Colorectal cancer immunotherapy effect prediction system

Abstract

The present invention discloses a colorectal cancer immunotherapy effect prediction system, wherein the processor in the system calls the executable program code stored in the memory to execute a colorectal cancer treatment effect prediction method, the method comprising: obtaining a biological tissue digital image of a colorectal cancer patient; predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on a classifier algorithm model; determining multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to the tissue type parameters and the cell type parameters; calculating the treatment effect score corresponding to the colorectal cancer patient according to the multiple cell feature parameters and the preset parameter scoring rules. It can be seen that the present invention can effectively improve the accuracy and efficiency of colorectal cancer treatment effect prediction, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a colorectal cancer immunotherapy effect prediction system. Background Art

[0002] Colorectal cancer is the most common malignant digestive system tumor. Immunotherapy has become an important means of colorectal cancer treatment. In many guidelines, including the National Comprehensive Cancer Network (NCCN) guidelines and the Chinese Society of Clinical Oncology (CSCO) guidelines, immunotherapy represented by pembrolizumab occupies the first-line treatment position for patients with dMMR / MSI-H colorectal cancer. In clinical practice, MMR status is often evaluated by immunohistochemistry of pathological tissues, MSI (microsatellite instability) status is evaluated by PCR technology, or MSI status and MMR (MisMatch Repair) gene mutations are evaluated by second-generation sequencing technology to guide immunotherapy. However, the above detection methods are expensive, time-consuming, and technically demanding, making them difficult to carry out in primary hospitals. As an emerging technology, pathogenomics has been widely used in clinically relevant efficacy prediction. Recently, many studies have confirmed that pathogenomics features such as lymphocyte density and spatial distribution identified by pathogenomics are associated with the efficacy of immunotherapy. However, most of these studies were conducted on tumors such as lung cancer and melanoma, and were not combined with image analysis methods. As a unique digestive system tumor, colorectal cancer has significant differences in pathological characteristics from other tumors. Therefore, it is still necessary to construct a treatment effect evaluation method unique to colorectal cancer. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a colorectal cancer immunotherapy effect prediction system, which can effectively improve the accuracy and efficiency of colorectal cancer treatment effect prediction, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for predicting the treatment effect of colorectal cancer, the method comprising:

[0005] Acquire digital images of biological tissues of patients with colorectal cancer;

[0006] Based on the classifier algorithm model, predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image;

[0007] Determine a plurality of cell characteristic parameters corresponding to the biological tissue digital image according to a plurality of cell characteristic calculation rules corresponding to the tissue type parameter and the cell type parameter;

[0008] According to the multiple cell characteristic parameters and the preset parameter scoring rules, the treatment effect score corresponding to the colorectal cancer patient is calculated; the treatment effect score is used to predict the treatment effect of the colorectal cancer patient receiving immunotherapy.

[0009] As an optional embodiment, in the first aspect of the present invention, the predicting of tissue type parameters and cell type parameters corresponding to the digital image of biological tissue based on the classifier algorithm model includes:

[0010] Inputting the biological tissue digital image into a trained tissue region recognition algorithm model to obtain a plurality of tissue regions corresponding to the biological tissue digital image and a tissue type corresponding to each of the tissue regions;

[0011] The biological tissue digital image is input into a trained cell recognition algorithm model to obtain a plurality of cell regions corresponding to the biological tissue digital image and a cell type corresponding to each of the cell regions.

[0012] As an optional embodiment, in the first aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter comprises:

[0013] Calculating the number of regions of all the tissue regions whose tissue type is a mucus component type;

[0014] The ratio between the area number and the total area number corresponding to all the tissue areas is calculated to obtain a mucus area ratio parameter.

[0015] As an optional embodiment, in the first aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter comprises:

[0016] Screening out all tissue regions whose tissue types are tumor types to obtain multiple tumor tissue regions;

[0017] Calculating the minimum circumscribed polygons of the multiple tumor tissue regions to obtain a comprehensive tumor region;

[0018] The tumor comprehensive area is divided into a plurality of sub-areas, and for each of the sub-areas,

[0019] Calculating the total number of cell regions in the subregion where the cell type belongs to lymphocytes to obtain the number of lymphocytes;

[0020] Calculate the total number of cell regions in the subregion where the cell type belongs to tumor cells to obtain the number of tumor cells;

[0021] Calculating the ratio of the number of lymphocytes to the first total number of cells to obtain the lymphocyte ratio; the first total number of cells is the sum of the number of lymphocytes and the number of tumor cells;

[0022] Calculating the ratio of the number of tumor cells to the total number of cells to obtain the tumor cell ratio;

[0023] According to the lymphocyte proportions and the tumor cell proportions corresponding to all the sub-regions, based on the co-localization coefficient algorithm, the lymphocyte abundance parameter corresponding to the tumor comprehensive region is calculated.

[0024] As an optional embodiment, in the first aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0025] Calculate the total number of cell regions in each of the subregions where the cell type belongs to plasma cells to obtain the number of plasma cells;

[0026] Calculating the ratio of the number of plasma cells in each of the sub-regions to the second total number of cells to obtain the proportion of plasma cells in each of the sub-regions; the second total number of cells is the sum of the number of plasma cells and the number of tumor cells;

[0027] According to the plasma cell proportions and the tumor cell proportions corresponding to all the sub-regions, based on the co-localization coefficient algorithm, the plasma cell co-localization parameters corresponding to the tumor comprehensive region are calculated.

[0028] As an optional embodiment, in the first aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0029] Calculating the total number of cell regions in each of the sub-regions where the cell type belongs to neutrophils to obtain the number of neutrophils;

[0030] Calculating the ratio of the number of neutrophils in each of the sub-regions to the third total number of cells to obtain the proportion of neutrophils in each of the sub-regions; the third total number of cells is the sum of the number of neutrophils and the number of tumor cells;

[0031] According to the neutrophil proportions and the tumor cell proportions corresponding to all the sub-areas, based on the colocalization coefficient algorithm, the neutrophil colocalization parameter corresponding to the tumor comprehensive area is calculated.

