Prognosis effect prediction method and system based on multiple features

Abstract

The invention discloses a prognosis effect prediction method and system based on multiple features. The method comprises the following steps: acquiring a tissue cell image of a target patient; performing feature calculation on the tissue cell image, and determining type parameters corresponding to a plurality of preset cell feature types; determining at least one corresponding prognosis effect prediction model according to a parameter relationship between the type parameters corresponding to the at least two cell feature types; and calculating a prognosis risk score corresponding to the target patient according to the prognosis effect prediction model and the type parameter corresponding to the cell feature type. Therefore, the prognosis effect prediction model can be accurately screened out by fully utilizing the relationship between the cell characteristics so as to realize more accurate prognosis effect prediction, the prediction efficiency and accuracy of cancer prognosis effect prediction are improved, and an accurate data basis is provided for disease treatment or research.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a prognosis effect prediction method and system based on multiple features. Background Art

[0002] Cancer is a major disease that seriously threatens human life and health. For cancer patients, targeted therapy for specific driver gene mutations and the emerging immunotherapy for the regulation of the body's immune system in recent years have good effects, and the effective prediction of the prognosis of treatment has become an important technical issue of concern. With the development of image processing technology and the popularization of medical-assisted imaging technology, more and more institutions have introduced image recognition technology to extract and analyze cell features in biological tissue images to predict the prognosis of patients. However, when considering cell features, the existing prognosis prediction technology generally only considers the feature parameters corresponding to the pre-screened features to determine the risk, and does not further screen the corresponding algorithm model based on the relationship between different cell features for more accurate parameter prediction. Therefore, the efficiency and accuracy of its prognosis prediction are lacking. 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 prognosis prediction method and system based on multiple features, which can make full use of the relationship between cell features to accurately screen out a prognosis prediction model to achieve more accurate prognosis prediction, improve the prediction efficiency and accuracy of cancer prognosis prediction, and provide an accurate data basis for disease treatment or research.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a prognosis effect prediction method based on multiple features, the method comprising: Acquire tissue cell images of target patients; Performing feature calculation on the tissue cell image to determine type parameters corresponding to a plurality of preset cell feature types; Determining at least one corresponding prognostic effect prediction model according to a parameter relationship between type parameters corresponding to at least two of the cell feature types; The prognostic risk score corresponding to the target patient is calculated according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type.

[0005] As an optional embodiment, in the first aspect of the present invention, the cell feature type is a preset distribution feature of cells of a preset cell type within an area of ​​a preset area parameter type; the preset cell type includes at least one of CD3+ cells, PanCK+ cells, CD8+ cells and CD3+ / CD8- cells; the preset area parameter type includes at least one of an intra-tumor area, a tumor infiltration area, a tumor infiltration front area, a tumor preset outer expansion range area and a tumor preset inner contraction range area; the preset distribution feature includes at least one of a density feature, a graphic feature, a quantity ratio feature, a co-localization feature and an abundance feature.

[0006] As an optional embodiment, in the first aspect of the present invention, determining at least one corresponding prognostic effect prediction model according to the parameter relationship between the type parameters corresponding to at least two of the cell feature types comprises: Determine the preset cell type corresponding to the cell characteristic type corresponding to each of the type parameters corresponding to the tissue cell image, so as to obtain a plurality of image cell types corresponding to the tissue cell image; Determine the image cell type corresponding to at least two of the type parameters to obtain a multi-feature cell type; For each of the multi-feature cell types, grouping all of the type parameters corresponding to the multi-feature cell type to obtain a combination of parameters of the same type; Input each of the same type of parameter combinations into a corresponding fitting algorithm model to obtain a corresponding fitting parameter relationship; Determine the fitting parameter relationships corresponding to all the multi-feature cell types as parameter relationship data corresponding to the tissue cell image; At least one prognosis effect prediction model is determined from a plurality of candidate prediction models according to the parameter relationship data.

[0007] As an optional embodiment, in the first aspect of the present invention, the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same or the preset regional parameter types are the same; when the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a polynomial fitting model corresponding to the preset distribution characteristics corresponding to the same type parameter combination, and the polynomial fitting model is a density polynomial fitting model, a graphic parameter polynomial fitting model, a quantity proportion polynomial fitting model, a co-localization polynomial fitting model or an abundance polynomial fitting model; when the preset regional parameter types of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a trained vector feature extraction neural network, and the preset convolutional neural network is trained with a training data set including multiple training cell feature type parameters and corresponding prognostic evaluation annotations until convergence, and only the feature extraction convolution layer of the convolutional neural network is retained to obtain the vector feature extraction neural network.

[0008] As an optional embodiment, in the first aspect of the present invention, determining at least one prognosis effect prediction model from a plurality of candidate prediction models according to the parameter relationship data comprises: For each of the candidate prediction models, obtaining multiple data feature relationships of the model training data corresponding to the candidate prediction model; Calculating the relationship similarity between each of the data feature relationships and each of the fitting parameter relationships of the parameter relationship data; Calculate the average of all the relationship similarities corresponding to all the data feature relationships to obtain the model matching degree corresponding to the candidate prediction model; The candidate prediction model whose model matching degree is higher than a preset matching degree threshold is determined as the prognosis effect prediction model.

[0009] As an optional implementation, in the first aspect of the present invention, the candidate prediction model is trained by the following steps: Acquire a plurality of patient training data including type parameters of at least two of the cell feature types and corresponding prognosis assessment data; Dividing the patient training data set into a training part of data and a validation part of data; According to the training part data and the verification part data, the preset prediction model is trained and verified until convergence to obtain the candidate prediction model; the prediction model is a polynomial weighted model, a neural network model or a random forest model; Determining the part of the verification data whose prediction accuracy during verification is greater than a preset accuracy threshold as preferred data; The type parameters in the preferred data are input into the fitting algorithm model to obtain multiple data feature relationships corresponding to the candidate prediction model.

[0010] As an optional embodiment, in the first aspect of the present invention, the plurality of preset cell feature types are screened by the following steps: Acquire multiple patient data; the patient data includes patient information and corresponding type parameters of multiple candidate cell feature types and patient prognosis assessment annotations; According to the Lasso-cox regression model and a preset evaluation function, the evaluation function value corresponding to each of the candidate cell feature types is calculated according to the plurality of patient data; the evaluation function is a partial likelihood deviation or a C-index; According to the evaluation function value, multiple target cell feature types are screened out from all the candidate cell feature types.

[0011] As an optional embodiment, in the first aspect of the present invention, the prognostic risk score corresponding to the target patient is calculated according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type, comprising: For each of the prognostic effect prediction models, an associated parameter relationship is screened out from all the fitting parameter relationships; the average value of the relationship similarity between the associated parameter relationship and all the data feature relationships corresponding to the prognostic effect prediction model is greater than a preset parameter threshold; Inputting the type parameters corresponding to the cell feature types in all the associated parameter relationships into the prognostic effect prediction model to obtain an output model risk score; Calculate the weighted sum average of the model risk scores of all the prognostic effect prediction models to obtain the prognostic risk score corresponding to the target patient; wherein the weight corresponding to the model risk score of each prognostic effect prediction model includes a first weight and a second weight; the first weight is proportional to the model matching degree corresponding to the corresponding prognostic effect prediction model; the second weight is proportional to the number of types of the cell feature types in all the associated parameter relationships in the input data corresponding to the corresponding prognostic effect prediction model.

[0012] A second aspect of an embodiment of the present invention discloses a prognosis effect prediction system based on multiple features, the system comprising: An acquisition module, used for acquiring tissue cell images of a target patient; A first determination module is used to perform feature calculation on the tissue cell image to determine type parameters corresponding to a plurality of preset cell feature types; A second determination module is used to determine at least one corresponding prognosis effect prediction model according to a parameter relationship between type parameters corresponding to at least two of the cell feature types; A calculation module is used to calculate the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type.

[0013] As an optional embodiment, in the second aspect of the present invention, the cell feature type is a preset distribution feature of cells of a preset cell type within an area of ​​a preset area parameter type; the preset cell type includes at least one of CD3+ cells, PanCK+ cells, CD8+ cells and CD3+ / CD8- cells; the preset area parameter type includes at least one of an intra-tumor area, a tumor infiltration area, a tumor infiltration front area, a tumor preset outer expansion range area and a tumor preset inner contraction range area; the preset distribution feature includes at least one of a density feature, a graphic feature, a quantity ratio feature, a co-localization feature and an abundance feature.

[0014] As an optional embodiment, in the second aspect of the present invention, the second determination module determines the specific manner of at least one corresponding prognostic effect prediction model according to the parameter relationship between the type parameters corresponding to at least two of the cell feature types, including: Determine the preset cell type corresponding to the cell characteristic type corresponding to each of the type parameters corresponding to the tissue cell image, so as to obtain a plurality of image cell types corresponding to the tissue cell image; Determine the image cell type corresponding to at least two of the type parameters to obtain a multi-feature cell type; For each of the multi-feature cell types, grouping all of the type parameters corresponding to the multi-feature cell type to obtain a combination of parameters of the same type; Input each of the same type of parameter combinations into a corresponding fitting algorithm model to obtain a corresponding fitting parameter relationship; Determine the fitting parameter relationships corresponding to all the multi-feature cell types as parameter relationship data corresponding to the tissue cell image; At least one prognosis effect prediction model is determined from a plurality of candidate prediction models according to the parameter relationship data.

[0015] As an optional embodiment, in the second aspect of the present invention, the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same or the preset regional parameter types are the same; when the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a polynomial fitting model corresponding to the preset distribution characteristics corresponding to the same type parameter combination, and the polynomial fitting model is a density polynomial fitting model, a graphic parameter polynomial fitting model, a quantity proportion polynomial fitting model, a co-localization polynomial fitting model or an abundance polynomial fitting model; when the preset regional parameter types of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a trained vector feature extraction neural network, and the preset convolutional neural network is trained with a training data set including multiple training cell feature type parameters and corresponding prognostic evaluation annotations until convergence, and only the feature extraction convolution layer of the convolutional neural network is retained to obtain the vector feature extraction neural network.

[0016] As an optional implementation, in the second aspect of the present invention, the specific manner in which the second determination module determines at least one prognosis effect prediction model from a plurality of candidate prediction models according to the parameter relationship data includes: For each of the candidate prediction models, obtaining multiple data feature relationships of the model training data corresponding to the candidate prediction model; Calculating the relationship similarity between each of the data feature relationships and each of the fitting parameter relationships of the parameter relationship data; Calculate the average of all the relationship similarities corresponding to all the data feature relationships to obtain the model matching degree corresponding to the candidate prediction model; The candidate prediction model whose model matching degree is higher than a preset matching degree threshold is determined as the prognosis effect prediction model.

[0017] As an optional implementation, in the second aspect of the present invention, the candidate prediction model is trained by the following steps: Acquire a plurality of patient training data including type parameters of at least two of the cell feature types and corresponding prognosis assessment data; Dividing the patient training data set into a training part of data and a validation part of data; According to the training part data and the verification part data, the preset prediction model is trained and verified until convergence to obtain the candidate prediction model; the prediction model is a polynomial weighted model, a neural network model or a random forest model; Determining the part of the verification data whose prediction accuracy during verification is greater than a preset accuracy threshold as preferred data; The type parameters in the preferred data are input into the fitting algorithm model to obtain multiple data feature relationships corresponding to the candidate prediction model.

[0018] As an optional embodiment, in the second aspect of the present invention, the plurality of preset cell feature types are screened by the following steps: Acquire multiple patient data; the patient data includes patient information and corresponding type parameters of multiple candidate cell feature types and patient prognosis assessment annotations; According to the Lasso-cox regression model and a preset evaluation function, the evaluation function value corresponding to each of the candidate cell feature types is calculated according to the plurality of patient data; the evaluation function is a partial likelihood deviation or a C-index; According to the evaluation function value, multiple target cell feature types are screened out from all the candidate cell feature types.

[0019] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the calculation module calculates the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type includes: For each of the prognostic effect prediction models, an associated parameter relationship is screened out from all the fitting parameter relationships; the average value of the relationship similarity between the associated parameter relationship and all the data feature relationships corresponding to the prognostic effect prediction model is greater than a preset parameter threshold; Inputting the type parameters corresponding to the cell feature types in all the associated parameter relationships into the prognostic effect prediction model to obtain an output model risk score; Calculate the weighted sum average of the model risk scores of all the prognostic effect prediction models to obtain the prognostic risk score corresponding to the target patient; wherein the weight corresponding to the model risk score of each prognostic effect prediction model includes a first weight and a second weight; the first weight is proportional to the model matching degree corresponding to the corresponding prognostic effect prediction model; the second weight is proportional to the number of types of the cell feature types in all the associated parameter relationships in the input data corresponding to the corresponding prognostic effect prediction model.

[0020] The third aspect of the present invention discloses another prognosis effect prediction system based on multiple features, the system comprising: 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 part or all of the steps in the multi-feature-based prognostic effect prediction method disclosed in the first aspect of the present invention.

[0021] 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 multi-feature-based prognosis effect prediction method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can first perform feature calculation on tissue cell images based on multiple preset cell feature types to determine type parameters corresponding to multiple cell feature types, and then determine at least one corresponding prognosis effect prediction model through the parameter relationship between the type parameters corresponding to the cell feature types, so as to finally calculate the patient's corresponding prognosis risk score based on the prognosis effect prediction model according to the type parameters corresponding to the cell feature types, thereby making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flowchart of a prognosis effect prediction method based on multiple features disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of a prognosis effect prediction system based on multiple features disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another prognosis effect prediction system based on multiple features disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] 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.

[0029] 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.

[0030] The present invention discloses a prognosis effect prediction method and system based on multiple features, which can first perform feature calculation on tissue cell images based on multiple preset cell feature types to determine type parameters corresponding to multiple cell feature types, and then determine at least one corresponding prognosis effect prediction model through the parameter relationship between the type parameters corresponding to the cell feature types, so as to finally calculate the prognosis risk score corresponding to the patient based on the prognosis effect prediction model according to the type parameters corresponding to the cell feature types, so as to make full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 is a flow chart of a method for predicting prognosis effect based on multiple features disclosed in an embodiment of the present invention. Figure 1The described prognostic effect prediction method based on multiple features 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 prognosis effect prediction method based on multiple features may include the following operations: 101. Obtain tissue cell images of the target patient.

[0032] 102. Perform feature calculation on the tissue cell image to determine type parameters corresponding to a plurality of preset cell feature types. Specifically, the tissue cell image can be identified by a cell recognition model to obtain the cell region and cell type in the image, and then the cell region and cell type are calculated based on each cell feature type to obtain the corresponding type parameter.

[0033] 103. Determine at least one corresponding prognosis effect prediction model according to a parameter relationship between type parameters corresponding to at least two cell feature types. 104. Calculate the prognostic risk score corresponding to the target patient based on the prognostic effect prediction model and the type parameters corresponding to the cell feature type.

[0034] It can be seen that the above-mentioned embodiment of the invention can first perform feature calculation on the tissue cell image based on multiple preset cell feature types to determine the type parameters corresponding to the multiple cell feature types, and then determine at least one corresponding prognosis prediction model through the parameter relationship between the type parameters corresponding to the cell feature types, so as to finally calculate the patient's corresponding prognosis risk score based on the prognosis prediction model according to the type parameters corresponding to the cell feature types, thereby making full use of the relationship between cell features to accurately screen out the prognosis prediction model to achieve more accurate prognosis prediction, improve the prediction efficiency and accuracy of cancer prognosis prediction, and provide an accurate data basis for disease treatment or research.

[0035] As an optional embodiment, in the above steps, the cell feature type is a preset distribution feature of cells of a preset cell type in an area of ​​a preset area parameter type; the preset cell types include at least one of CD3+ cells, PanCK+ cells, CD8+ cells and CD3+ / CD8- cells; the preset area parameter types include at least one of an intra-tumor area, a tumor infiltration area, a tumor infiltration front area, a tumor preset outer expansion range area and a tumor preset inner contraction range area; the preset distribution feature includes at least one of a density feature, a graphic feature, a quantity ratio feature, a co-localization feature and an abundance feature.

[0036] Specifically, some examples of cell feature types may be multiple features of CD8+ cells, such as the mean, variance, maximum-minimum ratio, and discreteness of the Voronoi diagram polygon area of ​​CD8+ cells, the mean, variance, maximum-minimum ratio, and discreteness of the number of cells in the 1000um area outside the tumor, or co-localization features or abundance features between different types of cells, such as dividing the selected area into square areas of fixed size, calculating the number of first-type cells N1 and the number of second-type cells N2 in each square area, and then calculating the first-type cell proportion P1=N1 / (N1+N2) and the second-type cell proportion P2=N2 / (N1+N2) in each square area, and calculating the abundance T and co-localization feature M based on the proportion values ​​of the two types of cells in each block, wherein the calculation formula of the co-localization feature M is: ; The calculation formula for abundance T is: ; Among them, the superscript i Representative i A square area, N Represents the number of square areas cut out from the selected area.

[0037] It can be seen that through the above optional embodiments, the content of the cell feature type is limited to achieve accurate representation of cell features, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0038] As an optional embodiment, in the above step, determining at least one corresponding prognosis effect prediction model according to the parameter relationship between type parameters corresponding to at least two cell feature types includes: Determine a preset cell type corresponding to a cell characteristic type corresponding to each type parameter corresponding to the tissue cell image, so as to obtain a plurality of image cell types corresponding to the tissue cell image; Determine the image cell type corresponding to at least two type parameters to obtain a multi-feature cell type; For each multi-feature cell type, all type parameters corresponding to the multi-feature cell type are grouped to obtain a combination of parameters of the same type; Input each parameter combination of the same type into the corresponding fitting algorithm model to obtain the corresponding fitting parameter relationship; The fitting parameter relationships corresponding to all multi-feature cell types are determined as parameter relationship data corresponding to the tissue cell image; At least one prognosis effect prediction model is determined from a plurality of candidate prediction models according to the parameter relationship data.

[0039] It can be seen that through the above optional embodiments, feature screening can be performed based on patient data and the Lasso-cox regression model to determine multiple cell feature types with higher correlation, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0040] As an optional embodiment, in the above steps, the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same or the preset regional parameter types are the same; when the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a polynomial fitting model corresponding to the preset distribution characteristics corresponding to the same type parameter combination, and the polynomial fitting model is a density polynomial fitting model, a graphic parameter polynomial fitting model, a quantity proportion polynomial fitting model, a co-localization polynomial fitting model or an abundance polynomial fitting model; when the preset regional parameter types of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a trained vector feature extraction neural network, and the preset convolutional neural network is trained with a training data set including multiple training cell feature type parameters and corresponding prognostic evaluation annotations until convergence, and only the feature extraction convolution layer of the convolutional neural network is retained to obtain a vector feature extraction neural network.

[0041] It can be seen that through the above optional embodiments, the details of the cell feature relationship between type parameters and the corresponding parameter relationship fitting algorithm model are clarified, so as to accurately analyze the parameter relationship between type parameters, and subsequently realize accurate risk prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0042] As an optional embodiment, in the above step, determining at least one prognosis effect prediction model from a plurality of candidate prediction models according to the parameter relationship data includes: For each candidate prediction model, obtaining multiple data feature relationships of model training data corresponding to the candidate prediction model; Calculate the relationship similarity between each data feature relationship and each fitting parameter relationship of the parameter relationship data; Calculate the average of all relationship similarities corresponding to all data feature relationships to obtain the model matching degree corresponding to the candidate prediction model; The candidate prediction model whose model matching degree is higher than the preset matching degree threshold is determined as the prognosis effect prediction model.

[0043] It can be seen that through the above-mentioned optional embodiments, the model matching degree can be determined based on the similarity between the data feature relationship of the model training data of the candidate prediction model and the parameter relationship of the tissue cell image of the current patient, so as to screen out a suitable prognosis effect prediction model, and subsequently achieve a more accurate prognosis effect prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve a more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0044] As an optional embodiment, in the above steps, the candidate prediction model is trained by the following steps: Acquire a plurality of patient training data including type parameters of at least two cell feature types and corresponding prognosis assessment data; The patient training data set is divided into training part data and validation part data; According to the training data and the verification data, the preset prediction model is trained and verified until convergence to obtain a candidate prediction model; optionally, the prediction model is a polynomial weighted model, a neural network model or a random forest model; Determine as preferred data the part of the verification data whose prediction accuracy during verification is greater than a preset accuracy threshold; The type parameters in the preferred data are input into the fitting algorithm model to obtain multiple data feature relationships corresponding to the candidate prediction model.

[0045] It can be seen that through the above optional embodiments, the preset model can be trained based on the patient training data and the cell feature relationship in the data set with higher verification effect can be fitted and calculated, so as to facilitate model screening and accurate prognosis effect prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0046] As an optional embodiment, in the above steps, the plurality of preset cell feature types are screened and obtained by the following steps: Acquire multiple patient data; optionally, the patient data includes patient information and corresponding type parameters of multiple candidate cell feature types and patient prognosis assessment annotations; According to the Lasso-cox regression model and the preset evaluation function, the evaluation function value corresponding to each candidate cell feature type is calculated according to the multiple patient data; optionally, the evaluation function is a partial likelihood deviation or a C-index; According to the evaluation function value, multiple target cell feature types are screened out from all candidate cell feature types.

[0047] In a specific implementation scheme, a feature screening model is implemented, multiple features are incorporated, and a Lasso-Cox regression model is used to screen features and train the model.

[0048] First, the features are preprocessed into binarization to obtain the median of each feature value in the training set. If the feature value is greater than or equal to the median, it is set to 1, and if it is less than the median, it is set to 0. The samples of the validation and test sets are also binarized based on the median value of the features of the training set.

[0049] Feature screening is performed based on two models. One is the DFS model. The Lasso-cox regression model with 10-fold cross validation is used for feature screening on the training set. The evaluation function selected is the partial likelihood deviation value. The feature corresponding to the lamba value with the smallest partial likelihood deviation value is selected. The other is the OS model. The Lasso-cox regression model with 10-fold cross validation is used for feature screening on the training set. The evaluation function selected is C-index. The feature corresponding to the lamba value corresponding to the maximum C-index value is selected.

[0050] It can be seen that through the above optional embodiments, feature screening can be performed based on patient data and the Lasso-cox regression model to determine multiple cell feature types with higher correlation, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0051] As an optional embodiment, in the above steps, the prognostic risk score corresponding to the target patient is calculated according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type, including: For each prognostic effect prediction model, the associated parameter relationship is screened out from all the fitting parameter relationships; optionally, the average value of the relationship similarity between the associated parameter relationship and all the data feature relationships corresponding to the prognostic effect prediction model is greater than a preset parameter threshold; Inputting the type parameters corresponding to the cell feature types in all associated parameter relationships into the prognostic effect prediction model to obtain an output model risk score; Calculate the weighted sum average of the model risk scores of all prognostic effect prediction models to obtain the prognostic risk score corresponding to the target patient; optionally, the weight corresponding to the model risk score of each prognostic effect prediction model includes a first weight and a second weight; the first weight is proportional to the model matching degree corresponding to the corresponding prognostic effect prediction model; the second weight is proportional to the number of cell feature types in all associated parameter relationships in the input data corresponding to the corresponding prognostic effect prediction model.

[0052] It can be seen that through the above optional embodiments, the input type parameters corresponding to each prognosis prediction model can be screened out based on the relationship similarity to achieve model scoring, and then the score can be accurately weighted calculated based on the weight rules related to the model matching degree and the number of feature types, so as to make full use of the relationship between cell features to accurately screen out the prognosis prediction model to achieve more accurate prognosis prediction, improve the prediction efficiency and accuracy of cancer prognosis prediction, and provide an accurate data basis for disease treatment or research.

[0053] Embodiment 2 See also Figure 2 , Figure 2 is a schematic diagram of the structure of a prognosis effect prediction system based on multiple features disclosed in an embodiment of the present invention. Figure 2 The described prognosis effect prediction system based on multiple features 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 prognosis effect prediction system based on multiple features may include: The acquisition module 201 is used to acquire the tissue cell image of the target patient.

[0054] The first determination module 202 is used to perform feature calculation on the tissue cell image and determine type parameters corresponding to a plurality of preset cell feature types. The second determination module 203 is used to determine at least one corresponding prognosis effect prediction model according to the parameter relationship between type parameters corresponding to at least two cell feature types. The calculation module 204 is used to calculate the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type.

[0055] It can be seen that the above-mentioned embodiment of the invention can first perform feature calculation on the tissue cell image based on multiple preset cell feature types to determine the type parameters corresponding to the multiple cell feature types, and then determine at least one corresponding prognosis prediction model through the parameter relationship between the type parameters corresponding to the cell feature types, so as to finally calculate the patient's corresponding prognosis risk score based on the prognosis prediction model according to the type parameters corresponding to the cell feature types, thereby making full use of the relationship between cell features to accurately screen out the prognosis prediction model to achieve more accurate prognosis prediction, improve the prediction efficiency and accuracy of cancer prognosis prediction, and provide an accurate data basis for disease treatment or research.

[0056] As an optional embodiment, the cell feature type is a preset distribution feature of cells of a preset cell type within an area of ​​a preset area parameter type; the preset cell types include at least one of CD3+ cells, PanCK+ cells, CD8+ cells and CD3+ / CD8- cells; the preset area parameter types include at least one of an intra-tumor area, a tumor infiltration area, a tumor infiltration front area, a tumor preset outer expansion range area and a tumor preset inner contraction range area; the preset distribution feature includes at least one of a density feature, a graphic feature, a quantity ratio feature, a co-localization feature and an abundance feature.

[0057] It can be seen that through the above optional embodiments, the content of the cell feature type is limited to achieve accurate representation of cell features, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0058] As an optional embodiment, the second determination module determines the specific manner of at least one corresponding prognostic effect prediction model according to the parameter relationship between the type parameters corresponding to at least two cell feature types, including: Determine a preset cell type corresponding to a cell characteristic type corresponding to each type parameter corresponding to the tissue cell image, so as to obtain a plurality of image cell types corresponding to the tissue cell image; Determine the image cell type corresponding to at least two type parameters to obtain a multi-feature cell type; For each multi-feature cell type, all type parameters corresponding to the multi-feature cell type are grouped to obtain a combination of parameters of the same type; Input each parameter combination of the same type into the corresponding fitting algorithm model to obtain the corresponding fitting parameter relationship; The fitting parameter relationships corresponding to all multi-feature cell types are determined as parameter relationship data corresponding to the tissue cell image; At least one prognosis effect prediction model is determined from a plurality of candidate prediction models according to the parameter relationship data.

[0059] It can be seen that through the above-mentioned optional embodiments, the model matching degree can be determined based on the similarity between the data feature relationship of the model training data of the candidate prediction model and the parameter relationship of the tissue cell image of the current patient, so as to screen out a suitable prognosis effect prediction model, and subsequently achieve a more accurate prognosis effect prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve a more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0060] As an optional embodiment, the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same or the preset regional parameter types are the same; when the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a polynomial fitting model corresponding to the preset distribution characteristics corresponding to the same type parameter combination, and the polynomial fitting model is a density polynomial fitting model, a graphic parameter polynomial fitting model, a quantity proportion polynomial fitting model, a co-localization polynomial fitting model or an abundance polynomial fitting model; when the preset regional parameter types of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a trained vector feature extraction neural network, and the preset convolutional neural network is trained with a training data set including multiple training cell feature type parameters and corresponding prognostic evaluation annotations until convergence, and only the feature extraction convolution layer of the convolutional neural network is retained to obtain a vector feature extraction neural network.

[0061] It can be seen that through the above optional embodiments, the details of the cell feature relationship between type parameters and the corresponding parameter relationship fitting algorithm model are clarified, so as to accurately analyze the parameter relationship between type parameters, and subsequently realize accurate risk prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0062] As an optional embodiment, the specific manner in which the second determination module determines at least one prognosis effect prediction model from a plurality of candidate prediction models according to the parameter relationship data includes: For each candidate prediction model, obtaining multiple data feature relationships of model training data corresponding to the candidate prediction model; Calculate the relationship similarity between each data feature relationship and each fitting parameter relationship of the parameter relationship data; Calculate the average of all relationship similarities corresponding to all data feature relationships to obtain the model matching degree corresponding to the candidate prediction model; The candidate prediction model whose model matching degree is higher than the preset matching degree threshold is determined as the prognosis effect prediction model.

[0063] It can be seen that through the above optional embodiments, feature screening can be performed based on patient data and the Lasso-cox regression model to determine multiple cell feature types with higher correlation, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0064] As an optional embodiment, the candidate prediction model is trained by the following steps: Acquire a plurality of patient training data including type parameters of at least two cell feature types and corresponding prognosis assessment data; The patient training data set is divided into training part data and validation part data; According to the training data and the verification data, the preset prediction model is trained and verified until convergence to obtain a candidate prediction model; optionally, the prediction model is a polynomial weighted model, a neural network model or a random forest model; Determine as preferred data the part of the verification data whose prediction accuracy during verification is greater than a preset accuracy threshold; The type parameters in the preferred data are input into the fitting algorithm model to obtain multiple data feature relationships corresponding to the candidate prediction model.

