3 and CD8 positive cells in the region; and determining the density of CD3 and CD8 positive cells at the tumor infiltration front and the tumor center, and laying a foundation for the prognosis of the evaluation index.
The pretreatment before the cell nucleus segmentation comprises the following specific steps:
s4.1, performing color deconvolution on the image to obtain a DAB channel image I DAB The images were separated individually, filtered using a two-dimensional gaussian smoothing kernel with standard deviation σ (σ = 3), and a gray image I after gaussian blurring was obtained DAB2 . Using a mask to obtain a gray image I with a background region removed DAB3 。
The specific steps of dividing the CD3 and CD8 positive cells at the tumor infiltration front and the tumor central area are as follows:
s4.2, using a stepping local threshold segmentation method to I DAB3 The nuclei in the image are segmented. Initial window width W was set to 77 pixels, preset contrast threshold T d Is set to 15, for I DAB3 After execution of the bernsen algorithm, a binary mask M1 is obtained, and M1 is used for I DAB2 Masking operation to obtain I DAB4 (ii) a Morphological features were extracted for all connected domains within M1: pixel area and compactness; for I DAB4 Extracting gray features: mean and contrast; the setting conditions are as follows: connected domains with pixel area less than 200, or contrast less than 0.04, or gray scale mean greater than 200; then, the connected domain with the pixel area less than 2000 and the compactness greater than 0.93 is saved as N1. And (4) storing the connected domain which does not meet the condition as M2, and carrying out next segmentation.
S4.3, second segmentation; if M2 is empty (i.e., all pixels are background), the step is skipped and all pixel point values of M2 are set to 0. If M2 is not empty, using M2 to carry out masking operation on IDAB2 to obtain I DAB5 . The size W of the local window is adjusted to 47 pixels, the contrast threshold is kept unchanged, and local threshold segmentation is performed to obtain M3. And (4) segmenting the M3 by using a watershed algorithm with a foreground mark, and setting a minimum parameter H to be 3 to obtain M4. And repeating the morphological characteristic segmentation step, reserving a connected domain with the compactness of more than 0.95 and the area of less than 1000 pixel points, and storing the connected domain as N2. And storing the connected domain which does not meet the condition as M5.
And S4.4, third segmentation. If M5 is empty, the step is skipped,and sets all pixel point values of N3 to 0. If M5 is not empty, repeat the operation of the previous step for M5, except that: setting the size W of a local window of the bernsen segmentation as 17 pixels, setting a minimum value H in a watershed algorithm with a foreground marker as 1, skipping morphological operation to obtain N3, and finally obtaining a binary result of the immune cell as follows: n is a radical of DAB ＝N1|N2|N3。
S5, performing density immune grading on CD3 positive cells in a tumor infiltration frontier region; determining the immune grading of the colorectal cancer patient according to the density of CD3 positive cells in the tumor infiltration frontier region, wherein the immune grading is immune high grade and immune low grade.
Further, the method for CD3 positive cell density immune grading of the tumor infiltration frontal area is the same as the method for CD8 positive cell density immune grading, and the following description takes CD3 positive cell density immune grading of the tumor infiltration frontal area as an example, and the specific method is as follows:
s5.1, calculating the number of CD3 positive cells in the tumor infiltration frontier area, and normalizing the result, D' = (D) i -D min )/(D max -D min ) Di is the normalized score of IHC staining pattern of a certain colorectal cancer patient, D max And D min The IHC staining patterns of the colorectal cancer patients in the cohort were normalized to score the maximum and the minimum, respectively.
S5.2, when the prediction performance of the cell density variable is evaluated, the continuity of the variable is maintained, so that the result is prevented from being influenced by the cut-off setting. Establishing a Cox proportion risk model according to the indexes of the survival state, age, sex, survival period OS and the like of the patient to calculate the risk ratio of the OS predicted by each variable model, and selecting a quantity characteristic P by Pearson correlation analysis, multi-factor and single-factor logistic regression analysis<0.05 data evaluation. Comparison between two groups uses X 2 And (4) checking, and determining the optimal interception point by adopting a two-classification and three-classification method.