[0032] As an optional embodiment, in the first aspect of the present invention, the calculating the treatment effect score corresponding to the colorectal cancer patient according to the multiple cell characteristic parameters and the preset parameter scoring rules includes:

[0033] Calculating a first effect score corresponding to the mucus area ratio parameter; the first effect score is inversely proportional to the mucus area ratio parameter;

[0034] respectively calculating the second effect scores corresponding to the lymphocyte abundance parameter, the plasma cell colocalization parameter, and the neutrophil colocalization parameter; the second effect score is proportional to the lymphocyte abundance parameter, the plasma cell colocalization parameter, or the neutrophil colocalization parameter;

[0035] The sum of the first effect score and all the second effect scores is calculated to obtain the treatment effect score corresponding to the colorectal cancer patient.

[0036] As an optional embodiment, in the first aspect of the present invention, the calculating the sum of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient includes:

[0037] Calculate the weighted sum average of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient; wherein the weighted calculation weight of the first effect score is proportional to the total area of ​​all tissue regions whose tissue type is the mucus component type, and the weighted calculation weight of the second effect score is proportional to the total area of ​​the cell region corresponding to the cell type corresponding to the corresponding cell characteristic parameter.

[0038] A second aspect of an embodiment of the present invention discloses a system for predicting the effect of immunotherapy for colorectal cancer, the system comprising:

[0039] An acquisition module, used for acquiring a digital image of biological tissue of a colorectal cancer patient;

[0040] A prediction module, used for predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on a classifier algorithm model;

[0041] A determination module, used to determine a plurality of cell feature parameters corresponding to the biological tissue digital image according to a plurality of cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter;

[0042] A calculation module is used to calculate the treatment effect score corresponding to the colorectal cancer patient based on the multiple cell characteristic parameters and preset parameter scoring rules; the treatment effect score is used to predict the treatment effect of the colorectal cancer patient receiving immunotherapy.

[0043] As an optional embodiment, in the second aspect of the present invention, the prediction module predicts the tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on the classifier algorithm model, including:

[0044] Inputting the biological tissue digital image into a trained tissue region recognition algorithm model to obtain a plurality of tissue regions corresponding to the biological tissue digital image and a tissue type corresponding to each of the tissue regions;

[0045] The biological tissue digital image is input into a trained cell recognition algorithm model to obtain a plurality of cell regions corresponding to the biological tissue digital image and a cell type corresponding to each of the cell regions.

[0046] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the multiple cell feature parameters corresponding to the biological tissue digital image according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0047] Calculating the number of regions of all the tissue regions whose tissue type is a mucus component type;

[0048] The ratio between the area number and the total area number corresponding to all the tissue areas is calculated to obtain a mucus area ratio parameter.

[0049] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the multiple cell feature parameters corresponding to the biological tissue digital image according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0050] Screening out all tissue regions whose tissue types are tumor types to obtain multiple tumor tissue regions;

[0051] Calculating the minimum circumscribed polygons of the multiple tumor tissue regions to obtain a comprehensive tumor region;

[0052] The tumor comprehensive area is divided into a plurality of sub-areas, and for each of the sub-areas,

[0053] Calculating the total number of cell regions in the subregion where the cell type belongs to lymphocytes to obtain the number of lymphocytes;

[0054] Calculate the total number of cell regions in the subregion where the cell type belongs to tumor cells to obtain the number of tumor cells;

[0055] Calculating the ratio of the number of lymphocytes to the first total number of cells to obtain the lymphocyte ratio; the first total number of cells is the sum of the number of lymphocytes and the number of tumor cells;

[0056] Calculating the ratio of the number of tumor cells to the total number of cells to obtain the tumor cell ratio;

[0057] According to the lymphocyte proportions and the tumor cell proportions corresponding to all the sub-regions, based on the co-localization coefficient algorithm, the lymphocyte abundance parameter corresponding to the tumor comprehensive region is calculated.

[0058] As an optional embodiment, in the second aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0059] Calculate the total number of cell regions in each of the subregions where the cell type belongs to plasma cells to obtain the number of plasma cells;

[0060] Calculating the ratio of the number of plasma cells in each of the sub-regions to the second total number of cells to obtain the proportion of plasma cells in each of the sub-regions; the second total number of cells is the sum of the number of plasma cells and the number of tumor cells;

[0061] According to the plasma cell proportions and the tumor cell proportions corresponding to all the sub-regions, based on the co-localization coefficient algorithm, the plasma cell co-localization parameters corresponding to the tumor comprehensive region are calculated.

[0062] As an optional embodiment, in the second aspect of the present invention, the determining of the multiple cell feature parameters corresponding to the digital image of the biological tissue according to the multiple cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes:

[0063] Calculating the total number of cell regions in each of the sub-regions where the cell type belongs to neutrophils to obtain the number of neutrophils;

[0064] Calculating the ratio of the number of neutrophils in each of the sub-regions to the third total number of cells to obtain the proportion of neutrophils in each of the sub-regions; the third total number of cells is the sum of the number of neutrophils and the number of tumor cells;

[0065] According to the neutrophil proportions and the tumor cell proportions corresponding to all the sub-areas, based on the colocalization coefficient algorithm, the neutrophil colocalization parameter corresponding to the tumor comprehensive area is calculated.

[0066] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the calculation module calculates the treatment effect score corresponding to the colorectal cancer patient according to the multiple cell characteristic parameters and the preset parameter scoring rules includes:

[0067] Calculating a first effect score corresponding to the mucus area ratio parameter; the first effect score is inversely proportional to the mucus area ratio parameter;

[0068] respectively calculating the second effect scores corresponding to the lymphocyte abundance parameter, the plasma cell colocalization parameter, and the neutrophil colocalization parameter; the second effect score is proportional to the lymphocyte abundance parameter, the plasma cell colocalization parameter, or the neutrophil colocalization parameter;

[0069] The sum of the first effect score and all the second effect scores is calculated to obtain the treatment effect score corresponding to the colorectal cancer patient.

[0070] As an optional embodiment, in the second aspect of the present invention, the calculation module calculates the first effect score and the sum of all the second effect scores to obtain the specific method of the treatment effect score corresponding to the colorectal cancer patient, including:

[0071] Calculate the weighted sum average of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient; wherein the weighted calculation weight of the first effect score is proportional to the total area of ​​all tissue regions whose tissue type is the mucus component type, and the weighted calculation weight of the second effect score is proportional to the total area of ​​the cell region corresponding to the cell type corresponding to the corresponding cell characteristic parameter.

