Immunotherapy effect prediction method, system and device based on tissue mass spectrometry imaging

Abstract

The present invention relates to a method, system and device for predicting the effect of immunotherapy based on tissue mass spectrometry imaging. It includes: obtaining an image of mass spectrometry imaging of a patient's tumor tissue to be tested; obtaining protein marker information in the image based on the image of mass spectrometry imaging of the tumor tissue, and obtaining tumor cell protein marker expression data; inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of the immunotherapy responsiveness of the patient's tumor cells to be tested; and predicting the immunotherapy effect based on the prediction result of the immunotherapy responsiveness of the patient's tumor cells to be tested. The present invention develops an auxiliary diagnosis and treatment system based on a tumor cell expression state model to achieve precise treatment of immunotherapy methods.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and more specifically, to a method, system, device and storage medium for predicting immunotherapy effects based on tissue mass spectrometry imaging. Background Art

[0002] Tissue mass spectrometry imaging (IMC) is a new tissue imaging technology based on mass spectrometry, which can simultaneously detect up to 36 protein markers on a single slice of formalin-fixed tissue with a reconstruction resolution of 1μm. Unlike traditional fluorescence imaging, tissue mass spectrometry imaging can avoid the defects of endogenous fluorescence generated by tissues, which reduces the signal-to-noise ratio and damages the image quality, making tissue mass spectrometry imaging have great potential in spatial omics research.

[0003] Although immune checkpoint inhibitors (ICIs) (such as anti-PD-1 / PD-L1 antibodies) have achieved remarkable results in cancer treatment, they are only limited to a small number of patients to be tested, and a considerable proportion of patients with tumors to be tested do not respond to anti-PD1 / PD-L1 antibodies. The main challenge at present is to identify and develop auxiliary diagnosis and treatment systems that can predict the effects of the above-mentioned immunotherapy, so as to accurately identify patients to be tested who will benefit from immunotherapy. Summary of the invention

[0004] To solve the above problems, we have found that the effect of immunotherapy is related to the immune microenvironment and / or tumor cell expression status of the patient to be tested. This application establishes a method, system, device and storage medium for predicting the effect of immunotherapy based on tissue mass spectrometry imaging.

[0005] The present application discloses a method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging, and the specific method steps include:

[0006] Acquire a mass spectrometry imaging image of a tumor tissue of a patient to be tested;

[0007] Obtaining protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging to obtain tumor cell protein marker expression data;

[0008] Inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested;

[0009] Predict the effect of immunotherapy based on the predicted results of the immunotherapy responsiveness of the patient's tumor cells to be tested.

[0010] Furthermore, the method steps also include obtaining single cell morphology information and protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, classifying the cell population according to the single cell morphology information and protein marker information in the image, and obtaining cell subpopulation data; inputting the cell subpopulation data into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; predicting the immunotherapy effect according to the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness;

[0011] Optionally, the cell subpopulation data and protein marker information are input into an immunotherapy effect model to obtain an immunotherapy effect prediction result;

[0012] Preferably, the immunotherapy effect model includes an immune microenvironment scoring model and a tumor cell expression status model. The cell subpopulation data is input into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; the protein marker information in the image is input into the tumor cell expression status model to obtain the prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested, and the immunotherapy effect is predicted based on the immune microenvironment score of the patient to be tested and the tumor cell immunotherapy responsiveness prediction result.

[0013] Furthermore, the mass spectrometry imaging image of the tumor tissue of the patient to be detected is obtained by performing multi-channel tissue mass spectrometry imaging on the tumor tissue of the patient to be detected, and the tumor tissue includes a tumor-immune interface area, an internal tumor area, and a cancer-adjacent area;

[0014] Optionally, the method for acquiring the mass spectrometry imaging image of the tumor tissue of the patient to be detected is:

[0015] a. Differentiate the tumor-immune interface, tumor interior, and adjacent areas of tumor tissue through pathological morphological analysis;

[0016] b. Perform ROI scan on each area;

[0017] c. Use the Cytomapper package to draw channel synthetic pseudo-color photos.