S5.3, dividing the number of CD3 positive cells in the front zone of tumor infiltration into CD3 according to the two-classification optimal interception points determined in S5.2 CT High and CD3 CT Two Low groups, with an immunological grading of all patients in the cohort, if the patient is infected with IHCThe number of CD3 positive cells in the tumor infiltration frontier region in the color chart is lower than the cut-off point, and the result is the group CD3 CT Low, group CD3 if the number of CD3 positive cells in the tumor infiltration front in the IHC stain profile of the patient is higher than the cut-off point CT -High. Dividing the number of CD3 positive cells in the tumor infiltration front region into CD3 according to the two optimal truncation points of the three classifications determined in S5.2 CT -High、CD3 CT -Intermediate、CD3 CT -three groups Low. Grouping CD3 if the number of CD3 positive cells in the tumor infiltration frontal area in the IHC staining profile of the patient is lower than the first cut-off point CT Low, group CD3 if the number of CD3 positive cells in the tumor infiltration frontal area in the IHC stain profile of the patient is lower than the first cut-off point and lower than the second cut-off point CT Intermediate, group CD3 if the number of CD 3-positive cells in the tumor infiltration front zone in the IHC stain profile of the patient is higher than the second cut-off point CT -High。
It is understood that the method for the CD8 positive cell density immune fractionation is the same as that for the CD3 positive cell density immune fractionation described above, and thus, the detailed description thereof is omitted.
The operation is repeated on the verification set of the sixth subsidiary hospital of the Zhongshan university, and the obtained result is consistent with the result of the training set.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present invention is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present invention.
Based on the same idea as the immune classification method of tumor infiltration front of colorectal cancer IHC stain map in the above embodiment, the present invention also provides an immune classification system of tumor infiltration front of colorectal cancer IHC stain map, which can be used to perform the above immune classification method of tumor infiltration front of colorectal cancer IHC stain map. For convenience of illustration, the structural diagram of the embodiment of the immune grading system of the tumor infiltration front of colorectal cancer IHC staining pattern only shows the part relevant to the embodiment of the present invention, and those skilled in the art will understand that the illustrated structure does not limit the device, and may include more or less components than those illustrated, or combine some components, or arrange different components.
Referring to fig. 2, in another embodiment of the present application, an immune classification system 100 for tumor infiltration front of IHC stain map of colorectal cancer is provided, which includes a tissue classification module 101, a region segmentation module 102, a region identification module 103, a cell segmentation module 104, and an immune classification module 105;
the tissue classification module 101 is configured to automatically perform tissue classification on the IHC stain map of colorectal cancer to obtain nine tissue types in a cancerous region of colorectal cancer, and combine the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor, normal, glandular, other and background regions;
the region segmentation module 102 is configured to segment tumor cells or dispersed cell clusters in a tumor infiltration front region automatically, where the tumor infiltration front region is a region where a tumor region overlaps with a normal region;
the region identification module 103 is configured to automatically identify a tumor infiltration front region and a tumor center region, and obtain specific corresponding positions of the tumor infiltration front region and the tumor center region on the digital pathological section;
the cell segmentation module 104 is used for segmenting CD3 and CD8 positive cells in the region, determining the density of the CD3 and CD8 positive cells at the tumor infiltration front and the tumor central region, and laying a foundation for the prognosis of evaluation indexes;
the immune grading module 105 is used for performing immune grading on the densities of the CD3 and CD8 positive cells at the tumor infiltration front edge, and determining the immune grading of the colorectal cancer patient according to the densities of the CD3 and CD8 positive cells at the tumor infiltration front edge, wherein the immune grading is immune high grade and immune low grade.
