Prognosis survival prediction model construction method and prediction method

By constructing a prognostic survival prediction model based on the spatial positional relationship of myeloid cell, the shortcomings in the evaluation of the efficacy of immune checkpoint drugs in the prior art are solved, and a more accurate tumor prognosis judgment is achieved.

CN119007201AActive Publication Date: 2024-11-22HANGZHOU INPHITOMICS BIOTECHNOLOGY CO LTD

Patent Information

Application Number
CN202411491118.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-22
Estimated Expiration
2044-10-23

AI Technical Summary

Technical Problem

The existing cancer treatment effect prediction is mainly focused on lytic immune checkpoints, which cannot effectively evaluate and predict the efficacy of myeloid cell immune checkpoint drugs, and there is subjectivity and inaccuracy in clinical prognosis judgments, and there is a lack of cell spatial position relationships. Machine learning model.

Method used

By obtaining fluorescent sample images of sample tissue before treatment, segmenting and annotating myeloid cells, calculating the spatial distance and interaction relationship between cells, we construct a prognostic survival prediction model based on the spatial positional relationship of myeloid cells to predict tumor survival. .

Benefits of technology

It provides a more accurate and reliable prognostic survival prediction model, which provides a strong reference for clinical judgment of tumor prognostic survival, and improves the prediction accuracy and robustness of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007201A_ABST
    Figure CN119007201A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, and discloses a prognosis survival prediction model construction method and prediction method.The construction method comprises the steps that fluorescence sample images corresponding to sample tissues one by one before treatment and prognosis information of patients corresponding to the sample tissues are obtained; segmenting the myeloid cells, and determining the fluorescence expression quantity of each myeloid cell on different markers; determining the spatial distance from each myeloid cell in each sample tissue to other different types of myeloid cells to obtain cell spatial distance characteristics; determining a space interaction relationship between each myeloid cell in each sample tissue and surrounding cells to obtain cell interaction characteristics; dividing a training set and a test set; and constructing a prognosis survival prediction model based on cell spatial distance characteristics and cell interaction characteristics in the training set and the test set. The prognosis survival prediction model based on the myeloid cell space position relation is constructed, and a powerful reference basis is provided for clinically judging the tumor prognosis survival condition.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a prognosis survival prediction model construction method and a prediction method. Background Art

[0002] Myeloid refers to myeloid cells, which are cells differentiated from bone marrow hematopoietic stem cells, including granulocytes, red blood cells, macrophages and monocytes. Myeloid cells are hematopoietic cells in a narrow sense, while lymphocytes are considered non-hematopoietic cells. Different types of cells have different physiological functions in the body, but they all have certain significance for the normal life activities of the body.

[0003] Myeloid checkpoints refer to molecular signaling pathways and molecular regulatory factors that play a key regulatory role in the bone marrow hematopoietic system. The function of myeloid checkpoints is to ensure the balance and stability of the hematopoietic process and maintain the normal function of the blood system. Disturbance of myeloid checkpoints may lead to abnormal hematopoietic function and the occurrence of blood diseases.

[0004] In current immunotherapy, especially for the prediction of treatment effects for cancer patients, the focus is mainly on the research and application of lymphoid immune checkpoints (such as PD-1, PD-L1 and CTLA4), which mainly act on lymphocytes such as T cells. For myeloid immune checkpoints (such as CD47, LILRB1, CD171), there are relatively few current research and detection methods. In addition, the existing PD-1 and PD-L1 tests are mainly for the evaluation of lymphoid immune responses, and cannot predict or evaluate the efficacy of myeloid cell immune checkpoint drugs.

[0005] In addition, the current clinical prognosis of the effect of myeloid cell immune checkpoint drug treatment is mainly judged by clinicians based on imaging images and test results, which is subjective and inaccurate. There is currently a lack of a machine learning model based on the spatial position relationship of cells to provide a reference for clinical prognosis and survival of tumors. Summary of the invention

[0006] In view of this, the present invention provides a method for constructing a prognosis survival prediction model and a prediction method to provide a reference for clinical prognosis survival of tumors.

[0007] In a first aspect, the present invention provides a method for constructing a prognosis survival prediction model, the method comprising: Obtaining fluorescent sample images corresponding to sample tissues before treatment, wherein the fluorescent sample images are obtained after staining with antibodies for markers of myeloid cells; Obtaining prognostic information of the patient corresponding to the sample tissue, the prognostic information including the patient's survival status after receiving different preset treatment methods; Segment the myeloid cells in each sample tissue based on the fluorescent sample image, and determine the fluorescence expression amount of each myeloid cell on different markers; wherein, each fluorescent sample image is divided into regions to obtain multiple regional images corresponding to each fluorescent sample image; determine the position of the nucleus of the myeloid cell according to the fluorescence expression amount corresponding to the regional image; and segment the complete myeloid cell corresponding to the nucleus based on the position of the nucleus; Determine the myeloid cell type annotation of each myeloid cell based on the fluorescence expression of each myeloid cell on different markers and the cell type annotation algorithm; Based on the myeloid cell type annotations, the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells is determined to obtain the cell spatial distance characteristics; Based on the annotation of myeloid cell types, the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue was determined to obtain the cell interaction characteristics; Divide the sample tissue into training set and test set according to the preset ratio and prognostic information; A prognostic survival prediction model was constructed based on the cell spatial distance characteristics and cell interaction characteristics in the training set and the test set. The prognostic survival prediction model was used to predict the survival of pathological samples after intervention.

[0008] The present invention provides a method for constructing a prognosis prediction model for myeloid cells. The method extracts the characteristics of cells in the spatial field through cell segmentation, cell annotation, distance calculation, interaction analysis and other aspects of fluorescent sample images, extracts the characteristics between cells at the cellular level, and constructs a prognosis survival prediction model based on the spatial position relationship of myeloid cells based on these spatial characteristics, which provides a strong reference basis for clinical judgment of tumor prognosis and survival.

[0009] In an optional embodiment, the marker antibody is selected from one or more of the following: CD45, CD45RA, CD45RO, CD11b, CD11c, CD14, CD15, CD16, CD33, CD68, CD86, CD163, CD206, SPP1, FOLR2, C1QC, CD1c, HLA-DR, CD141, S100A9, S100A8, CD117, CD123, MPO.