[0018] Further, the protein marker information includes protein marker information of a combination of multiple protein markers; preferably, the protein markers include cell identity protein markers, cell function protein markers, and immunomodulatory protein markers; preferably, the identity protein markers include one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I; the cell function protein markers include one or a combination of the following proteins: dsDNA, Ki-67, HLA-DR, IFN-γ; the immunomodulatory protein markers include one or a combination of the following proteins: PD1, PDL1, PDL2, TGF-β, TNF-α;

[0019] Optionally, the protein includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I, dsDNA, Ki-67, HLA-DR, IFN-γ, PD1, PDL1, PDL2, TGF-β, TNF-α; preferably, the protein is a combination of the above-mentioned markers.

[0020] Furthermore, the single-cell morphological information is obtained by performing single-cell segmentation on the image of tumor tissue mass spectrometry imaging; preferably, a machine learning algorithm is used to perform single-cell segmentation on the image of tumor tissue mass spectrometry imaging to obtain the single-cell morphological information in the image.

[0021] Furthermore, the cell subpopulation data is clustered by single cell morphology information and protein marker information in the image to obtain the category and quantity of each cell subpopulation;

[0022] Preferably, the cell subsets include one or a combination of the following: CD8+T cells, B cells, CD4+T cells, NK cells, monocytes and macrophages, granulocytes, antigen presenting cells, and Treg cells.

[0023] Preferably, the clustering is performed using an unsupervised learning method;

[0024] Optionally, after clustering using single cell morphology information and protein marker information in the image, the same cell subpopulations are merged after protein marker visualization to obtain the required category and quantity of each merged cell.

[0025] The purpose of this application is to provide an immunotherapy effect prediction system based on tissue mass spectrometry imaging, including:

[0026] An acquisition unit, used for acquiring a mass spectrometry imaging image of a tumor tissue of a patient to be detected;

[0027] A first extraction unit is used to obtain protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtain tumor cell protein marker expression data;

[0028] A tumor cell expression state unit, used to input the protein marker information in the image into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested;

[0029] The prediction unit is used to predict the immunotherapy effect of the patient to be tested based on the prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested.

[0030] The purpose of this application is to provide an immunotherapy effect prediction system based on tissue mass spectrometry imaging, comprising:

[0031] An acquisition unit, used for acquiring a mass spectrometry imaging image of a tumor tissue of a patient to be detected;

[0032] A first extraction unit is used to obtain protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtain tumor cell protein marker expression data;

[0033] A tumor cell expression state unit, used to input the protein marker information in the image into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested;

[0034] A second extraction unit is used to obtain single cell morphology information and protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and classify the cell population according to the single cell morphology information and protein marker information in the image to obtain cell subpopulation data;

[0035] An immune microenvironment scoring unit, used to input the cell subset data into an immune microenvironment scoring model to obtain an immune microenvironment score of the patient to be tested;

[0036] The prediction unit is used to predict the immunotherapy effect of the patient to be tested based on the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness.

[0037] The purpose of the present application is to provide an immunotherapy effect prediction device based on tissue mass spectrometry imaging, characterized in that it includes: a memory and a processor;

[0038] The memory is used to store program instructions;

[0039] The processor is used to call program instructions, and when the program instructions are executed, the above-mentioned immunotherapy effect prediction method based on tissue mass spectrometry imaging is implemented.

[0040] The purpose of the present application is to provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging.

[0041] Advantages of this application:

[0042] 1. This application takes into account the impact of the immune microenvironment on the immunotherapy of patients with tumors to be tested, uses the single cell morphology information and protein marker information in the images of tumor tissue mass spectrometry imaging to obtain cell subpopulation data, and further obtains the immune microenvironment score of the patient to be tested based on the cell subpopulation data, and predicts the immunotherapy effect according to the immune microenvironment score of the patient to be tested;

[0043] 2. This application takes into account the impact of tumor cell expression status on the immunotherapy of patients to be tested for tumors, and uses the protein marker information in the images of tumor tissue mass spectrometry imaging to obtain the prediction results of the immunotherapy responsiveness of tumor cells in patients to be tested;

[0044] 3. This application takes into account the impact of the immune microenvironment and tumor cell expression status on the immunotherapy of patients to be tested for tumors, uses the single cell morphology information and protein marker information in the images of tumor tissue mass spectrometry imaging to obtain cell subpopulation data, and further obtains the immune microenvironment score of the patient to be tested based on the cell subpopulation data. At the same time, the protein marker information in the images of tumor tissue mass spectrometry imaging is used to obtain the prediction results of the immunotherapy responsiveness of tumor cells in the patient to be tested, and the immunotherapy effect is predicted based on the immune microenvironment score of the patient to be tested and the prediction results of the tumor cell immunotherapy responsiveness;

[0045] 4. Based on the results of previous studies, this application has developed a protein marker panel for predicting the efficacy of immunotherapy for tissue mass spectrometry imaging. The protein marker panel lays the foundation for effectively constructing an immune microenvironment scoring model and a tumor cell expression status model. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 This is a schematic flow chart of a method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging provided by an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of an immunotherapy effect prediction system based on tissue mass spectrometry imaging provided by an embodiment of the present invention;

[0049] Figure 3 It is a schematic diagram of an immunotherapy effect prediction system including an immune microenvironment scoring unit based on tissue mass spectrometry imaging provided by an embodiment of the present invention;

[0050] Figure 4 It is a schematic flow chart of a method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging and including an immune microenvironment scoring model provided by an embodiment of the present invention;

[0051] Figure 5 It is a schematic diagram of an immunotherapy effect prediction device based on tissue mass spectrometry imaging provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0053] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] Figure 1 The present invention provides a schematic flow chart of a method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging. Specifically, the method comprises the following steps:

[0056] 101: Acquire a mass spectrometry imaging image of a tumor tissue of a patient to be tested;

[0057] In one embodiment, the mass spectrometry imaging image of the tumor tissue of the patient to be detected is obtained by performing multi-channel tissue mass spectrometry imaging on the tumor tissue of the patient to be detected, and the tumor tissue includes a tumor-immune boundary area, a tumor internal area and a cancer-adjacent area; optionally, the method for obtaining the mass spectrometry imaging image of the tumor tissue of the patient to be detected is: a. distinguishing the tumor-immune boundary area, the tumor internal area and the cancer-adjacent area of ​​the tumor tissue through pathological morphological analysis; b. performing repeated scanning of 2 ROIs (Region of interest) for each area, and storing the imaging data through MCD files; c. using the Cytomapper program package to draw channel synthetic pseudo-color photos.

[0058] 102: Obtaining protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtaining tumor cell protein marker expression data;

[0059] In one embodiment, the protein marker information includes protein marker information of a combination of multiple protein markers; preferably, the protein markers include cell identity protein markers, cell function protein markers, and immunomodulatory protein markers; preferably, the identity protein markers include one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I; the cell function protein markers include one or a combination of the following proteins: dsDNA, Ki-67, HLA- DR, IFN-γ; the immunomodulatory protein marker includes one or a combination of the following proteins: PD1, PDL1, PDL2, TGF-β, TNF-α; optionally, the protein includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I, dsDNA, Ki-67, HLA-DR, IFN-γ, PD1, PDL1, PDL2, TGF-β, TNF-α; preferably, the protein is a combination of the above markers.

[0060] 103: Inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of tumor cell immunotherapy responsiveness of the patient to be tested;

[0061] In one embodiment, the training process of the tumor cell expression status model is: obtaining mass spectrometry imaging images of tumor tissues of patients to be tested with different immunotherapy responses (effective immunotherapy and poor immunotherapy), obtaining protein marker information in the images (including the types and expression levels of protein markers) based on the mass spectrometry imaging images of the tumor tissues, obtaining tumor cell protein marker expression data, and using the obtained tumor cell protein marker expression data as feature training to obtain a tumor cell expression status model.

[0062] 104: Predict the effect of immunotherapy based on the predicted results of the immunotherapy responsiveness of the patient's tumor cells to be tested.

[0063] In one embodiment, the method steps also include inputting the protein marker information in the image into a tumor cell expression status model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested; and predicting the immunotherapy effect based on the immune microenvironment score of the patient to be tested and the tumor cell immunotherapy responsiveness prediction result.

[0064] In one embodiment, Figure 4 As shown, the method for predicting the immunotherapy effect based on tissue mass spectrometry imaging includes: obtaining an image of mass spectrometry imaging of tumor tissue of a patient to be tested, obtaining protein marker information in the image based on the image of mass spectrometry imaging of the tumor tissue, and obtaining tumor cell protein marker expression data; inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested; obtaining single cell morphology information and protein marker information in the image based on the image of mass spectrometry imaging of the tumor tissue, classifying the cell population based on the single cell morphology information and protein marker information in the image, and obtaining cell subpopulation data; inputting the cell subpopulation data into an immune microenvironment scoring model to obtain an immune microenvironment score of the patient to be tested; and predicting the immunotherapy effect based on the immune microenvironment score of the patient to be tested and the prediction result of the tumor cell immunotherapy responsiveness.

[0065] In one embodiment, the training process of the immune microenvironment scoring model is as follows: obtaining mass spectrometry imaging images of tumor tissues of patients to be tested with different immunotherapy responses (effective immunotherapy and poor immunotherapy), obtaining single cell morphology information and protein marker information in the images based on the mass spectrometry imaging images of the tumor tissues, clustering the cell populations based on the single cell morphology information and protein marker information in the images to obtain cell subpopulations and the number of each cell subpopulation, and using the obtained cell subpopulations and the number of each cell subpopulation as features for training to obtain an immune microenvironment scoring model.

[0066] In one embodiment, known types of immune, tumor, and stromal cells can be identified based on the single-cell morphological information and protein marker information in the image, and potential new cell types can be identified. They are compared with conventional tissue cells to screen out tumor-related cell subpopulations, and the tumor-related cell subpopulations and their numbers are used as candidates for feature training to obtain an immune microenvironment scoring model.

[0067] In one embodiment, the single-cell morphological information is obtained by performing single-cell segmentation on the image of tumor tissue mass spectrometry imaging; preferably, a machine learning algorithm is used to perform single-cell segmentation on the image of tumor tissue mass spectrometry imaging to obtain the single-cell morphological information in the image.

[0068] In one embodiment, the cell subpopulation data is clustered by using the single cell morphology information and protein marker information in the image to obtain the category and quantity of each cell subpopulation; preferably, the clustering is performed using an unsupervised learning method; optionally, after clustering the single cell morphology information and protein marker information in the image, the same cell subpopulations are merged after protein marker visualization to obtain the required category and quantity of each merged cell.

[0069] In a specific embodiment, the built-in machine learning algorithm of CellProfiler is used to perform single-cell segmentation on the mass spectrometry imaging images of tumor tissues. Then, the unsupervised learning algorithm Phenograph is used to perform clustering based on single-cell morphology and protein markers to obtain several cell subpopulations, including epithelial tumor cells, immune cells, and stromal cells. The same subpopulations are merged after visualization of protein markers.

[0070] In one embodiment, the cell subpopulation data and protein marker information are input into an immunotherapy effect model to obtain a prediction result of tumor cell immunotherapy responsiveness. The immunotherapy effect model includes an immune microenvironment scoring model and a tumor cell expression status model. The cell subpopulation data are input into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; the protein marker information in the image is input into the tumor cell expression status model to obtain a prediction result of tumor cell immunotherapy responsiveness of the patient to be tested, and the immunotherapy effect is predicted based on the immune microenvironment score of the patient to be tested and the tumor cell immunotherapy responsiveness prediction result.

[0071] Figure 2 An immunotherapy effect prediction system based on tissue mass spectrometry imaging is provided in an embodiment of the present invention, comprising:

[0072] An acquisition unit 201 is used to acquire a mass spectrometry imaging image of a tumor tissue of a patient to be detected;

[0073] A first extraction unit 202 is used to obtain protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtain tumor cell protein marker expression data;

[0074] The tumor cell expression state unit 203 is used to input the protein marker information in the image into the tumor cell expression state model to obtain the prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested;

[0075] The prediction unit 204 is used to predict the immunotherapy effect of the patient to be tested according to the prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested.

[0076] In a specific embodiment, Figure 3As shown, the immunotherapy effect prediction system based on tissue mass spectrometry imaging comprises:

[0077] An acquisition unit, used for acquiring a mass spectrometry imaging image of a tumor tissue of a patient to be detected;

[0078] A first extraction unit is used to obtain protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtain tumor cell protein marker expression data;

[0079] A tumor cell expression state unit, used to input the protein marker information in the image into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested;

[0080] A second extraction unit is used to obtain single cell morphology information and protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and classify the cell population according to the single cell morphology information and protein marker information in the image to obtain cell subpopulation data;

[0081] An immune microenvironment scoring unit, used to input the cell subset data into an immune microenvironment scoring model to obtain an immune microenvironment score of the patient to be tested;

[0082] The prediction unit is used to predict the immunotherapy effect of the patient to be tested based on the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness.

[0083] Figure 5 An immunotherapy effect prediction device based on tissue mass spectrometry imaging provided by an embodiment of the present invention comprises: a memory and a processor;

[0084] The memory is used to store program instructions;

[0085] The processor is used to call program instructions, and when the program instructions are executed, the above-mentioned immunotherapy effect prediction method steps based on tissue mass spectrometry imaging are implemented.

[0086] One object of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging are implemented.

[0087] The validation results of this validation example show that assigning intrinsic weights to indications can moderately improve the performance of the method relative to the default setting.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0092] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0093] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0094] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An immunotherapy effect prediction device based on tissue mass spectrometry imaging, characterized in that: A memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, a method for predicting the immunotherapy effect based on tissue mass spectrometry imaging is implemented, and the specific method steps include: Acquire a mass spectrometry imaging image of a tumor tissue of a patient to be tested; Obtaining protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging to obtain tumor cell protein marker expression data; Inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested; Predicting the effect of immunotherapy based on the predicted results of the immunotherapy responsiveness of tumor cells in the patient to be tested; The method also includes obtaining single cell morphology information and protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, classifying the cell population according to the single cell morphology information and protein marker information in the image to obtain cell subpopulation data; inputting the cell subpopulation data into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; and predicting the immunotherapy effect according to the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness; The single cell morphology information is obtained by performing single cell segmentation on the image of tumor tissue mass spectrometry imaging; the cell subpopulation data is obtained by clustering the single cell morphology information and protein marker information in the image, and then merging the same cell subpopulations after protein marker visualization to obtain the category and quantity of each merged cell subpopulation.

2. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The cell subpopulation data and protein marker information are input into the immunotherapy effect model to obtain the immunotherapy effect prediction result.

3. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 2, characterized in that: The immunotherapy effect model includes an immune microenvironment scoring model and a tumor cell expression status model. The cell subpopulation data is input into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; the protein marker information in the image is input into the tumor cell expression status model to obtain the prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested, and the immunotherapy effect is predicted based on the immune microenvironment score of the patient to be tested and the tumor cell immunotherapy responsiveness prediction result.

4. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The mass spectrometry imaging image of the patient's tumor tissue to be detected is obtained by performing multi-channel tissue mass spectrometry imaging on the patient's tumor tissue to be detected, and the tumor tissue includes a tumor-immune interface area, a tumor internal area, and a cancer-adjacent area.

5. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The method for acquiring the mass spectrometry imaging image of the tumor tissue of the patient to be detected is: a. distinguishing the tumor-immune interface area, the tumor internal area and the adjacent cancer area of ​​the tumor tissue through pathological morphological analysis; b. performing ROI scanning on each area; c. using the Cytomapper program package to draw a channel synthetic pseudo-color photo.

6. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The protein marker information includes protein marker information of a combination of multiple protein markers.

7. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 6, characterized in that: The protein markers include cell identity protein markers, cell function protein markers, and immune regulation protein markers.

8. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 7, characterized in that: The identity identification protein marker includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I; the cell function protein marker includes one or a combination of the following proteins: dsDNA, Ki-67, HLA-DR, IFN-γ; the immunomodulatory protein marker includes one or a combination of the following proteins: PD1, PDL1, PDL2, TGF-β, TNF-α.

9. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The protein includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I, dsDNA, Ki-67, HLA-DR, IFN-γ, PD1, PDL1, PDL2, TGF-β, TNF-α.

10. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 7, characterized in that: The protein is a combination of the above markers.

11. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: A machine learning algorithm is used to perform single-cell segmentation on tumor tissue mass spectrometry images to obtain single-cell morphological information in the images.

12. The immunotherapy effect prediction device based on tissue mass spectrometry imaging according to claim 1, characterized in that: The clustering is performed using an unsupervised learning method.

13. An immunotherapy effect prediction system based on tissue mass spectrometry imaging, characterized in that: include: An acquisition unit, used for acquiring a mass spectrometry imaging image of a tumor tissue of a patient to be detected; A first extraction unit is used to obtain protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, and obtain tumor cell protein marker expression data; A tumor cell expression state unit, used to input the protein marker information in the image into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested; The second extraction unit is used to obtain single cell morphology information and protein marker information in the image according to the image of the mass spectrometry imaging of the tumor tissue, classify the cell group according to the single cell morphology information and protein marker information in the image, and obtain cell subpopulation data; the single cell morphology information is obtained by performing image single cell segmentation on the image of the mass spectrometry imaging of the tumor tissue; the cell subpopulation data is clustered by the single cell morphology information and protein marker information in the image, and then the same cell subpopulations are merged after protein marker visualization to obtain the category and quantity of each merged cell subpopulation; An immune microenvironment scoring unit, used to input the cell subset data into an immune microenvironment scoring model to obtain an immune microenvironment score of the patient to be tested; The prediction unit is used to predict the immunotherapy effect of the patient to be tested based on the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a method for predicting the effect of immunotherapy based on tissue mass spectrometry imaging is implemented, the method comprising: Acquire a mass spectrometry imaging image of a tumor tissue of a patient to be tested; Obtaining protein marker information in the image according to the image of the mass spectrometry imaging of the tumor tissue, and obtaining tumor cell protein marker expression data; the protein marker information includes protein marker information of a combination of multiple protein markers; the protein markers include cell identity protein markers, cell function protein markers, and immune regulation protein markers; Inputting the tumor cell protein marker expression data into a tumor cell expression state model to obtain a prediction result of the tumor cell immunotherapy responsiveness of the patient to be tested; Predicting the effect of immunotherapy based on the predicted results of the immunotherapy responsiveness of tumor cells in the patient to be tested; The method also includes obtaining single cell morphology information and protein marker information in the image according to the image of the tumor tissue mass spectrometry imaging, classifying the cell population according to the single cell morphology information and protein marker information in the image to obtain cell subpopulation data; inputting the cell subpopulation data into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; and predicting the immunotherapy effect according to the immune microenvironment score of the patient to be tested and the prediction result of tumor cell immunotherapy responsiveness; The single cell morphology information is obtained by performing single cell segmentation on the image of tumor tissue mass spectrometry imaging; the cell subpopulation data is obtained by clustering the single cell morphology information and protein marker information in the image, and then merging the same cell subpopulations after protein marker visualization to obtain the category and quantity of each merged cell subpopulation.

15. The computer-readable storage medium according to claim 14, wherein: The cell subpopulation data and protein marker information are input into the immunotherapy effect model to obtain the immunotherapy effect prediction result.

16. The computer-readable storage medium according to claim 15, wherein: The immunotherapy effect model includes an immune microenvironment scoring model and a tumor cell expression status model. The cell subpopulation data is input into the immune microenvironment scoring model to obtain the immune microenvironment score of the patient to be tested; the protein marker information in the image is input into the tumor cell expression status model to obtain the prediction result of the immunotherapy responsiveness of the tumor cells of the patient to be tested, and the immunotherapy effect is predicted based on the immune microenvironment score of the patient to be tested and the tumor cell immunotherapy responsiveness prediction result.

17. The computer-readable storage medium according to claim 14, wherein: The mass spectrometry imaging image of the patient's tumor tissue to be detected is obtained by performing multi-channel tissue mass spectrometry imaging on the patient's tumor tissue to be detected, and the tumor tissue includes a tumor-immune interface area, a tumor internal area, and a cancer-adjacent area.

18. The computer-readable storage medium according to claim 14, wherein: The method for acquiring the mass spectrometry imaging image of the tumor tissue of the patient to be detected is: a. distinguishing the tumor-immune interface area, the tumor internal area and the adjacent cancer area of ​​the tumor tissue through pathological morphological analysis; b. performing ROI scanning on each area; c. using the Cytomapper program package to draw a channel synthetic pseudo-color photo.

19. The computer-readable storage medium according to claim 14, wherein: The identity identification protein marker includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I; the cell function protein marker includes one or a combination of the following proteins: dsDNA, Ki-67, HLA-DR, IFN-γ; the immunomodulatory protein marker includes one or a combination of the following proteins: PD1, PDL1, PDL2, TGF-β, TNF-α.

20. The computer-readable storage medium of claim 14, wherein: The protein includes one or a combination of the following proteins: CKAE1 / AE3, β-catenin, E-cadherin, CD45, CD3, CD8, CD4, FoxP3, CD11b, CD11c, CD14, CD15, CD16, CD19, CD33, CD56, CD68, Vimentin, αSMA, collagen-I, dsDNA, Ki-67, HLA-DR, IFN-γ, PD1, PDL1, PDL2, TGF-β, TNF-α.

21. The computer-readable storage medium of claim 14, wherein: A machine learning algorithm is used to perform single-cell segmentation on tumor tissue mass spectrometry images to obtain single-cell morphological information in the images.

22. The computer-readable storage medium of claim 14, wherein: The clustering is performed using an unsupervised learning method.

Images