It should be noted that the immune classification system of the tumor infiltration front of the colorectal cancer IHC staining pattern of the present invention corresponds to the immune classification method of the tumor infiltration front of the colorectal cancer IHC staining pattern of the present invention one by one, and the technical features and the beneficial effects thereof described in the above embodiments of the immune classification method of the tumor infiltration front of the colorectal cancer IHC staining pattern are all applicable to the embodiments of the immune classification system of the tumor infiltration front of the colorectal cancer IHC staining pattern, and specific contents thereof can be referred to the description in the embodiments of the method of the present invention, and are not repeated herein, which is hereby stated.
In addition, in the embodiment of the immune classification system for a tumor infiltration front of colorectal cancer IHC staining pattern of the above embodiment, the logical division of the program modules is only an example, and in practical applications, the above function assignment may be performed by different program modules according to needs, for example, due to the configuration requirements of corresponding hardware or the convenience of implementation of software, that is, the internal structure of the immune classification system for a tumor infiltration front of colorectal cancer IHC staining pattern is divided into different program modules to perform all or part of the above described functions.
Referring to fig. 3, in an embodiment, an electronic device 200 for an immune classification method of a tumor infiltration front of a colorectal cancer IHC stain map is provided, the electronic device may include a first processor 201, a first memory 202 and a bus, and may further include a computer program, such as an immune classification program 203 of a tumor infiltration front of a colorectal cancer IHC stain map, stored in the first memory 202 and executable on the first processor 201.
The first memory 202 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The first memory 202 may in some embodiments be an internal storage unit of the electronic device 200, such as a removable hard disk of the electronic device 200. The first memory 202 may also be an external storage device of the electronic device 200 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 200. Further, the first memory 202 may also include both an internal storage unit and an external storage device of the electronic device 200. The first memory 202 can be used for storing not only the application software installed in the electronic device 200 and various data, such as the code of the immune classification program 203 for the tumor infiltration front of the IHC staining pattern of colorectal cancer, etc., but also temporarily storing the data that has been output or will be output.
The first processor 201 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The first processor 201 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions of the electronic device 200 and processes data by running or executing programs or modules stored in the first memory 202 and calling data stored in the first memory 202.
Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the configuration shown in fig. 3 is not limiting to the electronic device 200, and may include fewer or more components than shown, or some components may be combined, or a different arrangement of components.
The first memory 202 of the electronic device 200 stores an immune grading program 203 of a tumor infiltration front of colorectal cancer IHC staining pattern, which is a combination of instructions that, when executed in the first processor 201, can implement:
s1, automatically carrying out tissue classification on an IHC staining pattern of the colorectal cancer to obtain nine tissue types of a colorectal cancer canceration region, and combining the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor region, normal region, glandular region, other and background regions;
s2, automatically segmenting tumor cells or dispersed cell clusters in a tumor infiltration frontier area, wherein the tumor infiltration frontier area is an area where a tumor area and a normal area are overlapped;
s3, automatically identifying a tumor infiltration front area and a tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section;
s4, segmenting CD3 and CD8 positive cells in the region, and determining the density of the CD3 and CD8 positive cells in the tumor infiltration front and the tumor central region to lay a foundation for the prognosis of the evaluation index;
s5, performing density immune grading on CD3 and CD8 positive cells in a tumor infiltration frontier area, and determining the immune grading of the colorectal cancer patient according to the density of the CD3 and CD8 positive cells in the tumor infiltration frontier area, wherein the immune grading is immune high grade and immune low grade.
Further, the modules/units integrated with the electronic device 200, if implemented in the form of software functional units and sold or used as independent products, may be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM).
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (10)