[0065] It can be seen that through the above optional embodiments, the preset model can be trained based on the patient training data and the cell feature relationship in the data set with higher verification effect can be fitted and calculated, so as to facilitate model screening and accurate prognosis effect prediction, and assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0066] As an optional embodiment, a plurality of preset cell feature types are screened and obtained by the following steps: Acquire multiple patient data; optionally, the patient data includes patient information and corresponding type parameters of multiple candidate cell feature types and patient prognosis assessment annotations; According to the Lasso-cox regression model and the preset evaluation function, the evaluation function value corresponding to each candidate cell feature type is calculated according to the multiple patient data; optionally, the evaluation function is a partial likelihood deviation or a C-index; According to the evaluation function value, multiple target cell feature types are screened out from all candidate cell feature types.

[0067] It can be seen that through the above optional embodiments, feature screening can be performed based on patient data and the Lasso-cox regression model to determine multiple cell feature types with higher correlation, and subsequently achieve more accurate prognosis effect prediction, assist in making full use of the relationship between cell features to accurately screen out the prognosis effect prediction model to achieve more accurate prognosis effect prediction, improve the prediction efficiency and accuracy of cancer prognosis effect prediction, and provide an accurate data basis for disease treatment or research.

[0068] As an optional embodiment, the specific method in which the calculation module calculates the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type includes: For each prognostic effect prediction model, the associated parameter relationship is screened out from all the fitting parameter relationships; optionally, the average value of the relationship similarity between the associated parameter relationship and all the data feature relationships corresponding to the prognostic effect prediction model is greater than a preset parameter threshold; Inputting the type parameters corresponding to the cell feature types in all associated parameter relationships into the prognostic effect prediction model to obtain an output model risk score; Calculate the weighted sum average of the model risk scores of all prognostic effect prediction models to obtain the prognostic risk score corresponding to the target patient; optionally, the weight corresponding to the model risk score of each prognostic effect prediction model includes a first weight and a second weight; the first weight is proportional to the model matching degree corresponding to the corresponding prognostic effect prediction model; the second weight is proportional to the number of cell feature types in all associated parameter relationships in the input data corresponding to the corresponding prognostic effect prediction model.

[0069] It can be seen that through the above optional embodiments, the input type parameters corresponding to each prognosis prediction model can be screened out based on the relationship similarity to achieve model scoring, and then the score can be accurately weighted calculated based on the weight rules related to the model matching degree and the number of feature types, so as to make full use of the relationship between cell features to accurately screen out the prognosis prediction model to achieve more accurate prognosis prediction, improve the prediction efficiency and accuracy of cancer prognosis prediction, and provide an accurate data basis for disease treatment or research.

[0070] Embodiment 3 See also Figure 3 , Figure 3 It is another prognosis effect prediction system based on multiple features disclosed in an embodiment of the present invention. Figure 3 The described prognosis effect prediction system based on multiple features 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 prognosis effect prediction system based on multiple features may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the prognosis effect prediction method based on multiple features described in the first embodiment.

[0071] Embodiment 4 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 prognosis effect prediction method based on multiple features described in the first embodiment.

[0072] Embodiment 5 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 prognosis effect prediction method based on multiple features described in Example 1.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] 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 comprising 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.

[0079] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] Finally, it should be noted that the multi-feature-based prognosis effect prediction method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, which are 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 described in the aforementioned embodiments can still be modified, or some of the technical features 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 prognosis effect prediction method based on multiple features, characterized in that: The method comprises: Acquire tissue cell images of target patients; Performing feature calculation on the tissue cell image to determine type parameters corresponding to a plurality of preset cell feature types; Determining at least one corresponding prognostic effect prediction model according to a parameter relationship between type parameters corresponding to at least two of the cell feature types; The prognostic risk score corresponding to the target patient is calculated according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type.

2. The method for predicting prognosis based on multiple features according to claim 1, characterized in that: The cell feature type is a preset distribution feature of cells of a preset cell type within an area of ​​a preset area parameter type; the preset cell type includes at least one of CD3+ cells, PanCK+ cells, CD8+ cells and CD3+ / CD8- cells; the preset area parameter type includes at least one of an intra-tumor area, a tumor infiltration area, a tumor infiltration front area, a tumor preset outer expansion range area and a tumor preset inner contraction range area; the preset distribution feature includes at least one of a density feature, a graphic feature, a quantity ratio feature, a co-localization feature and an abundance feature.