[0072] The third aspect of the present invention discloses another colorectal cancer immunotherapy effect prediction system, the system comprising:

[0073] A memory storing executable program code;

[0074] a processor coupled to the memory;

[0075] The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for predicting the treatment effect of colorectal cancer disclosed in the first aspect of the present invention.

[0076] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the method for predicting the colorectal cancer treatment effect disclosed in the first aspect of the present invention.

[0077] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0078] The present invention can first determine the tissue type and cell type corresponding to the biological image through a classifier algorithm, and then determine multiple cell feature parameters in combination with the corresponding feature calculation rules and then score them to obtain a score that can characterize the treatment effect, thereby effectively improving the accuracy and efficiency of predicting the treatment effect of colorectal cancer, reducing prediction costs, and providing an accurate data basis for subsequent treatment or research. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0080] Figure 1 It is a flow chart of a method for predicting the therapeutic effect of colorectal cancer disclosed in an embodiment of the present invention.

[0081] Figure 2 It is a structural schematic diagram of a colorectal cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention.

[0082] Figure 3 It is a schematic diagram of the structure of another colorectal cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0083] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0085] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0086] Before describing the specific technical scheme disclosed in the present invention, the prior art targeted by the overall scheme of the present invention is introduced. Specifically, in the current clinical practice, dMMR / MSI-H is the only recognized biomarker that can be used to guide neoadjuvant immunotherapy for colorectal cancer. It is currently believed that dMMR / MSI-H patients can benefit from neoadjuvant immunotherapy, while pMMR / MSS patients cannot benefit from neoadjuvant immunotherapy. However, in clinical practice, it was found that some dMMR / MSI-H patients still cannot benefit from neoadjuvant immunotherapy, and some pMMR / MSS patients can benefit from neoadjuvant immunotherapy. Therefore, early prediction of colorectal cancer patients who can benefit from neoadjuvant immunotherapy is a scientific problem of great clinical value. The scheme of the present invention can also be applied to this prediction problem, and there is no pathological genomics method in the prior art to predict the efficacy of immunotherapy for a special tumor type such as colorectal cancer.

[0087] In order to solve some or all of the problems in the above-mentioned prior art, the present invention discloses a colorectal cancer immunotherapy effect prediction system, which can first determine the tissue type and cell type corresponding to the biological image through a classifier algorithm, and then determine multiple cell feature parameters in combination with the corresponding feature calculation rules and then score them to obtain a score that can characterize the treatment effect, thereby effectively improving the accuracy and efficiency of colorectal cancer treatment effect prediction, reducing prediction costs, and providing an accurate data basis for subsequent treatment or research. The following is a detailed description.

[0088] Embodiment 1

[0089] See also Figure 1 , Figure 1: is a flow chart of a method for predicting the treatment effect of colorectal cancer disclosed in an embodiment of the present invention. Figure 1 The colorectal cancer treatment effect prediction method described can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the method for predicting the treatment effect of colorectal cancer may include the following operations:

[0090] 101. Obtain digital images of biological tissues of patients with colorectal cancer.

[0091] 102. Based on the classifier algorithm model, predict the tissue type parameters and cell type parameters corresponding to the digital image of biological tissue.

[0092] 103. Determine multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to tissue type parameters and cell type parameters.

[0093] 104. Based on multiple cell characteristic parameters and preset parameter scoring rules, the corresponding treatment effect score of colorectal cancer patients is calculated.

[0094] Optionally, the treatment efficacy score is used to predict the treatment efficacy of immunotherapy in patients with colorectal cancer.

[0095] Optionally, the digital image of biological tissue is a full-view digital slice image (WSI), which can be a HE-stained image of a colonoscopy biopsy specimen before treatment. Specifically, the traditional pathological HE-stained slice can be converted into a full-view digital slice through a scanner and a high-resolution microscope through digital pathological image recognition technology. Because there is no pathological omics method for HE-stained image analysis of colonoscopy biopsy specimens before treatment in the prior art, most of the current pathological omics recognition technologies are based on HE-stained images of gross specimens after tumor resection. Such gross specimens need to be obtained after surgical resection, and have lost the opportunity and necessity to predict the efficacy. Colonoscopy biopsy specimens can be obtained through colonoscopy before receiving any treatment, and patients still have the opportunity to choose treatment methods at this time. In addition, colonoscopy biopsy specimens have difficulties such as small amount of material, poor representativeness, and deformation of tissues caused by tearing during colonoscopy biopsy operations. It is not feasible to directly copy the recognition method and recognition features of gross specimens. Through the above steps, pathological omics can further apply a lot of information that is invisible to the naked eye to specific targets, produce high-precision and repeatable results, and thus improve the efficiency and accuracy of pathological diagnosis.

[0096] Specifically, immunotherapy refers to neoadjuvant immunotherapy for colorectal cancer. Specifically, since nivolumab was first used for tumor treatment in 2006, PD-1 antibodies and other related immunotherapy methods have become increasingly popular. They have become another effective means for the treatment of malignant tumors after surgery, chemotherapy, radiotherapy, targeted therapy and other treatment methods, and have completely changed the treatment strategies of many cancers such as lung cancer, gastric cancer, and breast cancer. In many guideline consensuses, including the National Comprehensive Cancer Network (NCCN) guidelines and the Chinese Society of Clinical Oncology (CSCO) guidelines, pembrolizumab and other representatives have occupied the first-line treatment position for dMMR / MSI-H colorectal cancer patients. Among them, neoadjuvant immunotherapy refers to immunotherapy for patients without distant metastasis before surgery, in order to achieve tumor regression, or even complete remission, and avoid surgery. Although immunotherapy is effective, some patients still cannot benefit from immune patients. Therefore, early prediction of colorectal cancer patients who can benefit from immunotherapy is a scientific issue of great clinical value.

[0097] Specifically, the scheme of the present invention focuses on identifying the microenvironmental characteristics in biological tissues when calculating cell characteristic parameters. Specifically, studies have shown that the tumor microenvironment can reflect the differences in colorectal cancer from multiple aspects. At the tissue level, in addition to the tumor epithelial area, different tissue regions such as the tumor interstitial area, mucus area, and tumor necrosis area have an important impact on the prognosis of colorectal cancer patients. At the cellular level, immune cells including tumor-infiltrating lymphocytes (TILs), plasma cells, neutrophils, etc. play a key role in the anti-tumor immune response and together with other cell types in the tumor area constitute the immune microenvironment.