1. An immune grading method of colorectal cancer IHC staining pattern tumor infiltration frontier is characterized by comprising the following steps:
s1, automatically carrying out tissue classification on an IHC staining map of the colorectal cancer to obtain nine tissue types in a cancerous area of the colorectal cancer, and combining the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor, normal, glandular, other and background regions;
s2, automatically segmenting tumor cells or dispersed cell clusters in a tumor infiltration frontier area, wherein the tumor infiltration frontier area is an area where a tumor area and a normal area are overlapped;
s3, automatically identifying a tumor infiltration front area and a tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section;
s4, segmenting CD3 and CD8 positive cells in the region, and determining the density of the CD3 and CD8 positive cells in the tumor infiltration front and the tumor central region to lay a foundation for the prognosis of the evaluation index;
s5, performing density immune grading on CD3 and CD8 positive cells in a tumor infiltration frontier area, and determining the immune grading of the colorectal cancer patient according to the density of the CD3 and CD8 positive cells in the tumor infiltration frontier area, wherein the immune grading is immune high grade and immune low grade.
2. The method for the immunological classification of the tumor infiltration front of colorectal cancer IHC staining pattern according to claim 1, wherein the step S1 is specifically:
s11, obtaining IHC staining images marked with tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal gland, lymph aggregate, fat and background and unmarked IHC staining images;
s12, training a classifier by using the labeled IHC staining image and the unlabeled IHC staining image, and obtaining segmentation images of nine tissue types by the classifier in a mode of classifying a sliding window;
s13, in order to determine a tumor infiltration frontier region, merging the segmentation maps of the nine tissue types to obtain five classifications of a tumor region, a normal region, a gland region, other regions and a background region; the tumor region comprises tumor necrosis, tumor stroma, tumor epithelial region and mucus; the normal region includes fat and muscle; the glandular region comprises normal glands; the other regions include lymph aggregates; the background region includes a background.
3. The method of claim 1, wherein step S2 is specifically performed by using an IHC staining map for tumor infiltration frontier in immune classification of colorectal cancer:
s21, converting the IHC dyeing images of the five classifications into gray images from RGB images;
s22, filtering the gray level image by adopting two-dimensional Gaussian smoothing to reduce image noise and details;
s23, determining a global threshold by using an Otsu method, setting a minimum value 0 and a maximum value 255, and automatically searching an optimal threshold for calculation by using the Otsu method; carrying out binarization processing on the gray level image, dividing the image after binarization processing into a black background and a white interested area, calculating the area of each connected area according to the area of the pixel, arranging the connected areas in a descending order, and reserving the most significant area as the interested area;
s24, under the condition that the overall position and the shape of the black-white image after the binarization processing are kept unchanged, filling small cracks in the black-white image after the binarization processing by adopting expansion and corrosion form closing operation, effectively removing isolated small points and burrs, and smoothing the boundary;
and S25, taking the overlapped area of the tumor area and the normal tissue area as a tumor infiltration front.
4. The method for the immunological classification of the tumor infiltration front of colorectal cancer IHC staining pattern according to claim 3, wherein the step S3 is specifically as follows:
performing dilation and erosion morphological closing operation on a tumor region and a normal tissue region, obtaining a local maximum value through dilation, firstly defining a convolution kernel B1 and having a separately defined reference point, performing convolution on the convolution kernel B1 and the image A1, calculating the maximum value of pixels in the coverage area of the convolution kernel B1, and assigning the maximum value to pixels specified by the reference point; convolving the convolution kernel B2 with the image A2, calculating the pixel minimum value of the coverage area of the convolution kernel B2, and assigning the minimum value to a pixel specified by the reference point; and finally, automatically determining the overlapped part of the two parts.
5. The method for immuno-staging of the tumor infiltration front of colorectal cancer IHC staining pattern according to claim 1, wherein before the segmentation of CD3, CD8 positive cells in the region of step S4, the method further comprises the following steps:
will be subjected to a morphological closing operationOf the DAB channel image I subjected to color deconvolution DAB Separating separately, filtering the image with two-dimensional Gaussian smooth kernel with standard deviation of sigma to obtain gray image I after Gaussian blur DAB2 Using a mask to obtain a gray image I with background region removed DAB3 。
6. The method for the immunological grading of the tumor infiltration front of colorectal cancer IHC staining pattern according to claim 1, wherein the segmentation of CD3 and CD8 positive cells in the region is specifically as follows:
s41, using a stepping local threshold segmentation method to I DAB3 The cell nucleus in the image is segmented, the initial window width W is set as 77 pixels, and a preset contrast threshold value T is set d Is set as 15, for I DAB3 Performing binarization processing to obtain a binarization mask M1, and pairing I with M1 DAB2 Mask operation to obtain I DAB4 Morphological features are extracted for all connected domains within M1: pixel area and compactness; for I DAB4 Extracting gray features: mean and contrast; setting the first-time segmentation conditions as follows: a connected domain with the pixel area smaller than 200, or the contrast smaller than 0.04, or the gray average larger than 200, then, storing the connected domain with the pixel area smaller than 2000 and the compactness larger than 0.93 as N1, and storing the connected domain which does not meet the conditions as M2, and carrying out next segmentation;