[0010] In an optional embodiment, each regional image includes a cancer region and a paracancerous region, and the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells is determined to obtain a cell spatial distance feature, including: determining a first Euclidean distance between each myeloid cell type and other different types of myeloid cells in the cancerous region included in each region image; Determine the second Euclidean distance between each myeloid cell type and other different types of myeloid cells in the adjacent cancer region included in each regional image; Based on all the first Euclidean distances, determining a first spatial distance between each myeloid cell and other different types of myeloid cells in all cancerous areas of the sample tissue, the first spatial distance comprising: a first minimum spatial distance, a first maximum spatial distance, and a first average spatial distance; Based on all the second Euclidean distances, determining the second spatial distances between each myeloid cell and other different types of myeloid cells in all paracancerous regions of the sample tissue, wherein the second spatial distances include: a second minimum spatial distance, a second maximum spatial distance, and a second average spatial distance; The first spatial distance and the second spatial distance are used as cell spatial distance features; After obtaining the cell space distance features, including: The distance features between the same myeloid cell types in the cell space distance features are subjected to data processing and feature screening to obtain processed cell space distance features, and the processed cell space distance features are used to construct a prognosis survival prediction model.

[0011] In this embodiment, by calculating the spatial distances between different types of myeloid cells, we can gain a deeper understanding of the interaction and spatial distribution characteristics of cells in the tumor microenvironment. In addition, this embodiment also analyzes the difference in spatial distances between myeloid cells in the cancerous area and the adjacent area, taking into account the cell changes during the development of the tumor, etc., which helps to improve the comprehensiveness of the analysis and the prediction accuracy of the constructed model.

[0012] In this embodiment, data processing and feature screening of distance features between the same myeloid cell types can improve the accuracy and robustness of the model, help better capture the characteristic relationship between cells, and provide stronger support for prognosis and survival prediction.

[0013] In an optional embodiment, each regional image includes a cancer region and a paracancerous region, and the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue is determined to obtain cell interaction characteristics, including: Determine a first interaction feature between each myeloid cell in the cancer region included in each regional image and surrounding interacting cells having an interacting relationship; Determine a second interaction feature between each myeloid cell and surrounding interacting cells having an interacting relationship in the peritumoral region included in each regional image; wherein the first interaction feature and the second interaction feature both include the proportion of each myeloid cell type in the interacting cells having an interacting relationship; The first interaction feature and the second interaction feature are used as cell interaction features.

[0014] In this embodiment, using the interaction relationship between two cells in space as an important reference indicator for disease prognosis can not only improve the accuracy and reliability of the prognosis survival prediction model, but also provide important information support for clinical decision-making.

[0015] In an optional embodiment, the features used to construct the prognosis survival prediction model include one or more of the following: T_MonoToM2_max, T_M1ToM2_mean, T_MonoToM2_mean, P_M2ToHLADRhicells_max, P_MonoToHLADRhicells_max, P_HLADRhicellsToMono_min P_MonoToHLADRhicells_min P_M2ToMono_mean, T_HLADRhicells_M2, T_M1_M1, T_M1_M2, T_M2_M1, T_M2_M2, T_Mono_M2, T_Neutro_M2, P_M2_Mono.

[0016] In a second aspect, the present invention provides a method for predicting prognosis and survival, the method comprising: Acquire a fluorescent sample image of a pathological sample to be predicted; The fluorescent sample image is input into the prognosis survival prediction model constructed according to the prognosis survival prediction model construction method described in any of the above embodiments, and the survival status of the pathological sample to be predicted after the intervention is output.

[0017] In a third aspect, the present invention provides a device for constructing a prognosis survival prediction model, the device comprising: An acquisition module is used to obtain a fluorescent sample image corresponding to the sample tissue before treatment, the fluorescent sample image is obtained after staining with antibodies for myeloid cell markers; it is also used to obtain the prognosis information of the patient corresponding to the sample tissue, the prognosis information includes the survival status of the patient after receiving different preset treatment methods; A segmentation module is used to segment the myeloid cells in each sample tissue based on the fluorescent sample image, and determine the fluorescence expression amount of each myeloid cell on different markers; wherein, each of the fluorescent sample images is divided into regions to obtain a plurality of regional images corresponding to each of the fluorescent sample images; the position of the nucleus of the myeloid cell is determined according to the fluorescence expression amount corresponding to the regional image; and based on the position of the nucleus, the complete myeloid cell corresponding to the nucleus is segmented; An annotation module, for determining a myeloid cell type annotation for each myeloid cell based on the fluorescence expression of each myeloid cell on different markers and a cell type annotation algorithm; A distance feature extraction module is used to determine the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells based on myeloid cell type annotations, and obtain cell spatial distance features; The interaction feature extraction module is used to determine the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue based on myeloid cell type annotations to obtain cell interaction features; A partitioning module is used to divide the sample tissue into a training set and a test set according to a preset ratio and prognostic information; A construction module is used to construct a prognosis survival prediction model based on the cell spatial distance characteristics and cell interaction characteristics in the training set and the test set. The prognosis survival prediction model is used to predict the survival of pathological samples after intervention.

[0018] In a fourth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for constructing a prognosis survival prediction model according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0019] In a fifth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method for constructing a prognosis survival prediction model according to the first aspect or any corresponding embodiment thereof.

[0020] In a sixth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the method for constructing a prognosis survival prediction model according to the first aspect or any corresponding embodiment thereof.

[0021] It should be noted that the prognosis survival prediction model construction device, computer device and computer readable storage medium provided by the present invention correspond to the above-mentioned prognosis survival prediction model construction method. Therefore, for the beneficial effects of the prognosis survival prediction model construction device, computer device and computer readable storage medium, please refer to the description of the corresponding beneficial effects of the prognosis survival prediction model construction method above, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1is a flow chart of a method for constructing a prognosis survival prediction model according to an embodiment of the present invention; Figure 2 is a schematic diagram of sample information according to an embodiment of the present invention; Figure 3 is a schematic diagram of a fluorescent sample image scanning result according to an embodiment of the present invention; Figure 4 is a schematic diagram of a fluorescent sample image after segmentation according to an embodiment of the present invention; Figure 5 is a schematic diagram of an annotated fluorescent sample image according to an embodiment of the present invention; Figure 6 is a schematic diagram of a heat map after standardization according to an embodiment of the present invention; Figure 7 is a schematic diagram of an ROC curve of a training set according to an embodiment of the present invention; Figure 8 is a visualization diagram of other evaluation indicators of the training set according to an embodiment of the present invention; Fig. 9 is a schematic diagram of an ROC curve of a validation set according to an embodiment of the present invention; Fig.10 is a visualization diagram of other evaluation indicators of the validation set according to an embodiment of the present invention; Fig.11 is a schematic diagram of the importance of features in a model according to an embodiment of the present invention; Fig.12 is a schematic diagram of a feature importance scoring line according to an embodiment of the present invention; Fig.13 is a schematic diagram of the impact of 16 features on model performance according to an embodiment of the present invention; Fig.14 is a structural block diagram of a device for constructing a prognosis survival prediction model according to an embodiment of the present invention; Fig.15 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] The existing treatment effect prediction mainly targets lymphocyte immune checkpoints, such as PD-1, PD-L1, and CTLA4. However, there are also immune checkpoint drugs targeting myeloid cells on the market, such as CD47, LILRB1, and CD171. The existing PD-1 and PD-L1 tests cannot predict or evaluate the efficacy of such myeloid cell immune checkpoint drugs. Therefore, it is urgent to propose a model or method for prognosis prediction based on myeloid cells.