[0098] It can be seen that the above-mentioned embodiment of the invention can first determine the tissue type and cell type corresponding to the biological image through the classifier algorithm, and then determine multiple cell feature parameters in combination with the corresponding feature calculation rules and then score them to obtain a score that can characterize the treatment effect, thereby effectively improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0099] As an optional embodiment, in the above steps, predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on the classifier algorithm model includes:

[0100] Inputting the biological tissue digital image into the trained tissue region recognition algorithm model to obtain multiple tissue regions corresponding to the biological tissue digital image and the tissue type corresponding to each tissue region;

[0101] The biological tissue digital image is input into the trained cell recognition algorithm model to obtain multiple cell regions corresponding to the biological tissue digital image and the cell type corresponding to each cell region.

[0102] Optionally, the tissue region recognition algorithm model can divide different regions in the digital image of biological tissue into at least two types including mucus component type and tumor region. Its feature encoding model structure is a Densenet architecture, which is trained by a training data set including multiple training images and corresponding biological tissue type annotations.

[0103] Optionally, the cell recognition algorithm model can divide different areas in the digital image of biological tissue into six cell types, including tumor epithelial cells, tumor stromal cells, lymphocytes, plasma cells, neutrophils, and eosinophils. The cell recognition model is trained using a publicly available training dataset (Lizard dataset), which is widely used in the construction of such colorectal cell recognition models. The Lizard dataset includes histological image regions of colorectal tissue from six different dataset sources, and is accompanied by nuclear markers of epithelial cells, stromal cells, lymphocytes, plasma cells, neutrophils, and eosinophils, which can be used to help effectively describe the tumor immune microenvironment. The Lizard dataset was randomly divided into training and validation sets in a ratio of 8:2, and the FCN neural network was selected as the model architecture.

[0104] It can be seen that through the above-mentioned optional embodiments, the tissue regions and cell regions in the digital images of biological tissues can be identified through the trained tissue region recognition algorithm model and cell recognition algorithm model, so as to facilitate the subsequent calculation of cell characteristic parameters and treatment effect scores based on this, thereby helping to improve the accuracy and efficiency of the prediction of colorectal cancer treatment effects, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

[0105] As an optional embodiment, in the above steps, determining multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to tissue type parameters and cell type parameters includes:

[0106] The number of areas in which all tissue types were mucus component types was calculated;

[0107] The ratio between the number of regions and the total number of regions corresponding to all tissue regions was calculated to obtain the mucus region ratio parameter.

[0108] It can be seen that through the above optional embodiments, the mucus area ratio parameter can be obtained by calculating the ratio of the number of tissue areas of the mucus component type to the total number of areas, which can effectively evaluate the mucus situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby assisting in improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0109] As an optional embodiment, in the above steps, determining multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to tissue type parameters and cell type parameters includes:

[0110] Screening out all tissue regions whose tissue types are tumor types, and obtaining multiple tumor tissue regions;

[0111] Calculate the minimum circumscribed polygons of multiple tumor tissue regions to obtain the comprehensive tumor region;

[0112] The tumor comprehensive area is divided into multiple sub-areas. For each sub-area,

[0113] The total number of cell regions in the sub-region whose cell type is lymphocytes is calculated to obtain the number of lymphocytes;

[0114] Calculate the total number of cell regions in the sub-region whose cell types belong to tumor cells to obtain the number of tumor cells;

[0115] Calculating the ratio of the number of lymphocytes to the first total number of cells to obtain the lymphocyte ratio; optionally, the first total number of cells is the sum of the number of lymphocytes and the number of tumor cells;

[0116] Calculate the ratio of the number of tumor cells to the total number of cells to obtain the tumor cell ratio;

[0117] According to the lymphocyte proportion and tumor cell proportion corresponding to all sub-areas, the lymphocyte abundance parameter corresponding to the tumor comprehensive area was calculated based on the co-localization coefficient algorithm.

[0118] Specifically, the tumor comprehensive region may be divided into a plurality of sub-regions by dividing the tumor comprehensive region into a plurality of 0.5 mm*0.5 mm square regions, so as to calculate the cell parameters in each square region.

[0119] Specifically, according to the lymphocyte proportion and tumor cell proportion corresponding to all sub-regions, based on the co-localization coefficient algorithm, the lymphocyte abundance parameters corresponding to the tumor comprehensive region are calculated, including:

[0120] For each sub-region, the product of the lymphocyte ratio and the tumor cell ratio corresponding to the sub-region is calculated to obtain a first parameter;

[0121] Calculate twice the sum of the first parameters of all sub-regions to obtain the second parameter;

[0122] The sum of the square values ​​of the lymphocyte proportions corresponding to all sub-regions is calculated to obtain the third parameter;

[0123] The sum of the square values ​​of the tumor cell proportions corresponding to all sub-regions is calculated to obtain the fourth parameter;

[0124] Calculate the sum of the third parameter and the fourth parameter to obtain the fifth parameter;

[0125] Calculate the ratio of the second parameter to the fifth parameter to obtain the colocalization score parameter;

[0126] Calculate the ratio of the colocalization score parameter to 2 to obtain a sixth parameter;

[0127] Calculate the sum of the lymphocyte proportions corresponding to all sub-regions to obtain the seventh parameter;

[0128] Calculate the sum of the tumor cell proportions corresponding to all sub-regions to obtain the eighth parameter;

[0129] Calculating the ratio of the seventh parameter to the eighth parameter to obtain a ninth parameter;

[0130] The product of the sixth parameter and the ninth parameter is calculated to obtain the lymphocyte abundance parameter corresponding to the comprehensive tumor area.

[0131] It can be seen that through the above-mentioned optional embodiments, the lymphocyte abundance parameters can be obtained by regional division of tissue areas of tumor types and co-localization calculation of the number of lymphocytes and the number of tumor cells, which can effectively evaluate the lymphocyte abundance in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby helping to improve the accuracy and efficiency of the prediction of colorectal cancer treatment effects, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

[0132] As an optional embodiment, in the above steps, determining multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to tissue type parameters and cell type parameters includes:

[0133] Calculate the total number of cell regions in each sub-region whose cell type belongs to plasma cells to obtain the number of plasma cells;

[0134] Calculate the ratio of the number of plasma cells in each sub-region to the second total number of cells to obtain the proportion of plasma cells in each sub-region; optionally, the second total number of cells is the sum of the number of plasma cells and the number of tumor cells;

[0135] According to the proportion of plasma cells and tumor cells corresponding to all sub-regions, the plasma cell colocalization parameters corresponding to the tumor comprehensive region were calculated based on the colocalization coefficient algorithm.

[0136] Specifically, according to the proportion of plasma cells and tumor cells corresponding to all sub-regions, based on the co-localization coefficient algorithm, the plasma cell co-localization parameters corresponding to the tumor comprehensive region are calculated, including:

[0137] For each sub-region, the product of the plasma cell proportion and the tumor cell proportion corresponding to the sub-region is calculated to obtain the tenth parameter;

[0138] Calculate twice the sum of the tenth parameters of all sub-areas to obtain the eleventh parameter;

[0139] The sum of the square values ​​of the plasma cell proportions corresponding to all sub-regions was calculated to obtain twelve parameters;

[0140] Calculate the sum of the twelfth parameter and the fourth parameter to obtain the thirteenth parameter;

[0141] The ratio of the eleventh parameter and the thirteenth parameter is calculated to obtain the plasma cell co-localization parameter corresponding to the comprehensive tumor area, wherein the calculation of the fourth parameter is as described in the above embodiment and will not be repeated here.

[0142] It can be seen that through the above-mentioned optional embodiments, the plasma cell colocalization parameters can be obtained by co-localizing the number of plasma cells and the number of tumor cells in the tissue area of ​​the tumor type, which can effectively evaluate the plasma cell situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby assisting in improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0143] As an optional embodiment, in the above steps, determining multiple cell feature parameters corresponding to the biological tissue digital image according to multiple cell feature calculation rules corresponding to tissue type parameters and cell type parameters includes:

[0144] The total number of cell regions in each sub-region whose cell type is neutrophils was calculated to obtain the number of neutrophils;

[0145] Calculating the ratio of the number of neutrophils in each sub-region to the third total number of cells to obtain the proportion of neutrophils in each sub-region; optionally, the third total number of cells is the sum of the number of neutrophils and the number of tumor cells;

[0146] According to the neutrophil proportion and tumor cell proportion corresponding to all sub-areas, the neutrophil colocalization parameter corresponding to the tumor comprehensive area was calculated based on the colocalization coefficient algorithm.

[0147] Specifically, according to the neutrophil proportion and tumor cell proportion corresponding to all sub-regions, based on the co-localization coefficient algorithm, the neutrophil co-localization parameters corresponding to the tumor comprehensive region are calculated, including:

[0148] For each sub-region, the product of the neutrophil cell ratio and the tumor cell ratio corresponding to the sub-region is calculated to obtain the fourteenth parameter;

[0149] Calculate twice the sum of the fourteenth parameters of all sub-areas to obtain the fifteenth parameter;

[0150] The sum of the square values ​​of the neutrophil percentages corresponding to all sub-regions was calculated to obtain sixteen parameters;

[0151] Calculate the sum of the sixteenth parameter and the fourth parameter to obtain the seventeenth parameter;

[0152] The ratio of the fifteenth parameter to the seventeenth parameter is calculated to obtain the neutrophil co-localization parameter corresponding to the tumor comprehensive area, wherein the calculation of the fourth parameter is as described in the above embodiment and will not be repeated here.

[0153] It can be seen that through the above-mentioned optional embodiments, the neutrophil colocalization parameters can be obtained by co-localizing the number of neutrophils and the number of tumor cells in the tissue area of ​​the tumor type, which can effectively evaluate the neutrophil situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby helping to improve the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reduce the prediction cost, and provide an accurate data basis for subsequent treatment or research.

[0154] As an optional embodiment, in the above steps, calculating the treatment effect score corresponding to the colorectal cancer patient according to multiple cell characteristic parameters and preset parameter scoring rules includes:

[0155] Calculating a first effect score corresponding to the mucus area ratio parameter; optionally, the first effect score is inversely proportional to the mucus area ratio parameter;

[0156] Calculating the second effect scores corresponding to the lymphocyte abundance parameter, the plasma cell colocalization parameter, and the neutrophil colocalization parameter respectively; optionally, the second effect score is proportional to the lymphocyte abundance parameter, the plasma cell colocalization parameter, or the neutrophil colocalization parameter;

[0157] The sum of the first effect score and all the second effect scores is calculated to obtain the corresponding treatment effect score for colorectal cancer patients.

[0158] In a specific embodiment, points are assigned according to the quartile of each characteristic parameter. For each characteristic parameter, if it is beneficial to treatment, the higher the parameter value, the higher the score, for example, if it is higher than the 75% percentile, it is scored as 1 point, if it is lower than the 25% percentile, it is scored as -1 point, and if it is between the 25th percentile and the 75th percentile, no score is given. If it is unfavorable to treatment, the higher the parameter value, the lower the score, for example, if it is higher than the 75th percentile, it is scored as -1 point, if it is lower than the 25th percentile, it is scored as 1 point, and if it is between the 25th percentile and the 75th percentile, no score is given. One optional scoring scheme is as follows:

[0159] Mucus area ratio parameter: <0.01224769 is 1 point, >0.053930183 is -1 point

[0160] Lymphocyte abundance parameter: <0.040537723 = -1 point >0.170647716 = 1 point

[0161] Plasma cell co-localization parameter: <0.084856712 = -1 point > 0.199756568 = 1 point

[0162] Neutrophil colocalization parameter: <0.037376427 = -1 point >0.085987609 = 1 point

[0163] Finally, the scores of all characteristic parameters are summed up to obtain the treatment effect score corresponding to the pathological genomics immune microenvironment. The corresponding scoring scheme can be: scores of 1, 2, 3, and 4 are evaluated as immune-hot tumors, scores of -1 and 0 are evaluated as immune-moderate tumors, and scores of -4, -3, and -2 are evaluated as immune-cold tumors. This score can predict the efficacy of immunotherapy independently of the MMR / MSI status. The higher the score, the more obvious the benefit from immunotherapy.

[0164] In the study using this implementation plan, 17 patients in the dMMR modeling cohort, 17 patients in the dMMR retrospective cohort, and 11 patients in the dMMR prospective cohort were identified as immune-hot tumors, and all 45 patients (35.4%) with immune-hot tumors achieved complete remission after neoadjuvant immunotherapy. Previous studies have shown that patients with colorectal cancer who achieve clinical complete remission after immunotherapy can adopt a surgically exempted observation and waiting strategy, and no recurrence or metastasis events were found in the 2-year follow-up. This suggests that this model is expected to be used to screen a special group of about one-third of dMMR colorectal cancer patients who can achieve complete remission through neoadjuvant immunotherapy, exempt from surgical treatment, and achieve organ preservation.

[0165] On the other hand, the study included 47 pMMR patients. Surprisingly, the model established in dMMR patients also showed good predictive efficacy in pMMR patients. A total of 12 pMMR (25.5%) were identified as immune-hot tumors. Their CR rate reached 57.1%, which was significantly better than that of patients with immune-moderate tumors and immune-cold tumors. At the same time, their ORR rate reached 81.0%, which was better than the 46.2% of immune-cold tumors, but because the sample size was too small, it did not reach statistical significance. It is worth noting that the current preferred neoadjuvant therapy for pMMR locally advanced colorectal cancer is neoadjuvant chemotherapy. The results of the OPTICAL study showed that the CR rate was only 7%, and only 20% of patients were pathologically downstaged to stage 0-Ⅰ after surgery. The current preferred neoadjuvant therapy for locally advanced rectal cancer is TNT treatment. According to the data from the PRODIGE 23 study, its CR rate is only 27.5%. Therefore, the CR rate of 57.1% and the ORR rate of 81.0% in the immune-hot tumor group in this study are significantly better than the current preferred neoadjuvant treatment for pMMR colorectal cancer. This suggests that the present embodiment is expected to be used to screen a special group of approximately one quarter of pMMR patients who can achieve better short-term efficacy through neoadjuvant immunotherapy.

[0166] It can be seen that through the above-mentioned optional embodiments, by calculating and summing the effect scores corresponding to multiple cell characteristic parameters, a treatment effect score that can predict the effect of immunotherapy on patients can be obtained, thereby improving the accuracy and efficiency of predicting the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0167] As an optional embodiment, in the above step, calculating the sum of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient includes:

[0168] Calculate the weighted sum average of the first effect score and all the second effect scores to obtain the corresponding treatment effect score for colorectal cancer patients; wherein the weighted calculation weight of the first effect score is proportional to the total area of ​​all tissue regions with mucus component types, and the weighted calculation weight of the second effect score is proportional to the total area of ​​the cell region corresponding to the cell type corresponding to the corresponding cell characteristic parameter.

[0169] Specifically, the above scheme introduces the calculation of the weight of the regional area, so that the treatment effect score obtained by the final weighted summation can effectively take into account the influence of the regional area on which the parameter calculation is based on the parameter value, making the final score clearer and better characterizing the patient's predicted treatment effect.

[0170] It can be seen that through the above-mentioned optional embodiments, the effect scores corresponding to multiple cell characteristic parameters can be weighted and summed based on the weight rules related to the regional area, so as to obtain a treatment effect score that can more accurately predict the effect of immunotherapy on patients, thereby improving the accuracy and efficiency of colorectal cancer treatment effect prediction, reducing prediction costs, and providing an accurate data basis for subsequent treatment or research.

[0171] Embodiment 2

[0172] See also Figure 2 , Figure 2 : is a schematic diagram of a colorectal cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. Figure 2 The colorectal cancer immunotherapy effect prediction system described can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the colorectal cancer immunotherapy effect prediction system may include:

[0173] The acquisition module 201 is used to acquire a digital image of biological tissue of a colorectal cancer patient.

[0174] The prediction module 202 is used to predict tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on the classifier algorithm model.

[0175] The determination module 203 is used to determine a plurality of cell characteristic parameters corresponding to the biological tissue digital image according to a plurality of cell characteristic calculation rules corresponding to the tissue type parameters and the cell type parameters.

[0176] The calculation module 204 is used to calculate the treatment effect score corresponding to the colorectal cancer patient according to multiple cell characteristic parameters and preset parameter scoring rules.

[0177] Optionally, the treatment efficacy score is used to predict the treatment efficacy of immunotherapy in patients with colorectal cancer.

[0178] It can be seen that the above-mentioned embodiment of the invention can first determine the tissue type and cell type corresponding to the biological image through the classifier algorithm, and then determine multiple cell feature parameters in combination with the corresponding feature calculation rules and then score them to obtain a score that can characterize the treatment effect, thereby effectively improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0179] As an optional embodiment, the prediction module predicts the tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on the classifier algorithm model, including:

[0180] Inputting the biological tissue digital image into the trained tissue region recognition algorithm model to obtain multiple tissue regions corresponding to the biological tissue digital image and the tissue type corresponding to each tissue region;

[0181] The biological tissue digital image is input into the trained cell recognition algorithm model to obtain multiple cell regions corresponding to the biological tissue digital image and the cell type corresponding to each cell region.

[0182] It can be seen that through the above-mentioned optional embodiments, the tissue regions and cell regions in the digital images of biological tissues can be identified through the trained tissue region recognition algorithm model and cell recognition algorithm model, so as to facilitate the subsequent calculation of cell characteristic parameters and treatment effect scores based on this, thereby helping to improve the accuracy and efficiency of the prediction of colorectal cancer treatment effects, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

[0183] As an optional embodiment, the specific manner in which the determination module determines the multiple cell feature parameters corresponding to the biological tissue digital image according to the multiple cell feature calculation rules corresponding to the tissue type parameters and the cell type parameters includes:

[0184] The number of areas in which all tissue types were mucus component types was calculated;

[0185] The ratio between the number of regions and the total number of regions corresponding to all tissue regions was calculated to obtain the mucus region ratio parameter.

[0186] It can be seen that through the above optional embodiments, the mucus area ratio parameter can be obtained by calculating the ratio of the number of tissue areas of the mucus component type to the total number of areas, which can effectively evaluate the mucus situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby assisting in improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0187] As an optional embodiment, the specific manner in which the determination module determines the multiple cell feature parameters corresponding to the biological tissue digital image according to the multiple cell feature calculation rules corresponding to the tissue type parameters and the cell type parameters includes:

[0188] Screening out all tissue regions whose tissue types are tumor types, and obtaining multiple tumor tissue regions;

[0189] Calculate the minimum circumscribed polygons of multiple tumor tissue regions to obtain the comprehensive tumor region;

[0190] The tumor comprehensive area is divided into multiple sub-areas. For each sub-area,

[0191] The total number of cell regions in the sub-region whose cell type is lymphocytes is calculated to obtain the number of lymphocytes;

[0192] Calculate the total number of cell regions in the sub-region whose cell types belong to tumor cells to obtain the number of tumor cells;

[0193] Calculating the ratio of the number of lymphocytes to the first total number of cells to obtain the lymphocyte ratio; optionally, the first total number of cells is the sum of the number of lymphocytes and the number of tumor cells;

[0194] Calculate the ratio of the number of tumor cells to the total number of cells to obtain the tumor cell ratio;

[0195] According to the lymphocyte proportion and tumor cell proportion corresponding to all sub-areas, the lymphocyte abundance parameter corresponding to the tumor comprehensive area was calculated based on the co-localization coefficient algorithm.

[0196] It can be seen that through the above-mentioned optional embodiments, the lymphocyte abundance parameters can be obtained by regional division of tissue areas of tumor types and co-localization calculation of the number of lymphocytes and the number of tumor cells, which can effectively evaluate the lymphocyte abundance in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby helping to improve the accuracy and efficiency of the prediction of colorectal cancer treatment effects, reduce prediction costs, and provide an accurate data basis for subsequent treatment or research.

[0197] As an optional embodiment, according to the multiple cell feature calculation rules corresponding to the tissue type parameters and the cell type parameters, the multiple cell feature parameters corresponding to the biological tissue digital image are determined, including:

[0198] Calculate the total number of cell regions in each sub-region whose cell type belongs to plasma cells to obtain the number of plasma cells;

[0199] Calculate the ratio of the number of plasma cells in each sub-region to the second total number of cells to obtain the proportion of plasma cells in each sub-region; optionally, the second total number of cells is the sum of the number of plasma cells and the number of tumor cells;

[0200] According to the proportion of plasma cells and tumor cells corresponding to all sub-regions, the plasma cell colocalization parameters corresponding to the tumor comprehensive region were calculated based on the colocalization coefficient algorithm.

[0201] It can be seen that through the above-mentioned optional embodiments, the plasma cell colocalization parameters can be obtained by co-localizing the number of plasma cells and the number of tumor cells in the tissue area of ​​the tumor type, which can effectively evaluate the plasma cell situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby assisting in improving the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0202] As an optional embodiment, according to the multiple cell feature calculation rules corresponding to the tissue type parameters and the cell type parameters, the multiple cell feature parameters corresponding to the biological tissue digital image are determined, including:

[0203] The total number of cell regions in each sub-region whose cell type is neutrophils was calculated to obtain the number of neutrophils;

[0204] Calculating the ratio of the number of neutrophils in each sub-region to the third total number of cells to obtain the proportion of neutrophils in each sub-region; optionally, the third total number of cells is the sum of the number of neutrophils and the number of tumor cells;

[0205] According to the neutrophil proportion and tumor cell proportion corresponding to all sub-areas, the neutrophil colocalization parameter corresponding to the tumor comprehensive area was calculated based on the colocalization coefficient algorithm.

[0206] It can be seen that through the above-mentioned optional embodiments, the neutrophil colocalization parameters can be obtained by co-localizing the number of neutrophils and the number of tumor cells in the tissue area of ​​the tumor type, which can effectively evaluate the neutrophil situation in the tissue, so as to facilitate the subsequent calculation of the treatment effect score based on this, thereby helping to improve the accuracy and efficiency of the prediction of the treatment effect of colorectal cancer, reduce the prediction cost, and provide an accurate data basis for subsequent treatment or research.

[0207] As an optional embodiment, the specific method in which the calculation module calculates the treatment effect score corresponding to the colorectal cancer patient according to the multiple cell characteristic parameters and the preset parameter scoring rules includes:

[0208] Calculating a first effect score corresponding to the mucus area ratio parameter; optionally, the first effect score is inversely proportional to the mucus area ratio parameter;

[0209] Calculating the second effect scores corresponding to the lymphocyte abundance parameter, the plasma cell colocalization parameter, and the neutrophil colocalization parameter respectively; optionally, the second effect score is proportional to the lymphocyte abundance parameter, the plasma cell colocalization parameter, or the neutrophil colocalization parameter;

[0210] The sum of the first effect score and all the second effect scores is calculated to obtain the corresponding treatment effect score for colorectal cancer patients.

[0211] It can be seen that through the above-mentioned optional embodiments, by calculating and summing the effect scores corresponding to multiple cell characteristic parameters, a treatment effect score that can predict the effect of immunotherapy on patients can be obtained, thereby improving the accuracy and efficiency of predicting the treatment effect of colorectal cancer, reducing the prediction cost, and providing an accurate data basis for subsequent treatment or research.

[0212] As an optional embodiment, the calculation module calculates the sum of the first effect score and all the second effect scores to obtain the specific method of the treatment effect score corresponding to the colorectal cancer patient, including:

[0213] Calculate the weighted sum average of the first effect score and all the second effect scores to obtain the corresponding treatment effect score for colorectal cancer patients; wherein the weighted calculation weight of the first effect score is proportional to the total area of ​​all tissue regions with mucus component types, and the weighted calculation weight of the second effect score is proportional to the total area of ​​the cell region corresponding to the cell type corresponding to the corresponding cell characteristic parameter.

[0214] It can be seen that through the above-mentioned optional embodiments, the effect scores corresponding to multiple cell characteristic parameters can be weighted and summed based on the weight rules related to the regional area, so as to obtain a treatment effect score that can more accurately predict the effect of immunotherapy on patients, thereby improving the accuracy and efficiency of colorectal cancer treatment effect prediction, reducing prediction costs, and providing an accurate data basis for subsequent treatment or research.

[0215] Embodiment 3

[0216] See also Figure 3 , Figure 3 This is another colorectal cancer immunotherapy effect prediction system disclosed in an embodiment of the present invention. Figure 3 The colorectal cancer immunotherapy effect prediction system described is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the colorectal cancer immunotherapy effect prediction system may include:

[0217] A memory 301 storing executable program codes;

[0218] a processor 302 coupled to the memory 301;

[0219] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the method for predicting the treatment effect of colorectal cancer described in the first embodiment.

