Intelligent radiation dose estimation system

Abstract

The invention relates to the technical field of radiation medicine, in particular to an intelligent radiation dose estimation system which comprises a data acquisition module, a data preprocessing module, a chromosome distortion analysis module, a radiation dose estimation module and a result output module. The data preprocessing module is used for preprocessing the collected multivariate heterogeneous data, the chromosome distortion analysis module is used for analyzing the preprocessed data, the radiation dose estimation module is used for intelligently estimating the radiation dose, and the result output module is used for visually presenting the radiation dose estimation result to a user. By adopting the technical scheme, the radiation exposure condition and chromosome distortion characteristics of a patient can be more comprehensively known, so that the accuracy of radiation dose estimation is improved, modular design and an automatic processing flow are adopted, data acquisition, preprocessing, analysis and result output can be quickly completed, and the analysis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of radiation medicine, and particularly to an intelligent radiation dose estimation system. Background Art

[0002] In many fields involving radioactivity such as nuclear energy, medical treatment, and industrial flaw detection, radiation workers face varying degrees of occupational exposure risks. Accurately estimating the radiation dose is crucial for assessing the health risks of radiation workers, preventing radiation diseases, and formulating emergency response plans.

[0003] However, the traditional radiation dose estimation and analysis process is cumbersome and takes a long time to obtain results, which may lead to delays in the best treatment opportunities. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent radiation dose estimation system, aiming to solve the technical problem that the traditional radiation dose estimation and analysis process is cumbersome and takes a long time to obtain results, which may lead to delays in the best treatment opportunities.

[0005] To achieve the above purpose, the present invention provides an intelligent radiation dose estimation system, including a data acquisition module, a data preprocessing module, a chromosome aberration analysis module, a radiation dose estimation module, and a result output module. The data acquisition module is responsible for collecting heterogeneous data related to radiation exposure and chromosome aberration. The data preprocessing module is used to preprocess the collected heterogeneous data to improve the quality and usability of the data. The chromosome aberration analysis module uses artificial intelligence technology to analyze the preprocessed data to identify the types and degrees of chromosome aberrations. The radiation dose estimation module intelligently estimates the radiation dose based on the results of the chromosome aberration analysis. The result output module is used to present the results of the radiation dose estimation to the user in an intuitive manner and provide relevant diagnostic suggestions and emergency response plans.

[0006] Among them, the data acquisition module includes a text data acquisition sub-module, an image data acquisition sub-module, and a genomic data acquisition sub-module;

[0007] The text data acquisition sub-module obtains text data such as the patient's personal information, occupational history, and radiation exposure history by docking with the information system of medical institutions. At the same time, relevant medical literature and research reports are collected to provide reference for the subsequent chromosome aberration analysis module;

[0008] The image data acquisition sub-module uses a microscope image acquisition device to obtain the patient's chromosome image data;

[0009] The genomic data acquisition sub-module uses gene sequencing technology to obtain the patient's genomic data.

[0010] Among them, the data preprocessing module includes a text data preprocessing sub-module, an image data preprocessing sub-module, and a genomic data preprocessing sub-module;

[0011] The text data preprocessing sub-module is used to clean, segment, and perform part-of-speech tagging on text data, remove noise information, extract key features, and at the same time, establish a text feature vector to convert the text data into a numerical form that can be processed by a computer;

[0012] The image data preprocessing sub-module is used to denoise, enhance, and segment chromosome images, improve the clarity and contrast of the images, and use image recognition technology to locate and identify chromosomes and extract the morphological features of chromosomes;

[0013] The genomic data preprocessing sub-module is used to normalize and fill in missing values in genomic data to ensure the quality of genomic data, and at the same time, perform gene annotation and function prediction to mine information related to radiation exposure and chromosome aberration in genomic data.

[0014] Among them, the chromosome aberration analysis module includes a machine learning analysis sub-module and a deep learning analysis sub-module. The machine learning analysis sub-module uses machine learning algorithms to classify and predict text data and image data, and by analyzing the features of chromosome images and relevant information in the text data, it determines whether there are chromosome aberrations and the types of aberrations;

[0015] The deep learning analysis sub-module uses a convolutional neural network deep learning model to perform deep feature extraction and analysis on chromosome images, and at the same time, combines genomic data to further analyze the molecular mechanism of chromosome aberration.

[0016] Among them, the radiation dose estimation module includes a dose-aberration relationship model sub-module and a dose estimation sub-module. The dose-aberration relationship model sub-module is used to establish a relationship model between radiation dose and the type and degree of chromosome aberration. This model is based on a large amount of experimental data and clinical research results and can accurately describe the change law of chromosome aberration under different radiation doses;

[0017] The dose estimation sub-module uses a genetic algorithm to estimate the radiation dose of the patient based on the results of chromosome aberration analysis and the dose-aberration relationship model.

[0018] Among them, the specific steps of the genetic algorithm in the dose estimation sub-module are as follows:

[0019] Initialize the population: Randomly generate a group of initial radiation dose values as the population, and each individual represents a possible dose solution;

[0020] Fitness evaluation: According to the analysis results of the chromosome aberration analysis module and the dose-aberration relationship model, calculate the fitness value of each individual, that is, the matching degree between the model prediction result and the actual aberration analysis result at this dose value;

[0021] Selection operation: Select excellent individuals according to the fitness value and let them enter the next generation to simulate the process of natural selection;

[0022] Crossover operation: Perform crossover operations on the selected individuals to generate new individuals and increase the diversity of the population;

[0023] Mutation operation: Perform mutation operations on the new individuals to introduce randomness and avoid falling into local optimal solutions;

[0024] Iterative evolution: Repeat the above steps until the termination condition is met.

[0025] Among them, the result output module includes a result visualization sub-module, a diagnostic advice sub-module, and an emergency response plan sub-module;

[0026] The result visualization sub-module is used to visually display the results of radiation dose estimation to facilitate users to intuitively understand the patient's radiation exposure situation;

[0027] The diagnostic advice sub-module provides personalized diagnostic advice based on the results of radiation dose estimation and the patient's clinical information;

[0028] The emergency response plan sub-module formulates emergency response plans for different radiation doses.

[0029] Among them, the intelligent radiation dose estimation system also includes a risk assessment module. The risk assessment module is used to set a reasonable warning threshold according to the patient's specific situation and the risk level of radiation diseases. When the patient's risk of radiation diseases exceeds the preset threshold, an early warning prompt is automatically issued.

[0030] Among them, the risk assessment module includes a risk factor analysis sub-module, a disease risk prediction sub-module, and an early warning prompt sub-module;

[0031] The risk factor analysis sub-module is used to comprehensively consider the patient's personal information, occupational history, radiation exposure history, and chromosome aberration analysis results to identify key factors related to the risk of radiation disease occurrence;

[0032] The disease risk prediction sub-module, based on the results of risk factor analysis, uses machine learning or statistical models to predict the probability of the patient developing radiation diseases in the future;

[0033] The early warning prompt sub-module is used to automatically issue an early warning prompt when the patient's risk of radiation diseases exceeds the preset threshold.

[0034] An intelligent radiation dose estimation system of the present invention includes a data acquisition module, a data preprocessing module, a chromosome aberration analysis module, a radiation dose estimation module, and a result output module. The data acquisition module is used to collect heterogeneous multi-source data related to radiation exposure and chromosome aberration. The data preprocessing module is used to preprocess the collected heterogeneous multi-source data to improve the quality and usability of the data. The chromosome aberration analysis module uses artificial intelligence technology to analyze the preprocessed data to identify the types and degrees of chromosome aberration. The radiation dose estimation module intelligently estimates the radiation dose according to the results of the chromosome aberration analysis. The result output module presents the results of the radiation dose estimation to the user in an intuitive manner and provides relevant diagnostic suggestions and emergency treatment plans. By integrating heterogeneous multi-source data such as text, images, and genomes and using artificial intelligence technology for analysis, the technical solution of the present invention can comprehensively understand the patient's radiation exposure situation and chromosome aberration characteristics, thereby improving the accuracy of radiation dose estimation. Moreover, with a modular design and an automated processing flow, it can quickly complete data acquisition, preprocessing, analysis, and result output, greatly shortening the time for radiation dose estimation and improving the analysis efficiency. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a schematic block diagram of the intelligent radiation dose estimation system according to the first embodiment of the present invention.

[0037] Figure 2 It is a schematic block diagram of the intelligent radiation dose estimation system according to the second embodiment of the present invention.

[0038] 101 - Data acquisition module, 102 - Data pre - processing module, 103 - Chromosome aberration analysis module, 104 - Radiation dose estimation module, 105 - Result output module, 106 - Text data acquisition sub - module, 107 - Image data acquisition sub - module, 108 - Genome data acquisition sub - module, 109 - Text data pre - processing sub - module, 110 - Image data pre - processing sub - module, 111 - Genome data pre - processing sub - module, 112 - Machine learning analysis sub - module, 113 - Deep learning analysis sub - module, 114 - Dose - aberration relationship model sub - module, 115 - Dose estimation sub - module, 116 - Result visualization sub - module, 117 - Diagnostic advice sub - module, 118 - Emergency response plan sub - module. Detailed implementation manners

[0039] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation to the present invention.

[0040] The first embodiment:

[0041] Please refer to Figure 1 , in which Figure 1 is the principle block diagram of the intelligent radiation dose estimation system of the first embodiment.

[0042] The present invention provides an intelligent radiation dose estimation system, including a data acquisition module 101, a data pre - processing module 102, a chromosome aberration analysis module 103, a radiation dose estimation module 104, and a result output module 105. The data acquisition module 101 includes a text data acquisition sub - module 106, an image data acquisition sub - module 107, and a genome data acquisition sub - module 108. The data pre - processing module 102 includes a text data pre - processing sub - module 109, an image data pre - processing sub - module 110, and a genome data pre - processing sub - module 111. The chromosome aberration analysis module 103 includes a machine learning analysis sub - module 112 and a deep learning analysis sub - module 113. The radiation dose estimation module 104 includes a dose - aberration relationship model sub - module 114 and a dose estimation sub - module 115. The result output module 105 includes a result visualization sub - module 116, a diagnostic advice sub - module 117, and an emergency response plan sub - module 118. By the foregoing solution, the problem that the traditional radiation dose estimation and analysis process is cumbersome and takes a long time to obtain results, which may lead to delays in the best treatment opportunity, is solved. It can be understood that the foregoing solution can be used in the architecture of the intelligent radiation dose estimation system.

[0043] For this specific implementation, the data acquisition module 101 is responsible for collecting multivariate heterogeneous data related to radiation exposure and chromosome aberration, the data preprocessing module 102 is used to preprocess the collected multivariate heterogeneous data to improve the quality and availability of the data, the chromosome aberration analysis module 103 uses artificial intelligence technology to analyze the preprocessed data to identify the type and degree of chromosome aberration, the radiation dose estimation module 104 intelligently estimates the radiation dose according to the results of the chromosome aberration analysis, and the result output module 105 is used to present the results of the radiation dose estimation to the user in an intuitive manner and provide relevant diagnostic suggestions and emergency treatment plans. The technical solution integrates multivariate heterogeneous data such as text, images and genomes, and uses artificial intelligence technology for analysis, so as to more comprehensively understand the patient's radiation exposure and chromosome aberration characteristics, thereby improving the accuracy of radiation dose estimation, and adopts modular design and automated processing procedures to quickly complete data acquisition, preprocessing, analysis and result output, greatly shortening the time of radiation dose estimation and improving analysis efficiency.

[0044] The text data collection submodule 106 obtains text data such as the patient's personal information, occupational history, radiation exposure history, etc. by connecting with the information system of the medical institution, and collects relevant medical literature and research reports to provide reference for the subsequent chromosome aberration analysis module 103;

[0045] The image data acquisition submodule 107 uses a microscope image acquisition device to acquire the patient's chromosome image data;

[0046] The genome data collection submodule 108 uses gene sequencing technology to obtain the genome data of the patient.

[0047] Secondly, the text data preprocessing submodule 109 is used to clean, segment and tag the text data, remove noise information, extract key features, and at the same time, establish a text feature vector to convert the text data into a numerical form that can be processed by a computer;

[0048] The image data preprocessing submodule 110 is used to perform denoising, enhancement and segmentation processing on the chromosome image to improve the clarity and contrast of the image, and use image recognition technology to locate and identify the chromosome and extract the morphological characteristics of the chromosome;

[0049] The genome data preprocessing submodule 111 is used to normalize the genome data and fill in missing values to ensure the quality of the genome data. At the same time, it performs gene annotation and function prediction to mine information related to radiation exposure and chromosome aberration in the genome data.

[0050] Meanwhile, the machine learning analysis sub-module 112 uses machine learning algorithms to classify and predict text data and image data, and determines whether there are chromosomal aberrations and the types of aberrations by analyzing the characteristics of chromosomal images and relevant information in the text data;

[0051] The deep learning analysis sub-module 113 uses a convolutional neural network deep learning model to extract and analyze deep features of chromosomal images. Meanwhile, in combination with genomic data, it further analyzes the molecular mechanism of chromosomal aberrations.

[0052] The dose-aberrations relationship model sub-module 114 is used to establish a relationship model between radiation dose and the type and degree of chromosomal aberrations. Based on a large amount of experimental data and clinical research results, this model can accurately describe the variation law of chromosomal aberrations under different radiation doses;

[0053] The dose estimation sub-module 115 uses a genetic algorithm to estimate the radiation dose of the patient based on the results of chromosomal aberration analysis and the dose-aberrations relationship model.

[0054] Among them, the specific steps of the genetic algorithm in the dose estimation sub-module 115 are as follows:

[0055] Initializing the population: Randomly generate a group of initial radiation dose values as the population, and each individual represents a possible dose solution;

[0056] Fitness evaluation: According to the analysis results of the chromosomal aberration analysis module 103 and the dose-aberrations relationship model, calculate the fitness value of each individual, that is, the matching degree between the model prediction result and the actual aberration analysis result at this dose value;

[0057] Selection operation: Select excellent individuals according to the fitness value and let them enter the next generation, simulating the process of natural selection;

[0058] Crossover operation: Perform a crossover operation on the selected individuals to generate new individuals and increase the diversity of the population;

[0059] Mutation operation: Perform a mutation operation on the new individuals to introduce randomness and avoid falling into a local optimal solution;

[0060] Iterative evolution: Repeat the above steps until the termination condition is met.

[0061] In addition, the result visualization sub-module 116 is used to visually display the results of radiation dose estimation, facilitating users to intuitively understand the patient's radiation exposure situation;

[0062] The diagnostic advice sub-module 117 provides personalized diagnostic advice based on the results of radiation dose estimation and the patient's clinical information.

[0063] The emergency response plan sub-module 118 formulates emergency response plans for different radiation doses.

[0064] When using an intelligent radiation dose estimation system according to this embodiment, the data acquisition module 101 is used to collect heterogeneous data related to radiation exposure and chromosome aberration. The data preprocessing module 102 is used to preprocess the collected heterogeneous data to improve the quality and usability of the data. The chromosome aberration analysis module 103 uses artificial intelligence technology to analyze the preprocessed data to identify the types and degrees of chromosome aberration. The radiation dose estimation module 104 intelligently estimates the radiation dose according to the results of chromosome aberration analysis. The result output module 105 presents the results of radiation dose estimation to the user in an intuitive manner and provides relevant diagnostic suggestions and emergency response plans. By integrating heterogeneous data such as text, images, and genomes and using artificial intelligence technology for analysis, this technical solution can comprehensively understand the patient's radiation exposure situation and chromosome aberration characteristics, thereby improving the accuracy of radiation dose estimation. Moreover, with a modular design and an automated processing flow, it can quickly complete data acquisition, preprocessing, analysis, and result output, greatly shortening the time for radiation dose estimation and improving the analysis efficiency.