[0026] According to an embodiment of the present invention, an embodiment of a method for constructing a prognosis survival prediction model is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] In this embodiment, a method for constructing a prognosis survival prediction model is provided, which can be executed by a server, a terminal, a mobile terminal, etc. Figure 1 is a flowchart of a method for constructing a prognosis survival prediction model according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps: Step S101, obtaining a fluorescent sample image corresponding to the sample tissue before treatment, the fluorescent sample image is obtained after staining with antibodies for myeloid cell markers; obtaining the prognostic information of the patient corresponding to the sample tissue, the prognostic information may include the survival status of the patient after receiving different preset treatment methods. Among them, different treatment methods include surgical resection, radiotherapy and chemotherapy, immunotherapy and targeted therapy, etc., and the survival status may include the survival time, that is, the prognostic information may include the survival time of the patient after receiving a certain treatment method.

[0028] In this embodiment, a specific example is given. In this embodiment, 90 sample tissues are provided as an example. For specific sample information, refer to Figure 2 As shown, T stage indicates the tumor stage, and a number is added after "T" (such as T1, T2, T3, T4). The larger the number, the larger the tumor or the more severe the expansion; N stage indicates the lymph node stage, and a number is added after "N" (such as N0, N1, N2, N3). The increase in the number usually indicates an increase in the number or degree of metastasis to the lymph nodes. Different letters are added after "N" to indicate different sizes or metastasis to different types of lymph nodes. In addition, the survival time in this embodiment can be the survival time of myeloid cells after treatment, which can be 1 month, 6 months, 12 months, 24 months, 60 months, 80 months, etc., and is not specifically limited here.

[0029] The following will describe in detail the process of acquiring a fluorescent sample image of one of the sample tissues.

[0030] Traditional immunohistochemical staining can only stain one marker (in this embodiment, it represents the marker antigen) on one slide. If 6 markers need to be stained, 6 linked slices are required, and the final result cannot reach the same cell level. Especially for clinical samples, tissues are very precious. If it can be achieved that one slide can be stained with 6 markers, and at the same cell level, it will be much more convenient and reliable for subsequent analysis. In this embodiment, multiple immunohistochemical fluorescence (mIHC) staining is used, and multiple immunohistochemical fluorescence (mIHC) staining can stain 6 markers on the same slide, which can accurately depict the state of tumors and immune cells in the tumor microenvironment, provide important reference information for the accurate diagnosis of tumors, and also have important significance for the immunotherapy of tumors, including the proportion and distribution of immune cell subpopulations, especially the spatial relationship between immune cells and tumor cells, which are important contents of tumor prognosis and prediction research. It can help some clinicians who lack pathological knowledge to conveniently, quickly and effectively predict the prognosis and treatment effect of myeloid cell targeted drugs.

[0031] It should be noted that myeloid cells refer to a series of white blood cells produced in the bone marrow, including granulocytes (Neutro), monocytes (Mono) and macrophages (Macro). These cells originate from hematopoietic stem cells and undergo a series of differentiation and maturation processes to form mature white blood cells, which are responsible for the body's immune defense and inflammation regulation.

[0032] In some optional embodiments, markers for identifying myeloid cells include one or more combinations of the following: CD45, CD45RA, CD45RO, CD11b, CD11c, CD14, CD15, CD16, CD33, CD68, CD86, CD163, CD206, SPP1, FOLR2, C1QC, CD1c, HLA-DR, CD141, S100A9, S100A8, CD117, CD123, and MPO.

[0033] In this embodiment, the following marker combination examples for identifying myeloid cells are provided: CD68, CD11b, CD14, MPO, HLA-DR, CD163, and the specific meanings of the markers are as follows.

[0034] CD68: Usually used to detect macrophages. Macrophages are an important immune cell that plays an important role in inflammation, infection, tumors and tissue repair. CD68 is one of the markers of macrophages. The detection of CD68 can help pathologists determine the location, number and activity of macrophages in tissues, thereby understanding the diagnosis and pathophysiological process of the disease.

[0035] CD11b: is an integrin, also known as Mac-1 or ITGAM, and is a marker on the surface of monocytes, macrophages, and neutrophils. The detection of CD11b can help identify and quantify the presence and distribution of monocytes, macrophages, and neutrophils in tissues. These cells play an important role in processes such as inflammatory response, infection, immune response, and tissue repair. Therefore, the detection of CD11b can help pathologists understand the pathophysiological process of the disease and guide the diagnosis and formulation of treatment plans.

[0036] CD14: It is a protein that plays a key role in innate immunity and is one of the important surface markers of monocytes. In pathological diagnosis, the detection of CD14 can be used to identify the immune cell infiltration pattern of specific diseases, such as autoimmune diseases, infectious diseases and tumors. The location and counting of CD14-positive cells can help doctors further understand the pathophysiological mechanism of the disease, thereby guiding the selection of treatment options and evaluating the prognosis of the disease.

[0037] MPO: is an enzyme specific to granulocytes. MPO is usually used to detect granulocytes, including neutrophils (neutrophils) and eosinophils. MPO is an important enzyme in granulocytes, and its detection can help determine the presence and activity of granulocytes in tissues. Granulocytes play an important role in the course of diseases such as inflammation, infection, and tumors. The detection of MPO helps to assess the degree of inflammation in tissues, the infiltration of granulocytes, and the pathophysiological mechanisms of the disease. Therefore, by detecting MPO-positive cells, we can better understand the situation of granulocytes in tissues and provide important information for the diagnosis and treatment of diseases.

[0038] HLA-DR: It is an antigen presentation-related protein mainly expressed on the surface of immune cells. HLA-DR is usually used to detect professional antigen presenting cells with antigen presentation and immunomodulatory functions, mainly mature and activated cells in the monocyte series. Especially in disease states such as inflammation, infection, autoimmune diseases and tumors, HLA-DR positive cells play an important role in tissues. These cells include macrophages, dendritic cells and B lymphocytes, which play a role in immune response and antigen presentation. By detecting HLA-DR positive cells, pathologists can evaluate the activity state of immune cells, the degree of immune response and the immunopathological characteristics of the disease, so as to better understand the pathogenesis and progression of the disease.

[0039] CD163: It is a type I membrane protein, also known as M130 antigen, which is mainly expressed in the mononuclear cell system and macrophage system. It is a marker of monocytes and macrophages, such as dendritic cells in the spleen and alveolar macrophages, and is mainly used for the detection of monocytes and tissue cells in tumors and reactive lesions.

[0040] In this embodiment, intestinal tissue is taken as an example, and a fluorescent sample image can be obtained through the following experimental steps. It includes: dewaxing, fixing, repairing, blocking, sealing, primary antibody incubation, secondary antibody incubation, fluorescent incubation, repairing, restarting the sealing, primary antibody incubation, secondary antibody incubation, fluorescent incubation, repairing, and stopping the repetitive steps after all 5 targets are marked. Continue the fluorescent incubation to complete the Opal Polaris (a multiple fluorescent staining technology, commonly used for tissue section analysis in biomedical research) labeling. Finally, nuclear staining, sealing, and scanning to obtain the fluorescent sample image. Among them, the scanning result refers to Figure 3 shown.

[0041] Step S102 : segmenting the myeloid cells in each sample tissue based on the fluorescent sample image, and determining the fluorescence expression amount of each myeloid cell on different markers.

[0042] Specifically, scanning can be placing the processed sample tissue in a fluorescence microscope, irradiating the sample with a laser of a specific wavelength, causing the labeled fluorescent dye to emit fluorescence, and then capturing the emitted fluorescence signal through a camera system, thereby obtaining the fluorescent sample image in this embodiment. Through the fluorescent sample image, the overall morphology of the cells can be observed, the fluorescent expression of different markers can be understood, and the cell type of each myeloid cell in the sample can also be determined.

[0043] Furthermore, cell segmentation can first locate the position of each cell nucleus through the fluorescence expression of the DAPI (4', 6-diamidino-2-phenylindole) channel, and then use the cell nucleus as the cell center to find the cell boundary, and finally obtain a complete cell information. The fluorescent sample image after segmentation is referenced Figure 4 The average fluorescence expression of each marker in each cell can also be used as the fluorescence expression of each marker in the cell, and this value can be used for subsequent cell clustering and cell type judgment.

[0044] Step S103, determining the myeloid cell type annotation of each myeloid cell based on the fluorescence expression amount of each myeloid cell on different markers and the cell type annotation algorithm.

[0045] After the cell type is preliminarily determined based on the fluorescence expression of myeloid cells on different markers, it can be further displayed on the image. Since the multiple immunohistochemistry fluorescence scheme (mIHC) has a high background signal intensity, and the background signal intensity varies to varying degrees between different markers and even different samples, it is difficult to determine an overall threshold to remove the background signal intensity, so as to achieve the purpose of accurate display. In this embodiment, a set of annotation tables suitable for this embodiment is designed, as shown in Table 1, which can be used to accurately annotate cell types through the CELESTA (v0.0.0.9000) algorithm. After verification, the results of the classification annotation of cell types in this annotation table are consistent with the actual image. In this embodiment, annotations for Macro (macrophages), Mono (monocytes), Neutro (neutrophils), HLADR+cells (HLA-DR positive cells), M1 (M1 macrophages or classically activated macrophages), M2 (M2 macrophages or alternatively activated macrophages), and Unknow cells (cells of unclear cell types) are completed. The annotated fluorescent sample image is referenced Figure 5 shown.

[0046] Table 1

[0047] After the annotation is completed, the heat map of the expression of each cell type on different markers is also visualized in this example and standardized. Figure 6 shown.

[0048] Step S104, based on the myeloid cell type annotation, determining the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells, and obtaining a cell spatial distance feature.

[0049] Specifically, in this embodiment, the Euclidean distance of each cell to the nearest cell of each cell type can be calculated one by one, including the maximum distance, minimum distance, average value, etc. Continuing with the above sample tissue as an example, the features of 216 dimensions of the sample tissue at the spatial distance level are finally obtained, including T_HLADR+cellsToM1_mean, T_M1ToMacro_mean, T_MonoToNeutro_max, P_MonoToM1_max, T_NeutroToMono_min, P_MacroToM2_min, etc. The T at the beginning of the feature name represents cancer, and P represents cancer-adjacent, thereby completing the extraction of cell spatial distance features.

[0050] Step S105, based on the myeloid cell type annotation, determining the spatial interaction relationship between each myeloid cell in each sample tissue and the surrounding cells, and obtaining cell interaction characteristics.

[0051] In this embodiment, it is defined that each cell has a cell interaction relationship with the 10 cells closest to it, and the proportion of each cell type in all interacting cells is calculated. The proportion is used as the feature of each cell in spatial interaction. Continuing with the above sample tissue as an example, 72-dimensional features at the spatial interaction level are finally obtained, including T_HLADR+cells_HLADR+cells, T_Macro_M1, etc., thereby realizing the extraction of spatial interaction features.

[0052] Step S106, dividing the sample tissue into a training set and a test set according to a preset ratio and prognostic information.

[0053] In this embodiment, we continue to take the above-mentioned sample tissue as an example, that is, taking 90 sample tissues as an example, the 90 samples can be split into a data set in a ratio of 7:3, of which 64 are used as training sets and 26 are used as test sets for testing, and in the training set and the test set, long survival and short survival each account for half. In this embodiment, samples with a survival time greater than or equal to 70 months in the prognostic information can be defined as long survival, numbered 1, and the others can be defined as short survival, numbered 0. In the final sample, long survival and short survival each account for 50%. The independent test set has a total of 26 samples, including 13 long survivals and 13 short survivals. The test set is independent of the modeling process, does not participate in any feature selection and model building process, and is only used for the final test to ensure the accuracy of the test.

[0054] In some optional embodiments, the 16 features selected for building the model are as follows: T_MonoToM2_max, T_M1ToM2_mean, T_MonoToM2_mean, P_M2ToHLADRhicells_max, P_MonoToHLADRhicells_max, P_HLADRhicellsToMono_min P_MonoToHLADRhicells_min P_M2ToMono_mean, T_HLADRhicells_M2, T_M1_M1, T_M1_M2, T_M2_M1, T_M2_M2, T_Mono_M2, T_Neutro_M2, P_M2_Mono.

[0055] Among them, T_MonoToM2_max: represents the maximum distance from the monocytes in the cancer area to the nearest M2 macrophages. T_M1ToM2_mean: represents the average distance from the M1 macrophages in the cancer area to the nearest M2 macrophages. T_MonoToM2_mean: represents the average distance from the monocytes in the cancer area to the nearest M2 macrophages. P_M2ToHLADRhicells_max: represents the maximum distance from the M2 macrophages in the paracancerous area to the nearest HLADR-positive cells. P_MonoToHLADRhicells_max: represents the maximum distance from the monocytes in the paracancerous area to the nearest HLAD-positive cells. P_HLADRhicellsToMono_min: represents the minimum distance from the HLADR-positive cells in the paracancerous area to the nearest monocytes. P_MonoToHLADRhicells_min: represents the minimum distance from the monocytes in the paracancerous area to the nearest HLADR-positive cells. P_M2ToMono_mean: represents the average distance from the M2 macrophages in the paracancerous area to the nearest monocytes. T_HLADRhicells_M2: indicates the proportion of M2 macrophages that interact with HLADR-positive cells in the cancer region. T_M1_M1: indicates the proportion of M1 macrophages that interact with M1 macrophages in the cancer region. T_M1_M2: indicates the proportion of M2 macrophages that interact with cancer cells and M1 macrophages. T_M2_M1: indicates the proportion of M1 macrophages that interact with M2 macrophages in the cancer region. T_M2_M2: indicates the proportion of M2 macrophages that interact with M2 macrophages in the cancer region. T_Mono_M2: indicates the proportion of M2 macrophages that interact with monocytes in the cancer region. T_Neutro_M2: indicates the proportion of M2 macrophages that interact with neutrophils in the cancer region. P_M2_Mono: indicates the proportion of monocytes that interact with M2 macrophages in the paracancerous region.

[0056] Constructing a prognosis survival prediction model based on the above characteristics can effectively improve the accuracy of model construction.

[0057] Step S107, constructing a prognosis survival prediction model based on the cell spatial distance characteristics and cell interaction characteristics in the training set and the test set, and the prognosis survival prediction model is used to predict the survival of the pathological sample after intervention.

[0058] Specifically, in this embodiment, a random forest model can be used. The corresponding sample information, cell spatial distance characteristics, cell interaction characteristics and other information in the training set are input into the random forest model for training to construct an initial survival prediction model. The AUC value of the model on the training set is 0.834, which has good prediction performance. Figure 7 is a schematic diagram of the ROC (Receiver Operating Characteristic) curve of the training set. In this embodiment, other evaluation indicators of the model training set are calculated and visualized. Figure 8 As shown in the figure, they all show good performance. Furthermore, the constructed prediction model was verified on the test set, and the AUC of the model on the test set was 0.787, which verified that it still maintained good prediction performance in the independent test set. Fig. 9 This is a schematic diagram of the ROC curve of the test set. In this embodiment, other evaluation indicators of the model test set are calculated and visualized. Fig.10 In this embodiment, good performance is shown in both the training set and the test set. The prediction model has the advantages of convenient feature extraction and high accuracy.

[0059] At present, the common prediction of treatment effect mainly targets lymphocyte immune checkpoints, such as PD-1, PD-L1, and CTLA4. However, the existing lymphocyte immune checkpoints cannot well predict or evaluate the efficacy of such myeloid cell immune checkpoint drugs. In addition, the current multiple immunohistochemical fluorescence analysis methods mostly stay at the naked eye observation of the experimental result images or simply count the percentage of cells positive for a certain marker or the percentage of double positive cells, etc., lacking a deeper level of analysis.

[0060] The present invention provides a method for constructing a prognosis prediction model based on myeloid cells. The method extracts the characteristics of cells in the spatial field through cell segmentation, cell annotation, distance calculation, interaction analysis and other aspects of fluorescent sample images, extracts the characteristics between cells at the cellular level, and constructs a prognosis survival prediction model based on the spatial position relationship of myeloid cells based on these spatial characteristics, which provides a strong reference for clinical judgment of tumor prognosis and survival.

[0061] In some optional embodiments, the above step S102, i.e. segmenting the myeloid cells in each sample tissue based on the fluorescent sample image and determining the fluorescence expression amount of each myeloid cell on different markers, includes: Step S1021 , dividing each fluorescent sample image into regions to obtain a plurality of regional images corresponding to each fluorescent sample image.

[0062] Step S1022, determining the position of the nucleus of the myeloid cell according to the fluorescence expression amount corresponding to the regional image.

[0063] Step S1023, based on the position of the cell nucleus, segment the complete myeloid cells corresponding to the cell nucleus.

[0064] Step S1024, determining all fluorescence expression levels corresponding to each marker in the complete myeloid cells, and calculating the average fluorescence expression level corresponding to each marker.

[0065] Step S1025, taking the average fluorescence expression level as the fluorescence expression level of the corresponding marker.

[0066] For regional division, Qupath software can be used to select the appropriate number of regional images (hereinafter referred to as ROI) in each fluorescent sample image. Specifically, the qptiff image of each tissue can be opened with Qupath software, and the appropriate area can be selected on the fluorescent sample image as the ROI area for bioinformatics analysis according to the staining of the sample tissue. When using tissue chips for experimental analysis, each chip point can be used as an ROI. Then Qupath software can be used to perform cell segmentation on the selected ROI, extract the fluorescence expression of each cell on different markers after segmentation, and export the results as csv format data. The data can be exported and a data structure object spe (SpatialExperiment v1.10.0, SingleCellExperiment v1.22.0, imcRtools v1.6.5) of the SpatialExperiment type can be constructed to store the cell information, expression information, prognosis information, etc. of each ROI. For each ROI, the position of each cell nucleus can be located by the fluorescence expression of the DAPI channel, and then the cell boundary can be found with the cell nucleus as the cell center, and finally a complete myeloid cell can be obtained. In this embodiment, the fluorescent sample image is divided into regions, and cell segmentation is performed on each regional image, so that myeloid cells can be segmented more accurately, thereby increasing the accuracy of cell segmentation.

[0067] Furthermore, the average of all expression levels of each marker in each cell is used as the fluorescence expression level of the cell on the marker, that is, the average of the fluorescence expression level of each marker in the complete myeloid cells is used as the fluorescence expression level of the complete myeloid cells on the marker. Using the average value to represent the overall expression level of the cell on these markers can facilitate further cell classification and analysis.

[0068] In some optional embodiments, the above step S104, i.e., each regional image includes a cancer region and a paracancerous region, and the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells is determined to obtain the cell spatial distance feature, includes: Step S1041 : determining a first Euclidean distance between each type of myeloid cell in the cancerous region included in each regional image and other different types of myeloid cells.

[0069] Step S1042: determining the second Euclidean distance between each type of myeloid cell and other different types of myeloid cells in the adjacent cancerous region included in each regional image.

[0070] Step S1043, based on all first Euclidean distances, determining a first spatial distance between each myeloid cell and other different types of myeloid cells in all cancerous regions of the sample tissue, wherein the first spatial distance includes: a first minimum spatial distance, a first maximum spatial distance, and a first average spatial distance.

[0071] Step S1044, based on all the second Euclidean distances, determine the second spatial distances between each myeloid cell and other different types of myeloid cells in all per-cancerous regions of the sample tissue, where the second spatial distances include: a second minimum spatial distance, a second maximum spatial distance, and a second average spatial distance.

[0072] Step S1045, taking the first spatial distance and the second spatial distance as cell spatial distance features.

[0073] Specifically, in this embodiment, the Euclidean distance between two different types of cells can be calculated. For example, if the coordinates of one cell in the regional image are (x1, y1) and the coordinates of the other cell in the regional image are (x2, y2), then the Euclidean distance can be calculated using the formula, distance^2 = (x1-x2)^2+(y1-y2)^2. Thus, the distance from each cell type to different cell types is obtained in each ROI, and a more comprehensive distance feature is obtained by calculating the maximum, minimum, and mean values ​​of these distances in each sample tissue. Among them, since each sample tissue includes two regions, cancer and paracancerous, when extracting features, the cell spatial distance features can be calculated and extracted for cancer and paracancerous separately, and finally the two parts of the features are combined. Still taking the above example, a 216-dimensional feature at the spatial distance level can be obtained.

[0074] In this embodiment, by calculating the spatial distances between different types of myeloid cells, we can gain a deeper understanding of the interaction and spatial distribution characteristics of cells in the tumor microenvironment. In addition, this embodiment also analyzes the difference in spatial distances between myeloid cells in the cancerous area and the adjacent area, taking into account the cell changes during the development of the tumor, etc., which helps to improve the comprehensiveness of the analysis and the prediction accuracy of the constructed model.

[0075] In some optional embodiments, after obtaining the cell space distance feature, the method further comprises: The distance features between the same myeloid cell types in the cell space distance features are subjected to data processing and feature screening to obtain processed cell space distance features, and the processed cell space distance features are used to construct a prognosis survival prediction model.

[0076] In this embodiment, after obtaining the cell space distance features and cell interaction features, the cell space distance features and cell interaction features need to be fused. Still taking the above example as an example, 288-dimensional features corresponding to each sample tissue can be obtained. It is worth noting that in the calculation of these features, the final features do not include the cell type Unknow. Furthermore, in this embodiment, the distance features between the same cell types in the cell space distance features are also filtered and not included in subsequent processing. All features are also standardized to eliminate the impact of the absolute numerical size differences between different features on model construction. Still taking the above example as an example, there are 250 features that finally enter the feature selection process.

[0077] Then, feature selection is performed. The 216+72-dimensional features extracted in the training set can be selected using the Boruta algorithm. The Boruta algorithm is a feature selection method based on random forests. Its main goal is to find the truly important features from a given feature set and distinguish them from irrelevant features. Fig.11 As shown, it is a schematic diagram of the importance of features in the model, refer to Fig.12 As shown, it is a line chart of feature importance score, where green is confirmed important features and yellow is tentative features. Finally, 16 features of two levels, important and tentative, were obtained according to the Boruta algorithm, including 10 confirmed important features, 6 tentative features and other unimportant features. The confirmed important features are: T_MonoToM2_mean, P_MonoToHLADRhicells_max, P_HLADRhicellsToMono_min, P_MonoToHLADRhicells_min, P_M2ToMono_mean, T_HLADRhicells_M2, T_M2_M1, T_Mono_M2, T_Neutro_M2, P_M2_Mono. The tentative features are: T_MonoToM2_max, T_M1ToM2_mean, P_M2ToHLADRhicells_max, T_M1_M1, T_M1_M2, T_M2_M2. For details, please refer to Fig.13 As shown, this is a schematic diagram of the impact of the 16 features on model performance.

[0078] In this embodiment, data processing and feature screening of distance features between the same myeloid cell types can improve the accuracy and robustness of the model, help better capture the characteristic relationship between cells, and provide stronger support for prognosis and survival prediction.

[0079] In some optional embodiments, the above step S105, i.e., each regional image includes a cancer region and a paracancerous region, and the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue is determined to obtain the cell interaction characteristics, includes: Step S1051, determining a first interaction feature between each myeloid cell in the cancer region included in each regional image and the surrounding interacting cells having an interactive relationship. The interacting cells are cells having an interactive relationship between cells.

[0080] Step S1052, determining a second interaction feature between each myeloid cell and surrounding interacting cells having an interacting relationship in the per-cancer region included in each regional image; wherein the first interaction feature and the second interaction feature both include the proportion of each myeloid cell type in the interacting cells having an interacting relationship.

[0081] Step S1053: taking the first interaction feature and the second interaction feature as cell interaction features.

[0082] In this embodiment, it is defined that each cell has a cell interaction relationship with its 10 nearest cells, and the interaction calculation is performed on each cell to obtain the cell types of the 10 cells around it, and the proportion of the cell types of these cells in the interacting cells is calculated to obtain the spatial interaction characteristics from the central cell to different cell types. Each sample tissue is statistically averaged to obtain the spatial interaction characteristics between each cell type and other different cell types in each regional image. The cell spatial interaction characteristics are calculated for the cancer and adjacent areas of the same sample tissue, and these characteristics are combined. Still taking the above example as an example, 72-dimensional features at the cell interaction level can be obtained.

[0083] In this embodiment, using the interaction relationship between two cells in space as an important reference indicator for disease prognosis can not only improve the accuracy and reliability of the prognosis survival prediction model, but also provide important information support for clinical decision-making.

[0084] In this embodiment, a prognosis survival prediction method is provided, which can be executed by a server, a terminal, a mobile terminal and other devices. The method includes the following steps: Step S201, obtaining a fluorescent sample image of a pathological sample to be predicted; Step S202: input the fluorescent sample image into the prognosis survival prediction model constructed according to the prognosis survival prediction model construction method described in any of the above embodiments, and output the predicted survival time of the pathological sample to be predicted after intervention.

[0085] The present invention utilizes the construction of a prognosis survival prediction model based on the spatial characteristics of myeloid cells, which can better predict the prognosis survival and provide an important reference basis for clinical judgment of tumor prognosis survival.

[0086] The specific introduction of the prognosis survival prediction model is shown in the above embodiment and will not be repeated here.

[0087] In the present embodiment, a prognosis survival prediction model construction device is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made no further. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0088] This embodiment provides a prognosis survival prediction model construction device, such as Fig.14 As shown, the device comprises: The acquisition module 301 is used to acquire a fluorescent sample image corresponding to the sample tissue before treatment, where the fluorescent sample image is obtained after staining with antibodies for myeloid cell markers; and is also used to acquire prognostic information of the patient corresponding to the sample tissue, where the prognostic information includes the survival status of the patient after receiving different preset treatment methods; The segmentation module 302 is used to segment the myeloid cells in each sample tissue based on the fluorescent sample image, and determine the fluorescence expression amount of each myeloid cell on different markers; wherein, each of the fluorescent sample images is divided into regions to obtain a plurality of regional images corresponding to each of the fluorescent sample images; the position of the nucleus of the myeloid cell is determined according to the fluorescence expression amount corresponding to the regional image; and based on the position of the nucleus, the complete myeloid cell corresponding to the nucleus is segmented; An annotation module 303, for determining a myeloid cell type annotation for each myeloid cell based on the fluorescence expression amount of each myeloid cell on different markers and a cell type annotation algorithm; A distance feature extraction module 304 is used to determine the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells based on the myeloid cell type annotations, and obtain a cell spatial distance feature; An interaction feature extraction module 305 is used to determine the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue based on the myeloid cell type annotation, and obtain cell interaction features; A division module 306 is used to divide the sample tissue into a training set and a test set according to a preset ratio and prognostic information; The construction module 307 is used to construct a prognosis survival prediction model based on the cell spatial distance characteristics and cell interaction characteristics in the training set and the test set. The prognosis survival prediction model is used to predict the survival of the pathological sample after intervention.

[0089] In an optional implementation, the segmentation module 302 includes: The segmentation unit is used to divide each fluorescent sample image into regions to obtain multiple regional images corresponding to each fluorescent sample image; determine the cell nucleus position of the myeloid cell according to the fluorescence expression amount corresponding to the regional image; segment the complete myeloid cell corresponding to the cell nucleus based on the cell nucleus position; determine all the fluorescence expression amounts corresponding to each marker in the complete myeloid cell, and calculate the average fluorescence expression amount corresponding to each marker one by one; and use the average fluorescence expression amount as the fluorescence expression amount on the corresponding marker.

[0090] In an optional implementation, each regional image includes a cancer region and a para-cancer region, and the distance feature extraction module 304 includes: The distance feature extraction unit is used to determine the first Euclidean distance between each myeloid cell type in the cancerous area included in each regional image and other different types of myeloid cells; determine the second Euclidean distance between each myeloid cell type in the adjacent cancerous area included in each regional image and other different types of myeloid cells; based on all the first Euclidean distances, determine the first spatial distance between each myeloid cell in all cancerous areas of the sample tissue and other different types of myeloid cells, the first spatial distance includes: a first minimum spatial distance, a first maximum spatial distance, and a first average spatial distance; based on all the second Euclidean distances, determine the second spatial distance between each myeloid cell in all adjacent cancerous areas of the sample tissue and other different types of myeloid cells, the second spatial distance includes: a second minimum spatial distance, a second maximum spatial distance, and a second average spatial distance; and use the first spatial distance and the second spatial distance as cell spatial distance features.

[0091] In an optional implementation, each regional image includes a cancer region and a para-cancer region, and the interaction feature extraction module 305 includes: The interaction feature extraction unit is used to determine the first interaction feature of the interaction relationship between each myeloid cell in the cancer area included in each regional image and the surrounding cells with which the interaction relationship exists; determine the second interaction feature of the interaction relationship between each myeloid cell in the adjacent cancer area included in each regional image and the surrounding cells with which the interaction relationship exists; wherein the first interaction feature and the second interaction feature both include the proportion of each myeloid cell type in the interacting cells; and use the first interaction feature and the second interaction feature as cell interaction features.

[0092] In an optional embodiment, the device further comprises: The processing module is used to perform data processing and feature screening on the distance features between the same myeloid cell types in the cell space distance features to obtain the processed cell space distance features, and the processed cell space distance features are used to construct a prognosis survival prediction model.

[0093] The prognosis survival prediction model construction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0094] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0095] The embodiment of the present invention also provides a computer device having the above Fig.14 The prognostic survival prediction model construction device shown.

[0096] See also Fig.15 , Fig.15 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig.15 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.15 A processor 10 is taken as an example.