s42, second segmentation; if M2 is empty, skipping the step, and setting all pixel point values of M2 to 0, if M2 is not empty, using M2 to perform masking operation on IDAB2 to obtain I DAB5 Adjusting the size W of the local window to 47 pixels, keeping the contrast threshold unchanged, and performing local threshold segmentation to obtain M3; dividing M3 by using a watershed algorithm with a foreground mark, setting a minimum value parameter H to be 3 to obtain M4, repeating the morphological characteristic dividing step, keeping a connected domain with the compactness of more than 0.95 and the area of less than 1000 pixel points as N2, and keeping a connected domain which does not meet the condition as M5;
s43, third time of segmentation, if M5 is empty, the step is skipped, all pixel point values of N3 are set to be 0, and if M5 is not empty, the last step is repeated for M5The difference lies in that: setting the size W of a local window of the bernsen segmentation as 17 pixels, setting a minimum value H in a watershed algorithm with a foreground marker as 1, skipping morphological operation to obtain N3, and finally obtaining a binary result of the immune cell as follows: n is a radical of DAB ＝N1|N2|N3。
7. The method for immuno-fractionation of tumor infiltration front according to claim 6, wherein in step S5, the tumor infiltration front is immuno-fractionated by CD3 and CD8 positive cell density, specifically:
s51, calculating the number of CD3 and CD8 positive cells in the tumor infiltration frontier area, and normalizing the result, wherein D' = (D) i -D min )/(D max -D min ) Di is the normalized score of IHC staining pattern of a certain colorectal cancer patient, D max And D min Respectively obtaining the maximum score and the minimum score of the IHC staining graph of colorectal cancer patients in the cohort after normalization;
s52, when the prediction performance of the cell density variable is evaluated, the continuity of the variable is kept to avoid the influence of cut-off setting on the result, a Cox proportion risk model is established through the indexes of the survival state, age, sex and survival time OS of the patient to calculate the risk ratio of the prediction OS of each variable model, and simultaneously Pearson correlation analysis, multi-factor and single-factor logistic regression analysis are adopted to select the quantity characteristic P<0.05 data evaluation, comparison between two groups X 2 Checking, namely determining an optimal interception point by adopting a two-classification and three-classification method;
s53, immune grading; according to the optimal binary classification cut-off point determined in the step S52, the number of CD3 and CD8 positive cells in the tumor infiltration frontier area is set as CD CT High and CD CT Two Low groups, all patients in the cohort were immuno-graded, and group CD was assigned if the number of CD3, CD8 positive cells in the tumor infiltration frontal area in the IHC staining profile of patients was below the cut-off point CT Low, group CD if the number of CD3, CD8 positive cells in the tumor infiltration front area in the IHC stain profile of the patient is higher than the cut-off point CT -High; two best according to the three classifications determined in step S52Cutting off the point, dividing the number of CD3 and CD8 positive cells in the tumor infiltration frontier area into CD CT -High、CD CT -Intermediate、CD CT Low three groups, group CD if the number of CD3, CD8 positive cells in the tumor infiltration front area in the IHC staining profile of the patient is lower than the first cut-off point CT Low, group CD if the number of CD3 positive cells in the tumor infiltration front area in the IHC stain profile of the patient is lower than the first cut-off point and lower than the second cut-off point CT Intermediate, group CD if the number of CD3, CD8 positive cells in the tumor infiltration front zone in the IHC stain profile of the patient is higher than the second cut-off point CT -High。
8. The immune classification system of the colorectal cancer IHC staining pattern tumor infiltration front is characterized by comprising a tissue classification module, a region segmentation module, a region identification module, a cell segmentation module and an immune classification module;
the tissue classification module is used for automatically performing tissue classification on the colorectal cancer IHC staining chart to obtain nine tissue types of colorectal cancer canceration areas, and combining the nine tissue types into five classifications; the nine tissue types include tumor epithelium, tumor stroma, tumor necrosis, mucus, muscle, normal glands, lymphatic aggregates, fat, and background; the five classifications include tumor region, normal region, glandular region, other and background regions;
the region segmentation module is used for automatically segmenting tumor cells or scattered cell clusters in a tumor infiltration front region, wherein the tumor infiltration front region is a region where a tumor region is overlapped with a normal region;
the area identification module is used for automatically identifying a tumor infiltration front area and a tumor center area to obtain specific corresponding positions of the tumor infiltration front area and the tumor center area on the digital pathological section;
the cell segmentation module is used for segmenting CD3 and CD8 positive cells in the region, determining the density of the CD3 and CD8 positive cells in the tumor infiltration front and the tumor center region, and laying a foundation for the prognosis of evaluation indexes;
the immune grading module is used for performing immune grading on the densities of the positive cells CD3 and CD8 at the tumor infiltration front edge, and determining the immune grading of the colorectal cancer patient according to the densities of the positive cells CD3 and CD8 at the tumor infiltration front edge, wherein the immune grading is immune high grade and immune low grade.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores computer program instructions executable by the at least one processor to cause the at least one processor to perform the method of immune grading of a colorectal cancer IHC stain profile tumor infiltration front according to any of claims 1-7.
10. A computer-readable storage medium storing a program which, when executed by a processor, implements the method for immunopotentiation of IHC staining pattern tumor infiltration front of colorectal cancer according to any one of claims 1-7.
CN202211143430.XA 2022-09-20 2022-09-20 Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier Pending CN115497093A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211143430.XA CN115497093A (en) 2022-09-20 2022-09-20 Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211143430.XA CN115497093A (en) 2022-09-20 2022-09-20 Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier

Publications (1)

Publication Number Publication Date
CN115497093A true CN115497093A (en) 2022-12-20

Family

ID=84471176

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211143430.XA Pending CN115497093A (en) 2022-09-20 2022-09-20 Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier

Country Status (1)

Country Link
CN (1) CN115497093A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116258676A (en) * 2022-12-30 2023-06-13 广州市第一人民医院（广州消化疾病中心、广州医科大学附属市一人民医院、华南理工大学附属第二医院） Cell density quantification method and system for colorectal cancer IHC pathological image
CN116646088A (en) * 2023-07-27 2023-08-25 广东省人民医院 Prediction method, prediction device, prediction equipment and prediction medium
CN117252893A (en) * 2023-11-17 2023-12-19 科普云医疗软件(深圳)有限公司 Segmentation processing method for breast cancer pathological image

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116258676A (en) * 2022-12-30 2023-06-13 广州市第一人民医院（广州消化疾病中心、广州医科大学附属市一人民医院、华南理工大学附属第二医院） Cell density quantification method and system for colorectal cancer IHC pathological image
CN116258676B (en) * 2022-12-30 2024-03-19 广州市第一人民医院（广州消化疾病中心、广州医科大学附属市一人民医院、华南理工大学附属第二医院） Cell density quantification method and system for colorectal cancer IHC pathological image
CN116646088A (en) * 2023-07-27 2023-08-25 广东省人民医院 Prediction method, prediction device, prediction equipment and prediction medium
CN116646088B (en) * 2023-07-27 2023-12-01 广东省人民医院 Prediction method, prediction device, prediction equipment and prediction medium
CN117252893A (en) * 2023-11-17 2023-12-19 科普云医疗软件(深圳)有限公司 Segmentation processing method for breast cancer pathological image
CN117252893B (en) * 2023-11-17 2024-02-23 科普云医疗软件(深圳)有限公司 Segmentation processing method for breast cancer pathological image

Similar Documents

Publication Publication Date Title
CN115497093A (en) Immune grading method, system and storage medium for colorectal cancer IHC staining pattern tumor infiltration frontier
Salvi et al. Multi-tissue and multi-scale approach for nuclei segmentation in H&E stained images
US8712142B2 (en) Method and apparatus for analysis of histopathology images and its application to cancer diagnosis and grading
Gertych et al. Machine learning approaches to analyze histological images of tissues from radical prostatectomies
Alirezazadeh et al. Representation learning-based unsupervised domain adaptation for classification of breast cancer histopathology images
Mi et al. Deep learning-based multi-class classification of breast digital pathology images
CN111402267B (en) Segmentation method, device and terminal of epithelial cell nuclei in prostate cancer pathological image
Liu et al. Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images
CA3010836A1 (en) Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions
CN113591919B (en) Analysis method and system for prognosis of early hepatocellular carcinoma postoperative recurrence based on AI
Alsheh Ali et al. Association of microcalcification clusters with short-term invasive breast cancer risk and breast cancer risk factors
US20220058801A1 (en) Predicting DCIS Recurrence Risk Using a Machine Learning-Based High-Content Image Analysis Approach
Li et al. Predicting underestimation of ductal carcinoma in situ: a comparison between radiomics and conventional approaches
CN114841947A (en) Method and device for multi-scale feature extraction and prognosis analysis of H &amp; E staining pathological image tumor region
CN116403094A (en) Embedded image recognition method and system
KR102373985B1 (en) Classification method of prostate cancer using support vector machine
KR20200135839A (en) Method for determining bone marrow leukocyte location by chroma cluster
CN113011257A (en) Breast cancer immunohistochemical artificial intelligence interpretation method
Ali et al. Breast tissue organisation and its association with breast cancer risk
CN114511523B (en) Gastric cancer molecular subtype classification method and device based on self-supervision learning
Roszkowiak et al. Clustered nuclei splitting based on recurrent distance transform in digital pathology images
CN116363647A (en) Lung cancer pathological tissue typing system based on deep semantic segmentation network
CN112419253B (en) Digital pathology image analysis method, system, equipment and storage medium
Bag et al. Computational analysis of p63+ nuclei distribution pattern by graph theoretic approach in an oral pre-cancer (sub-mucous fibrosis)
CN112508860B (en) Artificial intelligence interpretation method and system for positive check of immunohistochemical image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination