A method and system for distinguishing tumor tissue based on mass spectrometry detection

Abstract

The present invention belongs to the field of tumor tissue discrimination, relates to data analysis technology, and is used to solve the problem that the tumor tissue discrimination method in the prior art cannot combine historical diagnostic data and cross-discrimination methods to improve the accuracy of discrimination results. Specifically, it is a tumor tissue discrimination method and system based on mass spectrometry detection, including a mass spectrometry detection module, a case management module and a discrimination analysis module, the mass spectrometry detection module, the discrimination analysis module and the case management module are communicatively connected in sequence; the mass spectrometry detection module is used to perform mass spectrometry detection and analysis on the patient's tumor tissue, and the case management module is used to perform case analysis on confirmed tumor patients and obtain benign characteristics and malignant characteristics; the present invention can perform case analysis on confirmed tumor patients, extract benign characteristics and malignant characteristics according to the tumor location, and both benign characteristics and malignant characteristics include the characteristic range of the content of each type of protein molecules, so as to discriminate tumors according to the benign characteristics and malignant characteristics.

Description

Technical Field

[0001] The present invention belongs to the field of tumor tissue identification and relates to data analysis technology, and specifically is a tumor tissue identification method and system based on mass spectrometry detection. Background Art

[0002] The tumor tissue identification system based on mass spectrometry detection is an advanced medical diagnostic tool that combines modern biotechnology and computer science. This system uses mass spectrometry detection technology to analyze tumor tissue samples to ensure the accuracy of tumor identification and diagnosis results.

[0003] The tumor tissue identification method in the prior art can only analyze the content of a single protein molecule. The tumor tissue identification results obtained in this way have low accuracy and cannot be combined with historical diagnostic data and cross-identification methods to improve the accuracy of the identification results.

[0004] In view of the above technical problems, this application provides a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a tumor tissue discrimination method and system based on mass spectrometry detection, which is used to solve the problem that the tumor tissue discrimination method in the prior art cannot combine historical diagnostic data and cross-discrimination methods to improve the accuracy of the discrimination results;

[0006] The technical problem to be solved by the present invention is: how to provide a tumor tissue discrimination method and system based on mass spectrometry detection that can combine historical diagnostic data with a cross-discrimination method to improve the accuracy of the discrimination results.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A tumor tissue discrimination system based on mass spectrometry detection comprises a mass spectrometry detection module, a case management module and a discrimination analysis module, wherein the mass spectrometry detection module, the discrimination analysis module and the case management module are sequentially connected in communication;

[0009] The mass spectrometry detection module is used to perform mass spectrometry detection and analysis on the patient's tumor tissue: the patient's tumor tissue sample is analyzed using mass spectrometry detection technology to obtain a detection index JCi, i=1, 2, ..., n, n is a positive integer, and the detection index JCi represents the biomolecule content of different proteins in the tumor tissue;

[0010] The case management module is used to analyze the cases of confirmed tumor patients and obtain benign features and malignant features, and send the benign features and malignant features to the discrimination analysis module;

[0011] The discriminant analysis module is used to perform discriminant analysis on the patient's tumor tissue type, generate a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal according to the discriminant analysis result, and send it to the administrator's mobile phone terminal.

[0012] As a preferred embodiment of the present invention, the specific process of case analysis of confirmed tumor patients by the case management module includes: obtaining the tumor location of the tumor patient, marking the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location, respectively, obtaining the diagnostic index ZDi of all benign objects at the tumor location when confirmed, the protein type corresponding to the diagnostic index ZDi and the detection index JCi is the same; and performing benign feature extraction and malignant feature extraction on benign objects and malignant objects, respectively.

[0013] As a preferred embodiment of the present invention, the specific process of extracting benign features from benign objects includes: forming a first benign set from the diagnostic index ZD1 of all benign objects, performing variance calculation on the first benign set to obtain a benign coefficient, and comparing the benign coefficient with a benign threshold: if the benign coefficient is greater than the benign threshold, eliminating the maximum value and the minimum value of the elements in the first benign set, recalculating the benign coefficient and comparing the benign coefficient with the benign threshold again until the benign coefficient is less than or equal to the benign threshold; if the benign coefficient is less than or equal to the benign threshold, forming a benign diagnostic range of the diagnostic index ZD1 from the minimum value and the maximum value of the elements in the first benign set; then forming a second benign set from the diagnostic index ZD2 of all benign objects and obtaining the benign diagnostic range of the diagnostic index ZD2, and so on, until the benign diagnostic range of the diagnostic index ZDn is obtained, and all benign diagnostic ranges constitute the benign features of the benign objects.

[0014] As a preferred embodiment of the present invention, the specific process of extracting the malignant feature of the malignant object includes: forming a first malignant set with the diagnostic indexes ZDi of all malignant objects, performing variance calculation on the first malignant set to obtain a malignant coefficient, and comparing the malignant coefficient with a preset malignant threshold: if the malignant coefficient is greater than the malignant threshold, eliminating the maximum value and the minimum value of the elements in the first malignant set, recalculating the malignant coefficient and comparing the malignant coefficient with the malignant threshold again until the malignant coefficient is less than or equal to the malignant threshold; if the malignant coefficient is less than the malignant threshold, forming a malignant diagnostic range of the diagnostic index ZD1 with the minimum value and the maximum value of the elements in the first malignant set; then forming a second malignant set with the diagnostic indexes ZD2 of all malignant objects and obtaining the malignant diagnostic range of the diagnostic index ZD2, and so on, until the malignant diagnostic range of the diagnostic index ZDn is obtained, and all malignant diagnostic ranges constitute the malignant feature of the malignant object.

[0015] As a preferred embodiment of the present invention, the specific process of the discriminant analysis module performing discriminant analysis on the patient's tumor tissue type includes: randomly combining the protein types in the detection index JCi in pairs to obtain several protein combinations, and marking the protein combinations as benign combinations or malignant combinations; marking the ratio of the number of benign combinations to the number of protein combinations as a benign coefficient, marking the ratio of the number of malignant combinations to the number of protein combinations as a malignant coefficient, marking the absolute value of the difference between the benign coefficient and the malignant coefficient as a fuzzy value, comparing the fuzzy value with a preset fuzzy threshold and generating a benign diagnostic signal, a malignant diagnostic signal or a physician intervention signal through the comparison result.

[0016] As a preferred embodiment of the present invention, the specific process of marking a protein combination as a benign combination or a malignant combination includes: marking the values ​​of the two protein types in the protein combination in the patient detection index JDi as ZHa and ZHb, respectively, marking the benign diagnostic range and the malignant diagnostic range of the two protein types in the protein combination in the corresponding tumor position of the patient's tumor tissue as LXa, LXb, EXa and EXb, respectively, if ZHa∈LXa, ZHb∈LXb and ZHa∉EXa, ZHb∉EXb, then the corresponding protein combination is marked as a benign combination; if ZHa∈EXa, ZHb∈EXb and ZHa∉LXa, ZHb∉LXb, then the corresponding protein combination is marked as a malignant combination.

[0017] As a preferred embodiment of the present invention, the specific process of comparing the fuzzy value with the preset fuzzy threshold includes: if the fuzzy value is less than or equal to the fuzzy threshold, the number of protein types in all malignant combinations is marked as a malignant expression value, and the number of protein types in all benign combinations is marked as a benign expression value, and the malignant expression value is compared with the benign expression value: if the malignant expression value is less than the benign expression value, a benign diagnosis signal is generated and the benign diagnosis signal is sent to the mobile phone terminal of the administrator; if the malignant expression value is equal to the benign expression value, a physician intervention signal is generated and the physician intervention signal is sent to the mobile phone terminal of the administrator; if the malignant expression value is greater than the benign expression value, a malignant diagnosis signal is generated and the malignant diagnosis signal is sent to the mobile phone terminal of the administrator; if the fuzzy value is greater than the fuzzy threshold, the benign coefficient is compared with the malignant coefficient: if the benign coefficient is greater than the malignant coefficient, a benign diagnosis signal is generated and the benign diagnosis signal is sent to the mobile phone terminal of the administrator; if the benign coefficient is less than the malignant coefficient, a malignant diagnosis signal is generated and the malignant diagnosis signal is sent to the mobile phone terminal of the administrator.

[0018] A method for distinguishing tumor tissue based on mass spectrometry detection comprises the following steps:

[0019] Step 1: Perform mass spectrometry analysis on the patient's tumor tissue: Use mass spectrometry detection technology to analyze the patient's tumor tissue sample to obtain the detection index JCi;

[0020] Step 2: Conduct case analysis on confirmed tumor patients: obtain the tumor location of the tumor patient, mark the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location, respectively, and perform benign feature extraction and malignant feature extraction on the benign objects and malignant objects respectively;

[0021] Step 3: Discriminant analysis of the patient's tumor tissue type: Randomly combine the protein types in the detection index JCi in pairs to obtain several protein combinations, and mark the protein combinations as benign combinations or malignant combinations based on benign and malignant characteristics;

[0022] Step 4: Mark the ratio of the number of benign combinations to the number of protein combinations as a benign coefficient, mark the ratio of the number of malignant combinations to the number of protein combinations as a malignant coefficient, mark the absolute value of the difference between the benign coefficient and the malignant coefficient as a fuzzy value, compare the fuzzy value with the fuzzy threshold and generate a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal through the comparison result.

[0023] The present invention has the following beneficial effects:

[0024] 1. The mass spectrometry detection module can be used to perform mass spectrometry detection and analysis on the patient's tumor tissue. The patient's tumor tissue sample can be analyzed to obtain the detection index, which includes the content of various types of protein molecules and provides data support for the discriminant analysis process;

[0025] 2. The case management module can be used to analyze the cases of confirmed tumor patients, and extract benign and malignant features according to the location of the tumor. Both benign and malignant features include the characteristic range of the content of each type of protein molecule, so as to distinguish tumors based on benign and malignant features, thereby improving the efficiency of distinction and the accuracy of diagnostic results;

[0026] 3. The discriminant analysis module can be used to discriminate the patient's tumor tissue type and obtain protein combinations in a random manner, eliminating the limitations of the analysis results of a single type of protein molecule content, so that each group of protein combinations contains different types of protein molecule content data. The historical data and mass spectrometry detection data are fused and analyzed in a cross-combination manner to improve the accuracy of the diagnostic results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1

[0032] like Figure 1 As shown, a tumor tissue discrimination system based on mass spectrometry detection includes a mass spectrometry detection module, a case management module and a discrimination analysis module. The mass spectrometry detection module, the discrimination analysis module and the case management module are communicatively connected in sequence.

[0033] The mass spectrometry detection module is used to perform mass spectrometry detection and analysis on the patient's tumor tissue: the patient's tumor tissue sample is analyzed using mass spectrometry detection technology to obtain a detection index JCi, i=1, 2, ..., n, n is a positive integer, and the detection index JCi represents the biomolecule content of different proteins in the tumor tissue. For example, the detection index JC1 represents the biomolecule content of carcinoembryonic antigen, JC2 represents the biomolecule content of alpha-fetoprotein, and JC3 represents the biomolecule content of basic fetal protein, etc.; the patient's detection index JCi is sent to the discriminant analysis module; the patient's tumor tissue is subjected to mass spectrometry detection and analysis, and the patient's tumor tissue sample is analyzed to obtain a detection index, which includes the content of multiple types of protein molecules, providing data support for the discriminant analysis process.

[0034] The case management module is used to perform case analysis on confirmed tumor patients: obtain the tumor location of the tumor patient, mark the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location respectively, obtain the diagnostic index ZDi of all benign objects at the tumor location when they are diagnosed, the protein type corresponding to the diagnostic index ZDi and the detection index JCi are the same, and benign features are extracted for benign objects: the first benign set is formed by the diagnostic index ZD1 of all benign objects, the variance of the first benign set is calculated to obtain the benign coefficient, and the benign coefficient is compared with the benign threshold: if the benign coefficient is larger than the benign threshold, the benign coefficient is smaller than the benign threshold. If the benign coefficient is less than or equal to the benign threshold, the maximum value and the minimum value of the elements in the first benign set are eliminated, the benign coefficient is recalculated and the benign coefficient is compared with the benign threshold again until the benign coefficient is less than or equal to the benign threshold; if the benign coefficient is less than or equal to the benign threshold, the minimum value and the maximum value of the elements in the first benign set constitute the benign diagnostic range of the diagnostic index ZD1; then the diagnostic indexes ZD2 of all benign objects constitute the second benign set and the benign diagnostic range of the diagnostic index ZD2 is obtained, and so on, until the benign diagnostic range of the diagnostic index ZDn is obtained, and all benign diagnostic ranges constitute the benign diagnostic range of the benign objects. malignant features; extract malignant features from malignant objects: the first malignant set is formed by the diagnostic indexes ZDi of all malignant objects, the variance of the first malignant set is calculated to obtain the malignant coefficient, and the malignant coefficient is compared with the preset malignant threshold: if the malignant coefficient is greater than the malignant threshold, the maximum value and the minimum value of the elements in the first malignant set are eliminated, the malignant coefficient is recalculated and the malignant coefficient is compared with the malignant threshold again until the malignant coefficient is less than or equal to the malignant threshold; if the malignant coefficient is less than the malignant threshold, the minimum value and the maximum value of the elements in the first malignant set form the malignant diagnostic range of the diagnostic index ZD1 ; Then, the diagnostic index ZD2 of all malignant objects constitutes a second malignant set and obtains the malignant diagnostic range of the diagnostic index ZD2, and so on, until the malignant diagnostic range of the diagnostic index ZDn is obtained, and the malignant characteristics of the malignant objects are constituted by all malignant diagnostic ranges; the benign characteristics and the malignant characteristics are sent to the discriminant analysis module; case analysis is performed on confirmed tumor patients, and benign characteristics and malignant characteristics are extracted according to the tumor location. Both benign characteristics and malignant characteristics include the characteristic range of the content of each type of protein molecules, so that tumors are discriminated based on the benign characteristics and the malignant characteristics, thereby improving the discrimination efficiency and the accuracy of the diagnostic results.

[0035] The discriminant analysis module is used to discriminate the tumor tissue type of the patient: the protein types in the detection index JCi are randomly combined in pairs to obtain several protein combinations, and the values ​​of the two protein types in the protein combination in the patient detection index JDi are marked as ZHa and ZHb respectively, and the benign diagnosis range and malignant diagnosis range of the two protein types in the protein combination in the corresponding tumor position of the patient's tumor tissue are marked as LXa, LXb, EXa and EXb respectively. If ZHa∈LXa, ZHb∈LXb and ZHa∉EXa, ZHb∉EXb, then the corresponding The protein combination is marked as a benign combination; if ZHa∈EXa, ZHb∈EXb and ZHa∉LXa, ZHb∉LXb, the corresponding protein combination is marked as a malignant combination; the ratio of the number of benign combinations to the number of protein combinations is marked as a benign coefficient, the ratio of the number of malignant combinations to the number of protein combinations is marked as a malignant coefficient, the absolute value of the difference between the benign coefficient and the malignant coefficient is marked as a fuzzy value, and the fuzzy value is compared with a preset fuzzy threshold: if the fuzzy value is less than or equal to the fuzzy threshold, the number of protein types in all malignant combinations is marked as a malignant expression value, and all benign combinations are marked as malignant combinations. The number of protein types in the combination is marked as a benign expression value, and the malignant expression value is compared with the benign expression value: if the malignant expression value is less than the benign expression value, a benign diagnosis signal is generated and sent to the mobile terminal of the administrator; if the malignant expression value is equal to the benign expression value, a physician intervention signal is generated and sent to the mobile terminal of the administrator; if the malignant expression value is greater than the benign expression value, a malignant diagnosis signal is generated and sent to the mobile terminal of the administrator; if the fuzzy value is greater than the fuzzy threshold, the benign coefficient is compared with the malignant coefficient: if the benign coefficient is greater than the malignant coefficient, a benign diagnosis signal is generated and sent to the mobile terminal of the administrator; if the benign coefficient is less than the malignant coefficient, a malignant diagnosis signal is generated and sent to the mobile terminal of the administrator; the patient's tumor tissue type is discriminated and analyzed, and a protein combination is obtained in a random combination manner, eliminating the limitations brought by the analysis results of a single type of protein molecule content, so that each group of protein combinations has different types of protein molecule content data, and the historical data and mass spectrometry detection data are fused and analyzed in a cross-combination manner to improve the accuracy of the diagnosis results.

[0036] Embodiment 2

[0037] like Figure 2 As shown, a tumor tissue identification method based on mass spectrometry detection comprises the following steps:

[0038] Step 1: Perform mass spectrometry analysis on the patient's tumor tissue: Use mass spectrometry detection technology to analyze the patient's tumor tissue sample to obtain the detection index JCi;

[0039] Step 2: Conduct case analysis on confirmed tumor patients: obtain the tumor location of the tumor patient, mark the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location, respectively, and perform benign feature extraction and malignant feature extraction on the benign objects and malignant objects respectively;

[0040] Step 3: Discriminant analysis of the patient's tumor tissue type: Randomly combine the protein types in the detection index JCi in pairs to obtain several protein combinations, and mark the protein combinations as benign combinations or malignant combinations based on benign and malignant characteristics;

[0041] Step 4: Mark the ratio of the number of benign combinations to the number of protein combinations as a benign coefficient, mark the ratio of the number of malignant combinations to the number of protein combinations as a malignant coefficient, mark the absolute value of the difference between the benign coefficient and the malignant coefficient as a fuzzy value, compare the fuzzy value with the fuzzy threshold and generate a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal through the comparison result.

[0042] A method and system for distinguishing tumor tissue based on mass spectrometry detection. When working, the mass spectrometry detection technology is used to analyze the tumor tissue sample of the patient to obtain the detection index JCi; the tumor position of the tumor patient is obtained, and the benign tumor patients and malignant tumor patients at the same tumor position are marked as benign objects and malignant objects at the tumor position respectively, and benign features and malignant features are extracted from the benign objects and malignant objects respectively; the protein types in the detection index JCi are randomly combined in pairs to obtain several protein combinations, and the protein combinations are marked as benign combinations or malignant combinations through benign features and malignant features; the ratio of the number of benign combinations to the number of protein combinations is marked as a benign coefficient, the ratio of the number of malignant combinations to the number of protein combinations is marked as a malignant coefficient, the absolute value of the difference between the benign coefficient and the malignant coefficient is marked as a fuzzy value, the fuzzy value is compared with the fuzzy threshold, and a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal is generated through the comparison result.

[0043] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0045] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A tumor tissue identification system based on mass spectrometry detection, It is characterized in that It includes a mass spectrometry detection module, a case management module and a discrimination analysis module, wherein the mass spectrometry detection module, the discrimination analysis module and the case management module are sequentially connected in communication; The mass spectrometry detection module is used to perform mass spectrometry detection and analysis on the patient's tumor tissue: the patient's tumor tissue sample is analyzed using mass spectrometry detection technology to obtain a detection index JCi, i=1, 2, ..., n, n is a positive integer, and the detection index JCi represents the biomolecule content of different proteins in the tumor tissue; The case management module is used to analyze the cases of confirmed tumor patients and obtain benign features and malignant features, and send the benign features and malignant features to the discrimination analysis module; The discriminant analysis module is used to discriminate and analyze the patient's tumor tissue type, generate a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal according to the discriminant analysis result, and send it to the mobile phone terminal of the administrator; The specific process of case analysis of confirmed tumor patients by the case management module includes: obtaining the tumor location of the tumor patient, marking the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location respectively, obtaining the diagnostic index ZDi of all benign objects at the tumor location when they are diagnosed, and the corresponding protein types of the diagnostic index ZDi and the detection index JCi are the same; benign feature extraction and malignant feature extraction are performed on benign objects and malignant objects respectively; The specific process of extracting benign features of benign objects includes: forming a first benign set from the diagnostic indexes ZD1 of all benign objects, performing variance calculation on the first benign set to obtain a benign coefficient, and comparing the benign coefficient with a benign threshold: if the benign coefficient is greater than the benign threshold, eliminating the maximum value and the minimum value of the elements in the first benign set, recalculating the benign coefficient and comparing the benign coefficient with the benign threshold again until the benign coefficient is less than or equal to the benign threshold; if the benign coefficient is less than or equal to the benign threshold, forming a benign diagnostic range of the diagnostic index ZD1 from the minimum value and the maximum value of the elements in the first benign set; then forming a second benign set from the diagnostic indexes ZD2 of all benign objects and obtaining a benign diagnostic range of the diagnostic index ZD2, and so on, until the benign diagnostic range of the diagnostic index ZDn is obtained, and all benign diagnostic ranges constitute the benign features of the benign objects; The specific process of extracting the malignant features of the malignant objects includes: forming a first malignant set from the diagnostic indexes ZDi of all malignant objects, performing variance calculation on the first malignant set to obtain a malignant coefficient, and comparing the malignant coefficient with a preset malignant threshold: if the malignant coefficient is greater than the malignant threshold, eliminating the maximum value and the minimum value of the elements in the first malignant set, recalculating the malignant coefficient and comparing the malignant coefficient with the malignant threshold again until the malignant coefficient is less than or equal to the malignant threshold; if the malignant coefficient is less than the malignant threshold, forming a malignant diagnostic range of the diagnostic index ZD1 from the minimum value and the maximum value of the elements in the first malignant set; then forming a second malignant set from the diagnostic indexes ZD2 of all malignant objects and obtaining the malignant diagnostic range of the diagnostic index ZD2, and so on, until the malignant diagnostic range of the diagnostic index ZDn is obtained, and all the malignant diagnostic ranges constitute the malignant features of the malignant objects; The specific process of the discriminant analysis module for discriminant analysis of the patient's tumor tissue type includes: randomly combining the protein types in the detection index JCi in pairs to obtain several protein combinations, and marking the protein combinations as benign combinations or malignant combinations; marking the ratio of the number of benign combinations to the number of protein combinations as a benign coefficient, marking the ratio of the number of malignant combinations to the number of protein combinations as a malignant coefficient, marking the absolute value of the difference between the benign coefficient and the malignant coefficient as a fuzzy value, comparing the fuzzy value with a preset fuzzy threshold and generating a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal through the comparison result.

2. A tumor tissue identification system based on mass spectrometry detection according to claim 1, It is characterized in that The specific process of marking a protein combination as a benign combination or a malignant combination includes: marking the values ​​of the two protein types in the protein combination in the patient detection index JDi as ZHa and ZHb respectively, marking the benign diagnosis range and malignant diagnosis range of the two protein types in the protein combination in the corresponding tumor position of the patient's tumor tissue as LXa, LXb, EXa and EXb respectively, if ZHa∈LXa, ZHb∈LXb and ZHa EXa,ZHb EXb, the corresponding protein combination is marked as a benign combination; if ZHa∈EXa, ZHb∈EXb and ZHa LXa,ZHb LXb, the corresponding protein combination is marked as a malignant combination.

3. A tumor tissue identification system based on mass spectrometry detection according to claim 2, It is characterized in that The specific process of comparing the fuzzy value with the preset fuzzy threshold includes: if the fuzzy value is less than or equal to the fuzzy threshold, the number of protein types in all malignant combinations is marked as the malignant expression value, the number of protein types in all benign combinations is marked as the benign expression value, and the malignant expression value is compared with the benign expression value: if the malignant expression value is less than the benign expression value, a benign diagnosis signal is generated and the benign diagnosis signal is sent to the mobile phone terminal of the administrator; if the malignant expression value is equal to the benign expression value, a physician intervention signal is generated and the physician intervention signal is sent to the mobile phone terminal of the administrator; if the malignant expression value is greater than the benign expression value, a malignant diagnosis signal is generated and the malignant diagnosis signal is sent to the mobile phone terminal of the administrator; if the fuzzy value is greater than the fuzzy threshold, the benign coefficient is compared with the malignant coefficient: if the benign coefficient is greater than the malignant coefficient, a benign diagnosis signal is generated and the benign diagnosis signal is sent to the mobile phone terminal of the administrator; if the benign coefficient is less than the malignant coefficient, a malignant diagnosis signal is generated and the malignant diagnosis signal is sent to the mobile phone terminal of the administrator.

4. A method for distinguishing tumor tissue based on mass spectrometry for non-diagnostic purposes, It is characterized in that The following steps are involved: Step 1: Perform mass spectrometry analysis on the patient's tumor tissue: Use mass spectrometry detection technology to analyze the patient's tumor tissue sample to obtain the detection index JCi; Step 2: Conduct case analysis on confirmed tumor patients: obtain the tumor location of the tumor patient, mark the benign tumor patients and malignant tumor patients at the same tumor location as benign objects and malignant objects at the tumor location, respectively, and perform benign feature extraction and malignant feature extraction on the benign objects and malignant objects respectively; Step 3: Discriminant analysis of the patient's tumor tissue type: Randomly combine the protein types in the detection index JCi in pairs to obtain several protein combinations, and mark the protein combinations as benign combinations or malignant combinations based on benign and malignant characteristics; Step 4: Mark the ratio of the number of benign combinations to the number of protein combinations as a benign coefficient, mark the ratio of the number of malignant combinations to the number of protein combinations as a malignant coefficient, mark the absolute value of the difference between the benign coefficient and the malignant coefficient as a fuzzy value, compare the fuzzy value with the fuzzy threshold and generate a benign diagnosis signal, a malignant diagnosis signal or a physician intervention signal through the comparison result.

Images