[0097] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0098] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0099] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0101] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0102] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0103] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0104] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for constructing a prognosis survival prediction model, characterized in that: The method comprises: Obtaining a fluorescent sample image corresponding to the sample tissue before treatment, wherein the fluorescent sample image is obtained after staining with an antibody for a marker of myeloid cells; Obtaining prognostic information of the patient corresponding to the sample tissue, wherein the prognostic information includes the patient's survival status after receiving different preset treatment methods; The myeloid cells in each sample tissue are segmented based on the fluorescent sample image to determine the fluorescence expression amount of each myeloid cell on different markers; wherein, each of the fluorescent sample images is divided into regions to obtain a plurality of regional images corresponding to each of the fluorescent sample images; the cell nucleus position of the myeloid cell is determined according to the fluorescence expression amount corresponding to the regional image; and based on the cell nucleus position, the complete myeloid cell corresponding to the cell nucleus is segmented; Determine the myeloid cell type annotation of each myeloid cell based on the fluorescence expression of each myeloid cell on different markers and the cell type annotation algorithm; Based on the myeloid cell type annotation, determining the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells to obtain a cell spatial distance feature; Based on the myeloid cell type annotation, determining the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue to obtain cell interaction characteristics; Dividing the sample tissue into a training set and a test set according to a preset ratio and the prognostic information; A prognosis survival prediction model is constructed based on the cell spatial distance characteristics and the cell interaction characteristics in the training set and the test set, and the prognosis survival prediction model is used to predict the survival of pathological samples after intervention.

2. The method according to claim 1, characterized in that The markers used to identify myeloid cells are selected from one or more of the following: CD45, CD45RA, CD45RO, CD11b, CD11c, CD14, CD15, CD16, CD33, CD68, CD86, CD163, CD206, SPP1, FOLR2, C1QC, CD1c, HLA-DR, CD141, S100A9, S100A8, CD117, CD123, MPO.

3. The method according to claim 2, characterized in that Each of the regional images includes a cancer region and a paracancerous region. Determining the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells to obtain the cell spatial distance feature includes: Determine a first Euclidean distance between each type of myeloid cell and other different types of myeloid cells in the cancer region included in each of the region images; Determine a second Euclidean distance between each type of myeloid cell and other different types of myeloid cells in the adjacent cancer region included in each of the regional images; Based on all the first Euclidean distances, determining a first spatial distance between each myeloid cell and other different types of myeloid cells in all cancerous regions of the sample tissue, wherein the first spatial distance includes: a first minimum spatial distance, a first maximum spatial distance, and a first average spatial distance; Based on all the second Euclidean distances, determining a second spatial distance between each myeloid cell and other different types of myeloid cells in all paracancerous regions of the sample tissue, wherein the second spatial distance includes: a second minimum spatial distance, a second maximum spatial distance, and a second average spatial distance; Using the first spatial distance and the second spatial distance as the cell spatial distance features; After obtaining the cell space distance feature, it includes: Data processing and feature screening are performed on the distance features between the same myeloid cell types in the cell space distance features to obtain processed cell space distance features, and the processed cell space distance features are used to construct the prognosis survival prediction model.

4. The method according to claim 2, characterized in that: Each of the regional images includes a cancer region and a paracancerous region, and determining the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue to obtain cell interaction characteristics includes: Determine a first interaction feature between each myeloid cell in the cancer region included in each of the regional images and surrounding interacting cells having an interacting relationship; Determine a second interaction feature between each myeloid cell in the per-cancer region included in each of the regional images and the surrounding interacting cells having an interacting relationship; wherein the first interaction feature and the second interaction feature both include the proportion of each myeloid cell type in the interacting cells having an interacting relationship; The first interaction feature and the second interaction feature are used as the cell interaction features.

5. The method according to claim 1, characterized in that The features used to construct the prognostic survival prediction model include one or more of the following: T_MonoToM2_max, T_M1ToM2_mean, T_MonoToM2_mean, P_M2ToHLADRhicells_max, P_MonoToHLADRhicells_max, P_HLADRhicellsToMono_min P_MonoToHLADRhicells_min P_M2ToMono_mean, T_HLADRhicells_M2, T_M1_M1, T_M1_M2, T_M2_M1, T_M2_M2, T_Mono_M2, T_Neutro_M2, P_M2_Mono.

6. A method for predicting prognosis and survival, characterized in that: The method comprises: Acquire a fluorescent sample image of a pathological sample to be predicted; The fluorescent sample image is input into the prognosis survival prediction model constructed according to the prognosis survival prediction model construction method according to any one of claims 1 to 5, and the survival status of the pathological sample to be predicted after intervention is output.

7. A prognosis survival prediction model construction device, characterized in that: The device comprises: An acquisition module is used to acquire a fluorescent sample image corresponding to the sample tissue before treatment, wherein the fluorescent sample image is obtained after staining with antibodies for myeloid cell markers; and is also used to acquire prognostic information of the patient corresponding to the sample tissue, wherein the prognostic information includes the survival status of the patient after receiving different preset treatment methods; A segmentation module, for segmenting the myeloid cells in each sample tissue based on the fluorescent sample image, and determining the fluorescence expression amount of each myeloid cell on different markers; wherein, each of the fluorescent sample images is divided into regions to obtain a plurality of regional images corresponding to each of the fluorescent sample images; the position of the nucleus of the myeloid cell is determined according to the fluorescence expression amount corresponding to the regional image; and based on the position of the nucleus, the complete myeloid cell corresponding to the nucleus is segmented; An annotation module, for determining a myeloid cell type annotation for each myeloid cell based on the fluorescence expression of each myeloid cell on different markers and a cell type annotation algorithm; A distance feature extraction module is used to determine the spatial distance between each myeloid cell in each sample tissue and other different types of myeloid cells based on the myeloid cell type annotations, and obtain cell spatial distance features; An interaction feature extraction module, used to determine the spatial interaction relationship between each myeloid cell and surrounding cells in each sample tissue based on the myeloid cell type annotation, and obtain cell interaction features; A division module, used for dividing the sample tissue into a training set and a test set according to a preset ratio and the prognostic information; A construction module is used to construct a prognosis survival prediction model based on the cell spatial distance characteristics and the cell interaction characteristics in the training set and the test set, and the prognosis survival prediction model is used to predict the survival of pathological samples after intervention.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for constructing a prognosis survival prediction model according to any one of claims 1 to 5 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for constructing a prognosis survival prediction model according to any one of claims 1 to 5.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for constructing a prognosis survival prediction model according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Gastric cancer prognosis prediction device

    CN113092202A

  • Prediction method and system based on pathological image data

    CN117423479A

  • Tumor-lymphocyte space interaction score determination and prognosis judgment method

    CN117575989A

  • Non-small cell lung cancer immune checkpoint inhibitor therapy curative effect evaluation method and system based on tissue in-situ mass spectrometry imaging technology

    CN118522475A

  • Protein marker group for detecting myeloid cells, application, kit and detection method

    CN118688444A

Cited By

  • Screening method of cancer prognosis marker

    CN120404541A