Intelligent analysis system for benign and malignant breast cancer based on artificial intelligence

Abstract

The present invention discloses an artificial intelligence-based intelligent analysis system for breast cancer benign and malignant conditions, belonging to the field of breast cancer technology, and comprising: a data collection module for collecting historical breast cancer data; a data processing module for processing historical breast cancer data; a model training module for constructing an intelligent analysis model for breast cancer benign and malignant conditions and determining the optimal intelligent analysis model for breast cancer benign and malignant conditions; an intelligent analysis module for performing intelligent analysis on the benign and malignant conditions of a patient's breast cancer and determining the intelligent analysis results for the patient's breast cancer benign and malignant conditions; and an output management module for outputting the intelligent analysis results for the patient's breast cancer benign and malignant conditions. The present invention solves the problem that existing systems cannot perform intelligent analysis and effectively identify and classify benign and malignant breast cancer, resulting in poor results in intelligent analysis of benign and malignant breast cancer. The present invention can perform intelligent analysis and effectively identify and classify benign and malignant breast cancer, thereby improving the results of intelligent analysis of benign and malignant breast cancer.

Description

Technical Field

[0001] The present invention relates to the technical field of breast cancer, and in particular to an artificial intelligence-based intelligent analysis system for benign and malignant breast cancer. Background Art

[0002] With the development of science and technology, the application of artificial intelligence in the medical field has become more and more extensive. In recent years, breast cancer has become one of the most common malignant tumors in women, and its early diagnosis and treatment have an important impact on the patient's prognosis.

[0003] Existing technologies, such as manual diagnosis and X-rays, cannot perform intelligent analysis and effectively identify and classify benign and malignant breast cancer, resulting in poor results in intelligent analysis of benign and malignant breast cancer. Summary of the Invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based intelligent analysis system for benign and malignant breast cancer, which can perform intelligent analysis and effectively identify and classify benign and malignant breast cancer, improve the effect of intelligent analysis of benign and malignant breast cancer, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The AI-based intelligent analysis system for benign and malignant breast cancer includes:

[0007] The data collection module is used to collect the patient's personal medical history data, medical imaging data, pathological tissue data and genomic data to determine the AI-based breast cancer historical data;

[0008] a data processing module for processing AI-based breast cancer historical data and determining AI-based breast cancer characteristic data;

[0009] The model training module is used to build an AI-based intelligent analysis model for breast cancer benign and malignant diseases, and to test and optimize the AI-based intelligent analysis model for breast cancer benign and malignant diseases to determine the optimal intelligent analysis model for breast cancer benign and malignant diseases;

[0010] Intelligent analysis module, used to perform intelligent analysis on the benign and malignant status of the patient's breast cancer and determine the intelligent analysis results of the patient's breast cancer;

[0011] The output management module is used to output the intelligent analysis results of the patient's breast cancer benign and malignant status, and to display the intelligent analysis report of the patient's breast cancer benign and malignant status in a visual form, and to perform intelligent treatment management of the patient's breast cancer.

[0012] Preferably, the data collection module includes:

[0013] The personal medical history collection unit is used to collect the patient's age, gender, family medical history, past medical history, menstrual status and reproductive history to obtain personal medical history data;

[0014] A medical image collection unit, used to collect mammograms, ultrasound images, and magnetic resonance imaging of patients to obtain medical image data;

[0015] Pathological tissue collection unit, used to collect pathological sections and immunohistochemistry of patients and obtain pathological tissue data;

[0016] A genomics collection unit is used to collect the patient's gene expression profile, gene mutation and amplified genetic information to obtain genomics data;

[0017] Among them, artificial intelligence-based breast cancer historical data is determined based on personal medical history data, medical imaging data, pathological tissue data and genomic data.

[0018] Preferably, the data processing module includes:

[0019] A data cleaning unit, used to clean historical breast cancer data based on artificial intelligence;

[0020] Based on data cleaning tools, duplicate values, missing values, and outliers in AI-based breast cancer historical data are identified and processed;

[0021] When duplicate values ​​exist in AI-based breast cancer historical data, the duplicate values ​​are removed;

[0022] When missing values ​​exist in AI-based breast cancer historical data, samples containing missing values ​​are deleted or the median is used to fill the missing values;

[0023] When outliers exist in AI-based breast cancer historical data, samples containing outliers are deleted or the average value is used to replace the outliers.

[0024] Preferably, the data processing module further includes:

[0025] A data conversion unit, used to convert historical breast cancer data based on artificial intelligence;

[0026] Perform format and type conversion on AI-based breast cancer historical data, remove dimensional differences among AI-based breast cancer historical data, and determine standardized breast cancer historical data;

[0027] A feature extraction unit, used for extracting features from standardized breast cancer historical data;

[0028] Based on the random forest algorithm of feature importance evaluation, the extracted features are evaluated for their importance, the influence of the extracted features on the classification of benign and malignant breast cancer is evaluated, the features that can best distinguish benign and malignant breast cancer lesions are selected, and the breast cancer feature data based on artificial intelligence is determined.

[0029] Preferably, the model training module includes:

[0030] a data partitioning unit, configured to partition the artificial intelligence-based breast cancer feature data into a training set and a test set;

[0031] A model building unit, used to build an AI-based intelligent analysis model for benign and malignant breast cancer;

[0032] Based on deep learning technology, the training set and the benign and malignant breast cancer labels are input into the deep learning model. Through continuous training iterations, the deep learning model can autonomously learn the benign and malignant breast cancer classification and determine the AI-based intelligent analysis model for benign and malignant breast cancer.

[0033] The test set is input into the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is tested based on the test set to determine whether the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer can achieve the intelligent analysis and classification effect of benign and malignant breast cancer.

[0034] Preferably, determining whether the artificial intelligence-based intelligent analysis model for breast cancer benign and malignant can achieve the effect of intelligent analysis and classification of breast cancer benign and malignant includes:

[0035] Obtain the test set to perform a performance test on the AI-based intelligent analysis model for benign and malignant breast cancer. Based on the precision and recall of the AI-based intelligent analysis model for benign and malignant breast cancer, determine whether the AI-based intelligent analysis model for benign and malignant breast cancer can achieve the desired classification effect.

[0036] When the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer cannot achieve the intelligent analysis and classification effect of benign and malignant breast cancer, the parameters and structure of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer are continuously adjusted, the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is continuously iteratively optimized, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is verified based on the cross-validation method to achieve the best benign and malignant breast cancer classification effect and determine the optimal intelligent analysis model for benign and malignant breast cancer.

[0037] Preferably, the intelligent analysis module includes:

[0038] A model deployment unit, used to deploy the optimal breast cancer benign and malignant intelligent analysis model in an actual breast cancer benign and malignant intelligent analysis environment;

[0039] Intelligent analysis unit, used to intelligently analyze the benign and malignant status of patients' breast cancer;

[0040] The patient's real-time breast cancer data is input into the optimal intelligent analysis model for benign and malignant breast cancer. Based on the optimal intelligent analysis model for benign and malignant breast cancer, the patient's real-time breast cancer data is intelligently analyzed, and the patient's breast cancer is classified as benign and malignant to determine the intelligent analysis result of the patient's breast cancer, wherein the intelligent analysis result of the patient's breast cancer is benign or malignant.

[0041] Preferably, the output management module includes:

[0042] The output display unit is used to output the intelligent analysis results of the patient's breast cancer benign and malignant nature, analyze the patient's real-time breast cancer data and the intelligent analysis results of the patient's breast cancer benign and malignant nature, generate the patient's breast cancer benign and malignant intelligent analysis report, and display the patient's breast cancer benign and malignant intelligent analysis report in a visual form, so that doctors and patients can more intuitively understand the benign and malignant nature of the patient's breast cancer;

[0043] The analysis and management unit is used to intelligently manage the benign and malignant conditions of the patient's breast cancer. According to the intelligent analysis results of the patient's breast cancer, a breast cancer treatment plan is formulated for the patient, and the patient's breast cancer is intelligently managed based on the breast cancer treatment plan.

[0044] Preferably, personal medical history data, medical imaging data, pathological tissue data and genomic data are preprocessed to obtain preprocessed data;

[0045] Extracting tissue pathology feature vectors based on pre-processed medical imaging data and pathological tissue data, and extracting gene mutation molecular feature vectors based on pre-processed genomic data;

[0046] Fusing the tissue pathology feature vector with the gene mutation molecular feature vector to obtain the patient's fused multimodal features;

[0047] Determine the patient's gene differential expression parameters based on the fusion of multimodal features, and determine the cell transcription profile expression data based on the gene differential expression parameters;

[0048] Determine the patient's candidate mutation genes based on cell transcriptional profile expression data, and determine the patient's cancer signature based on the candidate mutation genes;

[0049] Determine the patient's mRNA and miRNA data under cancerous lesions based on the cancer label, and obtain the patient's pathological image features based on the pre-processed medical imaging data;

[0050] Reconstruct the pathological image features with the mRNA data and miRNA data to obtain the pathological image feature matrix, mRNA expression matrix and miRNA expression matrix;

[0051] Construct a correlation structure diagram based on the pathological image feature matrix, mRNA expression matrix, and miRNA expression matrix;

[0052] According to the association structure diagram, the pre-processed personal medical history data, medical imaging data, pathological tissue data and genomic data are labeled and packaged to generate an integrated file;

[0053] Generate AI-based historical breast cancer data from integrated files.

[0054] Preferably, after obtaining the medical imaging data, the method further includes:

[0055] Obtain the pixel grayscale value of each pixel in the medical image data and determine the image clutter degree of the medical image based on the pixel grayscale value:

[0056]

[0057] Among them, Q represents the image clutter degree of the medical image, M represents the number of regions into which the medical image is divided into equal-area regions, and i represents the i-th divided region. It is expressed as the average pixel gray value of the i-th divided area, and ln is expressed as the natural logarithm;

[0058] Determine the uniformity of pixel grayscale distribution of the medical image according to the image clutter degree of the medical image, and determine whether contrast enhancement of the medical image is required according to the uniformity of pixel grayscale distribution;

[0059] If so, the contrast enhancement of medical images is achieved through the following formula:

[0060]

[0061] in, Represented as the grayscale value of the output medical image, Expressed as a dynamic coefficient, Represented as the grayscale value of the input medical image, Expressed as the average value of grayscale in the neighborhood of point (i, j);

[0062] The enhanced medical images are used as medical imaging reference data.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The present invention collects the patient's personal medical history data, medical imaging data, pathological tissue data and genomic data to determine artificial intelligence-based breast cancer historical data, processes the artificial intelligence-based breast cancer historical data to determine artificial intelligence-based breast cancer characteristic data, constructs an artificial intelligence-based intelligent analysis model for benign and malignant breast cancer, and tests and optimizes the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer to determine the optimal intelligent analysis model for benign and malignant breast cancer. Based on the optimal intelligent analysis model for benign and malignant breast cancer, the patient's real-time breast cancer data is intelligently analyzed, the patient's breast cancer is classified, the patient's benign and malignant intelligent analysis results for the patient's breast cancer are determined, and the intelligent analysis results for the patient's breast cancer are output, and a benign and malignant intelligent analysis report for the patient's breast cancer is displayed in a visual form. Intelligent treatment management of the patient's breast cancer is performed, and benign and malignant breast cancer can be intelligently analyzed and effectively identified and classified, thereby improving the effect of intelligent analysis of benign and malignant breast cancer. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a module block diagram of the artificial intelligence-based intelligent analysis system for benign and malignant breast cancer of the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] In order to solve the existing problem of being unable to intelligently analyze and effectively classify benign and malignant breast cancer, which leads to poor results in intelligent analysis of benign and malignant breast cancer, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0068] The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer includes: a data collection module, a data processing module, a model training module, an intelligent analysis module and an output management module.

[0069] It should be noted that through the interactive communication between the data collection module, data processing module, model training module, intelligent analysis module and output management module, intelligent analysis and effective identification and classification of benign and malignant breast cancer can be performed, which can improve the effect of intelligent analysis of benign and malignant breast cancer.

[0070] Among them, the patient's personal medical history data, medical imaging data, pathological tissue data and genomic data are collected through the data collection module to determine the breast cancer historical data based on artificial intelligence.

[0071] In this embodiment, as a preferred technical solution of the present invention, the data collection module includes:

[0072] The personal medical history collection unit is used to collect the patient's age, gender, family medical history, past medical history, menstrual status and reproductive history to obtain personal medical history data;

[0073] A medical image collection unit, used to collect mammograms, ultrasound images, and magnetic resonance imaging of patients to obtain medical image data;

[0074] Pathological tissue collection unit, used to collect pathological sections and immunohistochemistry of patients and obtain pathological tissue data;

[0075] A genomics collection unit is used to collect the patient's gene expression profile, gene mutation and amplified genetic information to obtain genomics data;

[0076] Among them, artificial intelligence-based breast cancer historical data is determined based on personal medical history data, medical imaging data, pathological tissue data and genomic data.

[0077] Among them, the artificial intelligence-based breast cancer historical data is processed by the data processing module to determine the artificial intelligence-based breast cancer characteristic data.

[0078] In this embodiment, as a preferred technical solution of the present invention, the data processing module includes:

[0079] A data cleaning unit, used to clean historical breast cancer data based on artificial intelligence;

[0080] Based on data cleaning tools, duplicate values, missing values, and outliers in AI-based breast cancer historical data are identified and processed;

[0081] When duplicate values ​​exist in AI-based breast cancer historical data, the duplicate values ​​are removed;

[0082] When missing values ​​exist in AI-based breast cancer historical data, samples containing missing values ​​are deleted or the median is used to fill the missing values;

[0083] When outliers exist in AI-based breast cancer historical data, samples containing outliers are deleted or replaced with the average value;

[0084] It should be noted that by cleaning the AI-based breast cancer historical data, the subsequent processing accuracy and speed of the AI-based breast cancer historical data can be improved.

[0085] A data conversion unit, used to convert historical breast cancer data based on artificial intelligence;

[0086] Perform format and type conversion on AI-based breast cancer historical data, remove dimensional differences among AI-based breast cancer historical data, and determine standardized breast cancer historical data;

[0087] A feature extraction unit, used for extracting features from standardized breast cancer historical data;

[0088] Based on the random forest algorithm of feature importance evaluation, the extracted features are evaluated for their importance, the influence of the extracted features on the classification of benign and malignant breast cancer is evaluated, the features that can best distinguish benign and malignant breast cancer lesions are selected, and the breast cancer feature data based on artificial intelligence is determined.

[0089] Among them, an artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is constructed through the model training module, and the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is tested and optimized to determine the optimal intelligent analysis model for benign and malignant breast cancer.

[0090] In this embodiment, as a preferred technical solution of the present invention, the model training module includes:

[0091] a data partitioning unit, configured to partition the artificial intelligence-based breast cancer feature data into a training set and a test set;

[0092] A model building unit, used to build an AI-based intelligent analysis model for benign and malignant breast cancer;

[0093] Based on deep learning technology, the training set and the benign and malignant breast cancer labels are input into the deep learning model. Through continuous training iterations, the deep learning model can autonomously learn the benign and malignant breast cancer classification and determine the AI-based intelligent analysis model for benign and malignant breast cancer.

[0094] The test set is input into the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is tested based on the test set to determine whether the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer can achieve the intelligent analysis and classification effect of benign and malignant breast cancer.

[0095] In this embodiment, as a preferred technical solution of the present invention, determining whether the artificial intelligence-based intelligent analysis model for breast cancer benign and malignant can achieve the intelligent analysis and classification effect of breast cancer benign and malignant includes:

[0096] Obtain the test set to perform a performance test on the AI-based intelligent analysis model for benign and malignant breast cancer. Based on the precision and recall of the AI-based intelligent analysis model for benign and malignant breast cancer, determine whether the AI-based intelligent analysis model for benign and malignant breast cancer can achieve the desired classification effect.

[0097] When the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer cannot achieve the intelligent analysis and classification effect of benign and malignant breast cancer, the parameters and structure of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer are continuously adjusted, the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is continuously iteratively optimized, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is verified based on the cross-validation method to achieve the best benign and malignant breast cancer classification effect and determine the optimal intelligent analysis model for benign and malignant breast cancer.

[0098] Among them, the intelligent analysis module is used to perform intelligent analysis on the benign and malignant conditions of the patient's breast cancer to determine the intelligent analysis results of the patient's benign and malignant conditions.

[0099] In this embodiment, as a preferred technical solution of the present invention, the intelligent analysis module includes:

[0100] A model deployment unit, used to deploy the optimal breast cancer benign and malignant intelligent analysis model in an actual breast cancer benign and malignant intelligent analysis environment;

[0101] Intelligent analysis unit, used to intelligently analyze the benign and malignant status of patients' breast cancer;

[0102] The patient's real-time breast cancer data is input into the optimal intelligent analysis model for benign and malignant breast cancer. Based on the optimal intelligent analysis model for benign and malignant breast cancer, the patient's real-time breast cancer data is intelligently analyzed, and the patient's breast cancer is classified as benign and malignant to determine the intelligent analysis result of the patient's breast cancer, wherein the intelligent analysis result of the patient's breast cancer is benign or malignant.

[0103] Among them, the intelligent analysis results of the patient's breast cancer are output through the output management module, and the intelligent analysis report of the patient's breast cancer is displayed in a visual form, and the patient's breast cancer is intelligently treated and managed.

[0104] In this embodiment, as a preferred technical solution of the present invention, the output management module includes:

[0105] The output display unit is used to output the intelligent analysis results of the patient's breast cancer benign and malignant nature, analyze the patient's real-time breast cancer data and the intelligent analysis results of the patient's breast cancer benign and malignant nature, generate the patient's breast cancer benign and malignant intelligent analysis report, and display the patient's breast cancer benign and malignant intelligent analysis report in a visual form, so that doctors and patients can more intuitively understand the benign and malignant nature of the patient's breast cancer;

[0106] The analysis and management unit is used to intelligently manage the benign and malignant conditions of the patient's breast cancer. According to the intelligent analysis results of the patient's breast cancer, a breast cancer treatment plan is formulated for the patient, and the patient's breast cancer is intelligently managed based on the breast cancer treatment plan.

[0107] In one embodiment, personal medical history data, medical imaging data, pathological tissue data, and genomic data are preprocessed to obtain preprocessed data;

[0108] Extracting tissue pathology feature vectors based on pre-processed medical imaging data and pathological tissue data, and extracting gene mutation molecular feature vectors based on pre-processed genomic data;

[0109] Fusing the tissue pathology feature vector with the gene mutation molecular feature vector to obtain the patient's fused multimodal features;

[0110] Determine the patient's gene differential expression parameters based on the fusion of multimodal features, and determine the cell transcription profile expression data based on the gene differential expression parameters;

[0111] Determine the patient's candidate mutation genes based on cell transcriptional profile expression data, and determine the patient's cancer signature based on the candidate mutation genes;

[0112] Determine the patient's mRNA and miRNA data under cancerous lesions based on the cancer label, and obtain the patient's pathological image features based on the pre-processed medical imaging data;

[0113] Reconstruct the pathological image features with the mRNA data and miRNA data to obtain the pathological image feature matrix, mRNA expression matrix and miRNA expression matrix;

[0114] Construct a correlation structure diagram based on the pathological image feature matrix, mRNA expression matrix, and miRNA expression matrix;

[0115] According to the association structure diagram, the pre-processed personal medical history data, medical imaging data, pathological tissue data and genomic data are labeled and packaged to generate an integrated file;

[0116] Generate AI-based historical breast cancer data from integrated files.

[0117] The beneficial effects of the above technical solution are: by constructing an association structure diagram of the patient's cancer data and then annotating and packaging the personal medical history data, medical imaging data, pathological tissue data and genomic data, medical personnel can quickly characterize the patient's cancerous lesions based on the annotation results, thereby improving the work efficiency and experience of medical personnel. At the same time, it also effectively interprets the patient's in-depth symptoms, provides medical personnel with effective reference samples, and improves practicality.

[0118] In one embodiment, after obtaining the medical image data, the method further includes:

[0119] Obtain the pixel grayscale value of each pixel in the medical image data and determine the image clutter degree of the medical image based on the pixel grayscale value:

[0120]

[0121] Among them, Q represents the image clutter degree of the medical image, M represents the number of regions into which the medical image is divided into equal-area regions, and i represents the i-th divided region. It is expressed as the average pixel gray value of the i-th divided area, and ln is expressed as the natural logarithm;

[0122] Determine the uniformity of pixel grayscale distribution of the medical image according to the image clutter degree of the medical image, and determine whether contrast enhancement of the medical image is required according to the uniformity of pixel grayscale distribution;

[0123] If so, the contrast enhancement of medical images is achieved through the following formula:

[0124]

[0125] in, Represented as the grayscale value of the output medical image, Expressed as a dynamic coefficient, Represented as the grayscale value of the input medical image, Expressed as the average value of grayscale in the neighborhood of point (i, j);

[0126] The enhanced medical images are used as medical imaging reference data.

[0127] The beneficial effects of the above technical solution are: by contrast enhancement of medical images, the image quality and image display effect can be guaranteed, which lays the foundation for medical personnel to review and refer to, and further improves the practicality.

[0128] In summary, by collecting the patient's personal medical history data, medical imaging data, pathological tissue data and genomic data, the breast cancer historical data is determined, and by processing the breast cancer historical data, the breast cancer characteristic data is determined. Based on the optimal breast cancer benign and malignant intelligent analysis model, the patient's breast cancer real-time data is intelligently analyzed, and the patient's breast cancer benign and malignant conditions are classified. The patient's breast cancer benign and malignant intelligent analysis results are determined, and the patient's breast cancer benign and malignant intelligent analysis results are output. The patient's breast cancer benign and malignant intelligent analysis report is displayed in a visual form, so that doctors and patients can more intuitively understand the benign and malignant nature of the patient's breast cancer, and can perform intelligent analysis and effectively identify and classify the benign and malignant nature of breast cancer, which can improve the effect of the benign and malignant intelligent analysis of breast cancer.

[0129] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0130] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence-based intelligent analysis system for benign and malignant breast cancer, characterized by: include: The data collection module is used to collect the patient's personal medical history data, medical imaging data, pathological tissue data and genomic data to determine the AI-based breast cancer historical data; a data processing module for processing AI-based breast cancer historical data and determining AI-based breast cancer characteristic data; The model training module is used to build an AI-based intelligent analysis model for breast cancer benign and malignant diseases, and to test and optimize the AI-based intelligent analysis model for breast cancer benign and malignant diseases to determine the optimal intelligent analysis model for breast cancer benign and malignant diseases; Intelligent analysis module, used to perform intelligent analysis on the benign and malignant status of the patient's breast cancer and determine the intelligent analysis results of the patient's breast cancer; The output management module is used to output the intelligent analysis results of the patient's breast cancer benign and malignant status, and to display the intelligent analysis report of the patient's breast cancer benign and malignant status in a visual form, and to perform intelligent treatment management for the patient's breast cancer; The data collection module includes: The personal medical history collection unit is used to collect the patient's age, gender, family medical history, past medical history, menstrual status and reproductive history to obtain personal medical history data; A medical image collection unit, used to collect mammograms, ultrasound images, and magnetic resonance imaging of patients to obtain medical image data; Pathological tissue collection unit, used to collect pathological sections and immunohistochemistry of patients and obtain pathological tissue data; A genomics collection unit is used to collect the patient's gene expression profile, gene mutation and amplified genetic information to obtain genomics data; Among them, AI-based breast cancer historical data is determined based on personal medical history data, medical imaging data, pathological tissue data, and genomic data; After obtaining medical imaging data, it also includes: Obtain the pixel grayscale value of each pixel in the medical image data and determine the image clutter degree of the medical image based on the pixel grayscale value: Among them, Q represents the image clutter degree of the medical image, M represents the number of regions into which the medical image is divided into equal-area regions, and i represents the i-th divided region. It is expressed as the average pixel gray value of the i-th divided area, and ln is expressed as the natural logarithm; Determine the uniformity of pixel grayscale distribution of the medical image according to the image clutter degree of the medical image, and determine whether contrast enhancement of the medical image is required according to the uniformity of pixel grayscale distribution; If so, the contrast enhancement of medical images is achieved through the following formula: in, Represented as the grayscale value of the output medical image, Expressed as a dynamic coefficient, Represented as the grayscale value of the input medical image, Expressed as the average value of grayscale in the neighborhood of point (i, j); The enhanced medical images are used as medical imaging reference data.

2. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 1, characterized in that: After collecting the patient's personal medical history data, medical imaging data, pathological tissue data, and genomic data, and determining the AI-based breast cancer history data, it also includes: Preprocess personal medical history data, medical imaging data, pathological tissue data, and genomics data to obtain preprocessed data; Extracting tissue pathology feature vectors based on pre-processed medical imaging data and pathological tissue data, and extracting gene mutation molecular feature vectors based on pre-processed genomic data; Fusing the tissue pathology feature vector with the gene mutation molecular feature vector to obtain the patient's fused multimodal features; Determine the patient's gene differential expression parameters based on the fusion of multimodal features, and determine the cell transcription profile expression data based on the gene differential expression parameters; Determine the patient's candidate mutation genes based on cell transcriptional profile expression data, and determine the patient's cancer signature based on the candidate mutation genes; Determine the patient's mRNA and miRNA data under cancerous lesions based on the cancer label, and obtain the patient's pathological image features based on the pre-processed medical imaging data; Reconstruct the pathological image features with the mRNA data and miRNA data to obtain the pathological image feature matrix, mRNA expression matrix and miRNA expression matrix; Construct a correlation structure diagram based on the pathological image feature matrix, mRNA expression matrix, and miRNA expression matrix; According to the association structure diagram, the pre-processed personal medical history data, medical imaging data, pathological tissue data and genomic data are labeled and packaged to generate an integrated file; Generate AI-based historical breast cancer data from integrated files.

3. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 2, characterized in that: The data processing module includes: A data cleaning unit, used to clean historical breast cancer data based on artificial intelligence; Based on data cleaning tools, duplicate values, missing values, and outliers in AI-based breast cancer historical data are identified and processed; When duplicate values ​​exist in AI-based breast cancer historical data, the duplicate values ​​are removed; When missing values ​​exist in AI-based breast cancer historical data, samples containing missing values ​​are deleted or the median is used to fill the missing values; When outliers exist in AI-based breast cancer historical data, samples containing outliers are deleted or the average value is used to replace the outliers.

4. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 3, characterized in that: The data processing module further includes: A data conversion unit, used to convert historical breast cancer data based on artificial intelligence; Perform format and type conversion on AI-based breast cancer historical data, remove dimensional differences among AI-based breast cancer historical data, and determine standardized breast cancer historical data; A feature extraction unit, used for extracting features from standardized breast cancer historical data; Based on the random forest algorithm of feature importance evaluation, the extracted features are evaluated for their importance, the influence of the extracted features on the classification of benign and malignant breast cancer is evaluated, the features that can best distinguish benign and malignant breast cancer lesions are selected, and the breast cancer feature data based on artificial intelligence is determined.

5. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 4, characterized in that: The model training module includes: a data partitioning unit, configured to partition the artificial intelligence-based breast cancer feature data into a training set and a test set; A model building unit, used to build an AI-based intelligent analysis model for benign and malignant breast cancer; Based on deep learning technology, the training set and the benign and malignant breast cancer labels are input into the deep learning model. Through continuous training iterations, the deep learning model can autonomously learn the benign and malignant breast cancer classification and determine the AI-based intelligent analysis model for benign and malignant breast cancer. The test set is input into the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is tested based on the test set to determine whether the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer can achieve the intelligent analysis and classification effect of benign and malignant breast cancer.

6. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 5, characterized in that: Judging whether the AI-based intelligent analysis model for breast cancer benign and malignant classification can achieve the desired effect includes: Obtain the test set to perform a performance test on the AI-based intelligent analysis model for benign and malignant breast cancer. Based on the precision and recall of the AI-based intelligent analysis model for benign and malignant breast cancer, determine whether the AI-based intelligent analysis model for benign and malignant breast cancer can achieve the desired classification effect. When the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer cannot achieve the intelligent analysis and classification effect of benign and malignant breast cancer, the parameters and structure of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer are continuously adjusted, the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is continuously iteratively optimized, and the performance of the artificial intelligence-based intelligent analysis model for benign and malignant breast cancer is verified based on the cross-validation method to achieve the best benign and malignant breast cancer classification effect and determine the optimal intelligent analysis model for benign and malignant breast cancer.

7. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 6, characterized in that: The intelligent analysis module includes: A model deployment unit, used to deploy the optimal breast cancer benign and malignant intelligent analysis model in an actual breast cancer benign and malignant intelligent analysis environment; Intelligent analysis unit, used to intelligently analyze the benign and malignant status of patients' breast cancer; The patient's real-time breast cancer data is input into the optimal intelligent analysis model for benign and malignant breast cancer. Based on the optimal intelligent analysis model for benign and malignant breast cancer, the patient's real-time breast cancer data is intelligently analyzed, and the patient's breast cancer is classified as benign and malignant to determine the intelligent analysis result of the patient's breast cancer, wherein the intelligent analysis result of the patient's breast cancer is benign or malignant.

8. The artificial intelligence-based intelligent analysis system for benign and malignant breast cancer according to claim 7, characterized in that: The output management module includes: The output display unit is used to output the intelligent analysis results of the patient's breast cancer benign and malignant nature, analyze the patient's real-time breast cancer data and the intelligent analysis results of the patient's breast cancer benign and malignant nature, generate the patient's breast cancer benign and malignant intelligent analysis report, and display the patient's breast cancer benign and malignant intelligent analysis report in a visual form, so that doctors and patients can more intuitively understand the benign and malignant nature of the patient's breast cancer; The analysis and management unit is used to intelligently manage the benign and malignant conditions of the patient's breast cancer. According to the intelligent analysis results of the patient's breast cancer, a breast cancer treatment plan is formulated for the patient, and the patient's breast cancer is intelligently managed based on the breast cancer treatment plan.

Images