[0065] Second Embodiment:

[0066] Based on the first embodiment, please refer to Figure 2 , Figure 2 which is the principle block diagram of the intelligent radiation dose estimation system of the second embodiment.

[0067] The intelligent radiation dose estimation system provided by the present invention further includes a risk assessment module 201. The risk assessment module 201 includes a risk factor analysis sub-module 202, a disease risk prediction sub-module 203, and a warning prompt sub-module 204.

[0068] For this specific embodiment, the risk assessment module 201 is used to set a reasonable warning threshold according to the specific situation of the patient and the risk level of radioactive diseases. When the risk of radioactive diseases of the patient exceeds the preset threshold, a warning prompt is automatically issued.

[0069] Among them, the risk factor analysis sub-module 202 is used to comprehensively consider the patient's personal information, occupational history, radiation exposure history, and the results of chromosome aberration analysis to identify key factors related to the risk of radioactive diseases;

[0070] The disease risk prediction sub-module 203 predicts the probability of the patient suffering from radioactive diseases in the future based on the results of risk factor analysis by using machine learning or statistical models;

[0071] The warning prompt sub-module 204 is used to automatically issue a warning prompt by the system when the risk of the patient's radioactive disease exceeds a preset threshold, and visually output the warning prompt to the user through the result output module 105.

[0072] When using an intelligent radiation dose estimation system according to this embodiment, through the setting of the risk assessment module 201, a reasonable warning threshold can be set according to the specific situation of the patient and the risk level of the radioactive disease. When the risk of the patient's radioactive disease exceeds the preset threshold, a warning prompt is automatically issued, and the warning prompt is visually output to the user through the result output module 105.

[0073] The above-disclosed is only a preferred embodiment of the present invention. Of course, the scope of the rights of the present invention cannot be limited by this. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. An intelligent radiation dose estimation system, characterized in that: The system comprises a data acquisition module, a data preprocessing module, a chromosome aberration analysis module, a radiation dose estimation module and a result output module. The data acquisition module is responsible for collecting multivariate heterogeneous data related to radiation exposure and chromosome aberration. The data preprocessing module is used to preprocess the collected multivariate heterogeneous data to improve the quality and availability of the data. The chromosome aberration analysis module uses artificial intelligence technology to analyze the preprocessed data and identify the type and degree of chromosome aberration. The radiation dose estimation module intelligently estimates the radiation dose according to the result of chromosome aberration analysis. The result output module is used to present the result of radiation dose estimation to the user in an intuitive manner and provide relevant diagnostic suggestions and emergency treatment plans.

2. The intelligent radiation dose estimation system according to claim 1, characterized in that: The data acquisition module includes a text data acquisition submodule, an image data acquisition submodule and a genome data acquisition submodule; The text data collection submodule obtains the patient's personal information, occupational history, radiation exposure history and other text data by connecting with the information system of the medical institution. At the same time, it collects relevant medical literature and research reports to provide reference for the subsequent chromosome aberration analysis module; The image data acquisition submodule uses a microscope image acquisition device to acquire chromosome image data of the patient; The genome data acquisition submodule uses gene sequencing technology to obtain the patient's genome data.