3. The prognosis effect prediction method based on multiple features according to claim 1, characterized in that: Determining at least one corresponding prognosis effect prediction model according to the parameter relationship between the type parameters corresponding to at least two of the cell feature types comprises: Determine the preset cell type corresponding to the cell characteristic type corresponding to each of the type parameters corresponding to the tissue cell image, so as to obtain a plurality of image cell types corresponding to the tissue cell image; Determine the image cell type corresponding to at least two of the type parameters to obtain a multi-feature cell type; For each of the multi-feature cell types, grouping all of the type parameters corresponding to the multi-feature cell type to obtain a combination of parameters of the same type; Input each of the same type of parameter combinations into a corresponding fitting algorithm model to obtain a corresponding fitting parameter relationship; Determine the fitting parameter relationships corresponding to all the multi-feature cell types as parameter relationship data corresponding to the tissue cell image; At least one prognosis effect prediction model is determined from a plurality of candidate prediction models according to the parameter relationship data.

4. The method for predicting prognosis based on multiple features according to claim 3, characterized in that: The preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same or the preset regional parameter types are the same; when the preset distribution characteristics of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a polynomial fitting model corresponding to the preset distribution characteristics corresponding to the same type parameter combination, and the polynomial fitting model is a density polynomial fitting model, a graphic parameter polynomial fitting model, a quantity proportion polynomial fitting model, a co-localization polynomial fitting model or an abundance polynomial fitting model; when the preset regional parameter types of the cell feature types corresponding to the type parameters in the same type parameter combination are the same, the fitting algorithm model is a trained vector feature extraction neural network, and the preset convolutional neural network is trained with a training data set including multiple training cell feature type parameters and corresponding prognosis evaluation annotations until convergence, and only the feature extraction convolution layer of the convolutional neural network is retained to obtain the vector feature extraction neural network.

5. The method for predicting prognosis based on multiple features according to claim 3, characterized in that: Determining at least one prognosis effect prediction model from a plurality of candidate prediction models according to the parameter relationship data includes: For each of the candidate prediction models, obtaining multiple data feature relationships of the model training data corresponding to the candidate prediction model; Calculating the relationship similarity between each of the data feature relationships and each of the fitting parameter relationships of the parameter relationship data; Calculate the average of all the relationship similarities corresponding to all the data feature relationships to obtain the model matching degree corresponding to the candidate prediction model; The candidate prediction model whose model matching degree is higher than a preset matching degree threshold is determined as the prognosis effect prediction model.

6. The method for predicting prognosis based on multiple features according to claim 5, characterized in that: The candidate prediction model is trained by the following steps: Acquire a plurality of patient training data including type parameters of at least two of the cell feature types and corresponding prognosis assessment data; Dividing the patient training data set into a training part of data and a validation part of data; According to the training part data and the verification part data, the preset prediction model is trained and verified until convergence to obtain the candidate prediction model; the prediction model is a polynomial weighted model, a neural network model or a random forest model; Determining the part of the verification data whose prediction accuracy during verification is greater than a preset accuracy threshold as preferred data; The type parameters in the preferred data are input into the fitting algorithm model to obtain multiple data feature relationships corresponding to the candidate prediction model.

7. The method for predicting prognosis based on multiple features according to claim 1, characterized in that: The plurality of preset cell feature types are screened by the following steps: Acquire multiple patient data; the patient data includes patient information and corresponding type parameters of multiple candidate cell feature types and patient prognosis assessment annotations; According to the Lasso-cox regression model and a preset evaluation function, the evaluation function value corresponding to each of the candidate cell feature types is calculated according to the plurality of patient data; the evaluation function is a partial likelihood deviation or a C-index; According to the evaluation function value, multiple target cell feature types are screened out from all the candidate cell feature types.

8. The method for predicting prognosis based on multiple features according to claim 5, characterized in that: Calculating the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type includes: For each of the prognostic effect prediction models, an associated parameter relationship is screened out from all the fitting parameter relationships; the average value of the relationship similarity between the associated parameter relationship and all the data feature relationships corresponding to the prognostic effect prediction model is greater than a preset parameter threshold; Inputting the type parameters corresponding to the cell feature types in all the associated parameter relationships into the prognostic effect prediction model to obtain an output model risk score; Calculate the weighted sum average of the model risk scores of all the prognostic effect prediction models to obtain the prognostic risk score corresponding to the target patient; wherein the weight corresponding to the model risk score of each prognostic effect prediction model includes a first weight and a second weight; the first weight is proportional to the model matching degree corresponding to the corresponding prognostic effect prediction model; the second weight is proportional to the number of types of the cell feature types in all the associated parameter relationships in the input data corresponding to the corresponding prognostic effect prediction model.

9. A prognosis effect prediction system based on multiple features, characterized in that: The system comprises: An acquisition module, used for acquiring tissue cell images of a target patient; A first determination module is used to perform feature calculation on the tissue cell image to determine type parameters corresponding to a plurality of preset cell feature types; A second determination module is used to determine at least one corresponding prognosis effect prediction model according to a parameter relationship between type parameters corresponding to at least two of the cell feature types; A calculation module is used to calculate the prognostic risk score corresponding to the target patient according to the prognostic effect prediction model and the type parameter corresponding to the cell feature type.

10. A prognosis effect prediction system based on multiple features, 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 the prognostic effect prediction method based on multiple features as described in any one of claims 1-8.

Images