[0220] Embodiment 4

[0221] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for predicting the treatment effect of colorectal cancer described in the first embodiment.

[0222] Embodiment 5

[0223] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for predicting the treatment effect of colorectal cancer described in Example 1.

[0224] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0225] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0226] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0227] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0228] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0229] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0230] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0231] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0232] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0233] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0234] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0235] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0236] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0237] Finally, it should be noted that the colorectal cancer immunotherapy effect prediction system disclosed in the embodiment of the present invention discloses only a preferred embodiment of the present invention, which is only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes recorded in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A colorectal cancer immunotherapy effect prediction system, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute a method for predicting the treatment effect of colorectal cancer, the method comprising: Acquire digital images of biological tissues of patients with colorectal cancer; Based on the classifier algorithm model, predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image; Determining a plurality of cell feature parameters corresponding to the biological tissue digital image according to a plurality of cell feature calculation rules corresponding to the tissue type parameter and the cell type parameter includes: Counting the number of regions of all tissue regions where the tissue type is a mucus component type; Calculating the ratio between the number of regions and the total number of regions corresponding to all tissue regions to obtain a mucus region ratio parameter; Screening out all tissue regions whose tissue types are tumor types to obtain multiple tumor tissue regions; Calculating the minimum circumscribed polygons of the multiple tumor tissue regions to obtain a comprehensive tumor region; Dividing the tumor comprehensive area into a plurality of sub-areas, and for each of the sub-areas, calculating the total number of cell areas in the sub-area whose cell type belongs to lymphocytes, to obtain the number of lymphocytes; Calculate the total number of cell regions in the subregion where the cell type belongs to tumor cells to obtain the number of tumor cells; Calculating the ratio of the number of lymphocytes to the first total number of cells to obtain the lymphocyte ratio; the first total number of cells is the sum of the number of lymphocytes and the number of tumor cells; Calculating the ratio of the number of tumor cells to the total number of cells to obtain the tumor cell ratio; For each of the sub-regions, calculating the product of the lymphocyte proportion and the tumor cell proportion corresponding to the sub-region to obtain a first parameter; Calculate twice the sum of the first parameters of all the sub-areas to obtain a second parameter; Calculating the sum of the square values ​​of the lymphocyte proportions corresponding to all the sub-regions to obtain a third parameter; Calculating the sum of the square values ​​of the tumor cell proportions corresponding to all the sub-regions to obtain a fourth parameter; Calculating the sum of the third parameter and the fourth parameter to obtain a fifth parameter; Calculating the ratio of the second parameter to the fifth parameter to obtain a colocalization score parameter; Calculate the ratio of the colocalization score parameter to 2 to obtain a sixth parameter; Calculating the sum of the lymphocyte proportions corresponding to all the sub-regions to obtain a seventh parameter; Calculating the sum of the tumor cell proportions corresponding to all the sub-regions to obtain an eighth parameter; Calculating the ratio of the seventh parameter to the eighth parameter to obtain a ninth parameter; Calculating the product of the sixth parameter and the ninth parameter to obtain a lymphocyte abundance parameter corresponding to the tumor comprehensive area; Calculate the total number of cell regions in each of the subregions where the cell type belongs to plasma cells to obtain the number of plasma cells; Calculate the ratio of the number of plasma cells in each of the sub-regions to the second total number of cells to obtain the proportion of plasma cells in each of the sub-regions; the second total number of cells is the sum of the number of plasma cells and the number of tumor cells; According to the plasma cell proportions and the tumor cell proportions corresponding to all the sub-regions, based on a co-localization coefficient algorithm, the plasma cell co-localization parameter corresponding to the comprehensive tumor region is calculated; Calculating the total number of cell regions in each of the sub-regions where the cell type belongs to neutrophils to obtain the number of neutrophils; Calculating the ratio of the number of neutrophils in each of the sub-regions to the third total number of cells to obtain the proportion of neutrophils in each of the sub-regions; the third total number of cells is the sum of the number of neutrophils and the number of tumor cells; According to the neutrophil proportions and the tumor cell proportions corresponding to all the sub-regions, based on a colocalization coefficient algorithm, calculating the neutrophil colocalization parameter corresponding to the tumor comprehensive region; Calculating the treatment effect score corresponding to the colorectal cancer patient according to the multiple cell characteristic parameters and the preset parameter scoring rules, including: Calculating a first effect score corresponding to the mucus area ratio parameter; the first effect score is inversely proportional to the mucus area ratio parameter; respectively calculating the second effect scores corresponding to the lymphocyte abundance parameter, the plasma cell colocalization parameter, and the neutrophil colocalization parameter; the second effect score is proportional to the lymphocyte abundance parameter, the plasma cell colocalization parameter, or the neutrophil colocalization parameter; The sum of the first effect score and all the second effect scores is calculated to obtain a treatment effect score corresponding to the colorectal cancer patient; the treatment effect score is used to predict the treatment effect of immunotherapy on the colorectal cancer patient.

2. The colorectal cancer immunotherapy effect prediction system according to claim 1, characterized in that: The method of predicting tissue type parameters and cell type parameters corresponding to the biological tissue digital image based on the classifier algorithm model includes: Inputting the biological tissue digital image into a trained tissue region recognition algorithm model to obtain a plurality of tissue regions corresponding to the biological tissue digital image and a tissue type corresponding to each of the tissue regions; The biological tissue digital image is input into a trained cell recognition algorithm model to obtain a plurality of cell regions corresponding to the biological tissue digital image and a cell type corresponding to each of the cell regions.

3. The colorectal cancer immunotherapy effect prediction system according to claim 1, characterized in that: The calculating the sum of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient includes: Calculate the weighted sum average of the first effect score and all the second effect scores to obtain the treatment effect score corresponding to the colorectal cancer patient; wherein the weighted calculation weight of the first effect score is proportional to the total area of ​​all tissue regions whose tissue type is the mucus component type, and the weighted calculation weight of the second effect score is proportional to the total area of ​​the cell region corresponding to the cell type corresponding to the corresponding cell characteristic parameter.

4. The colorectal cancer immunotherapy effect prediction system according to claim 1, characterized in that: The biological tissue digital image is a full-view digital slice image.

Images