3. The intelligent radiation dose estimation system according to claim 2, characterized in that: The data preprocessing module includes a text data preprocessing submodule, an image data preprocessing submodule and a genome data preprocessing submodule; The text data preprocessing submodule is used to clean, segment and tag text data, remove noise information, extract key features, and at the same time, establish text feature vectors to convert text data into a numerical form that can be processed by a computer; The image data preprocessing submodule is used to perform denoising, enhancement and segmentation processing on the chromosome image to improve the clarity and contrast of the image, and use image recognition technology to locate and identify the chromosome and extract the morphological characteristics of the chromosome; The genomic data preprocessing submodule is used to normalize the genomic data and fill in missing values to ensure the quality of the genomic data. At the same time, it performs gene annotation and function prediction and mines the information related to radiation exposure and chromosome aberration in the genomic data.

4. The intelligent radiation dose estimation system according to claim 3, characterized in that: The chromosome aberration analysis module includes a machine learning analysis submodule and a deep learning analysis submodule. The machine learning analysis submodule uses a machine learning algorithm to classify and predict text data and image data, and determines whether the chromosome is distorted and the type of distortion by analyzing the features of the chromosome image and the relevant information in the text data. The deep learning analysis sub-module uses a convolutional neural network deep learning model to perform deep feature extraction and analysis on chromosome images. At the same time, in combination with genomic data, it further analyzes the molecular mechanism of chromosome aberration.

5. The intelligent radiation dose estimation system according to claim 4, wherein the radiation dose estimation module includes a dose-aberration relationship model sub-module and a dose estimation sub-module. The dose-aberration relationship model sub-module is used to establish a relationship model between radiation dose and the type and degree of chromosome aberration. Based on a large amount of experimental data and clinical research results, this model can accurately describe the variation law of chromosome aberration under different radiation doses; the dose estimation sub-module uses a genetic algorithm to estimate the radiation dose of the patient based on the results of chromosome aberration analysis and the dose-aberration relationship model.

6. The intelligent radiation dose estimation system according to claim 5, wherein the specific steps of the genetic algorithm in the dose estimation sub-module are as follows: Initializing the population: Randomly generate a group of initial radiation dose values as the population, and each individual represents a possible dose solution; Fitness evaluation: According to the analysis results of the chromosome aberration analysis module and the dose-aberration relationship model, calculate the fitness value of each individual, that is, the matching degree between the model prediction result and the actual aberration analysis result at this dose value; Selection operation: Select excellent individuals according to the fitness value and let them enter the next generation, simulating the process of natural selection; Crossover operation: Perform a crossover operation on the selected individuals to generate new individuals and increase the diversity of the population; Mutation operation: Perform a mutation operation on the new individuals to introduce randomness and avoid falling into a local optimal solution; Iterative evolution: Repeat the above steps until the termination condition is met.

7. The intelligent radiation dose estimation system according to claim 6, wherein the result output module includes a result visualization sub-module, a diagnostic advice sub-module, and an emergency response plan sub-module; the result visualization sub-module is used to visually display the results of radiation dose estimation, facilitating users to intuitively understand the patient's radiation exposure situation; the diagnostic advice sub-module provides personalized diagnostic advice based on the results of radiation dose estimation and the patient's clinical information; the emergency response plan sub-module formulates emergency response plans for different radiation doses.

8. The intelligent radiation dose estimation system according to claim 1, wherein the intelligent radiation dose estimation system further includes a risk assessment module. The risk assessment module is used to set a reasonable warning threshold according to the specific situation of the patient and the risk level of radioactive diseases. When the risk of radioactive diseases of the patient exceeds the preset threshold, an early warning prompt is automatically issued.

9. The intelligent radiation dose estimation system according to claim 8, wherein the risk assessment module includes a risk factor analysis sub-module, a disease risk prediction sub-module, and an early warning prompt sub-module; the risk factor analysis sub-module is used to comprehensively consider the patient's personal information, occupational history, radiation exposure history, and the results of chromosome aberration analysis to identify key factors related to the risk of radioactive diseases. The disease risk prediction sub-module predicts the probability of the patient suffering from radiation diseases in the future based on the results of risk factor analysis, using machine learning or statistical models; The warning prompt sub-module is used to automatically issue a warning prompt by the system when the radiation disease risk of the patient exceeds a preset threshold.

Images