Glioma diagnosis system based on resting-state brain function contralateral positioning

Abstract

The present application relates to the technical field of resting state brain function diagnosis, in particular to a brain glioma diagnosis system based on resting state brain function contralateral positioning, comprising: a collection module for collecting brain magnetic resonance image data of a user; a conversion module for calling the brain magnetic resonance image data of the user collected in the collection module and converting the brain magnetic resonance image data of the user into waveform images; a segmentation module for receiving the waveform images obtained by converting the brain magnetic resonance image data of the user in the conversion module and segmenting the waveform images; the present application estimates the risk of brain glioma of a user through analysis of brain magnetic resonance image data of the user, greatly replacing manual work, and the diagnosis accuracy is no longer affected by the accumulation of professional knowledge and experience, and the risk of brain glioma of a patient can be estimated more accurately.

Description

Technical Field

[0001] This invention relates to the field of resting-state brain function diagnostic technology, and more specifically to a glioma diagnostic system based on contralateral localization of resting-state brain function. Background Technology

[0002] Gliomas are the most common primary intracranial tumors, originating from glial cells. They are characterized by invasive growth, indistinct borders, and are difficult to surgically remove. They can cause symptoms such as headaches, vomiting, seizures, and limb dysfunction, severely affecting brain function. They can be classified into several types based on cell type, posing a significant threat to the patient's life and health.

[0003] The invention patent application number 200310109069.X discloses a method for implementing a computer-aided diagnostic system for gliomas based on data mining, characterized by the following specific steps: Attribute digitization: For each attribute in the case database, sort it according to different descriptive forms and replace it with integers of the corresponding order, that is, map the attribute value into an integer sequence, and mark any non-existent attribute values; Establishing fuzzy membership for each digitized attribute: After the digitization process, define a sensitivity factor r to establish membership relationships between different values ​​of the same attribute, that is, for a certain attribute A, its k-th value... With the j-th value The membership degree between them is This is worth It is the maximum value of attribute A. It is the minimum value of attribute A, and r generally takes a value between 0 and 10.

[0004] The application aims to address the following problems: "Decision tree methods are used to discover diagnostic patterns, but the generated decision trees have many nodes, are difficult to understand, and are prone to overfitting; rough set theory is not good at handling real-valued data and uncertain descriptions, and generates a large number of rules that are not concise and are difficult to understand; multilayer perceptron networks based on the BP training algorithm can achieve high diagnostic accuracy but have very poor interpretability."

[0005] However, while gliomas can currently be prevented by obtaining brain MRI images during regular checkups, this process requires doctors to observe the MRI images based on their own experience and make a predictive diagnosis. This places high demands on the doctor's professional knowledge and experience, which prevents this method from being widely adopted.

[0006] To address this, a diagnostic system for gliomas based on contralateral localization of resting-state brain function was proposed. Summary of the Invention

[0007] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a glioma diagnostic system based on resting-state brain function contralateral localization, which solves the technical problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A glioma diagnostic system based on contralateral localization of resting-state brain function includes:

[0010] The system comprises the following modules: an acquisition module for acquiring brain MRI image data; a conversion module for retrieving the acquired brain MRI image data and converting it into a waveform image; a segmentation module for receiving the waveform image obtained from the conversion module and segmenting it; an evaluation module for acquiring the segmented waveform image from the segmentation module and assessing the risk of glioma based on the waveform image; a calibration module for receiving the glioma risk assessment result from the evaluation module and further calibrating the assessment result; and a diagnosis module for acquiring the calibrated assessment result from the calibration module and diagnosing whether the user has a risk of glioma based on the assessment result.

[0011] The acquisition module is connected to a preprocessing and database via a wireless network. The acquisition module is also connected to a conversion module via a wireless network. The conversion module contains a segmentation unit via a wireless network. The conversion module is further connected to a segmentation module and an evaluation module via a wireless network. The evaluation module is connected to a calculation unit via a wireless network. The evaluation module also contains a calibration module and a diagnostic module via a wireless network. The calibration module is connected to the calculation unit via a wireless network.

[0012] Furthermore, the user's brain magnetic resonance image data acquired by the acquisition module originates from a magnetic resonance imaging device, and the acquisition module has sub-modules, including:

[0013] The preprocessing unit is used to receive the user's brain magnetic resonance image data acquired by the acquisition module and to smooth the user's brain magnetic resonance image data.

[0014] The database is used to obtain and store the user's brain magnetic resonance image data after smoothing in the preprocessing unit.

[0015] The preprocessing unit includes a smoothing logic for user brain MRI image data. Based on this logic, the user brain MRI image data is preprocessed. Each set of user brain MRI image data is marked with an acquisition timestamp. When storing user brain MRI image data in the database, a storage sequence is generated based on the acquisition timestamps corresponding to each user brain MRI image data. The user brain MRI image data is then sorted and stored based on the storage sequence.

[0016] Furthermore, the smoothing logic for the user's brain magnetic resonance image data in the preprocessing unit is expressed as follows:

[0017] ;

[0018] In the formula: The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image after smoothing. Weights for grayscale differences; The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image.

[0019] in, , For sensitivity parameters; The grayscale value of a pixel in a brain MRI image; sensitivity parameter. The value is defined by the system user, and the sensitivity parameter The value ranges from 0.1 to 1. Based on the above formula, each pixel in the user's brain magnetic resonance image data is smoothed to output the user's brain magnetic resonance image data after smoothing.

[0020] Furthermore, each time the conversion module runs, it retrieves at least two sets of user brain MRI image data at the center position of the stored sequence from the database. The conversion module internally includes sub-modules, including:

[0021] The segmentation unit is used to acquire the user's brain magnetic resonance image data retrieved by the conversion module, and to symmetrically segment the user's brain magnetic resonance image data to obtain the user's left and right brain magnetic resonance image data.

[0022] The segmentation unit segments the user's brain MRI image data, and then the system allows the user to define the ROI or perform waveform image conversion on the image data globally.

[0023] When the system user customizes the ROI in the user's left and right brain magnetic resonance image data for waveform image conversion, the selected ROI in the user's left and right brain magnetic resonance image data is symmetrically distributed. After the user's brain magnetic resonance image data is segmented, the waveform images corresponding to the user's left and right brain magnetic resonance image data are converted based on Fourier transform.

[0024] Furthermore, the segmentation precision of the waveform image in the segmentation module is 2~ A segment represents a wavy line of a waveform;

[0025] L represents the total number of wave lines that make up the waveform in the waveform image;

[0026] In the segmentation module, the segmentation accuracy of the waveform image is defined by the system user and follows the segmentation logic in the evaluation module: the higher the accuracy requirement for assessing the risk of glioma, the lower the segmentation accuracy, and vice versa.

[0027] Furthermore, after the assessment module obtains the waveform image after segmentation processing, the assessment logic for the risk of glioma is expressed as follows:

[0028] ;

[0029] In the formula: Pearson correlation coefficients between waveform B and reference waveform C in the left and right brain MRI images; The set of midpoints of the waveform; This represents the value of the g-th sampling point in waveform B; The average value of the sampling points of waveform B; The value of the g-th sampling point in the reference waveform C; The average value of the sampling points of the reference waveform C; The overall Pearson correlation coefficient of the waveform obtained by segmenting the segmentation module; This represents the total number of waveform segments; Pearson correlation coefficients of waveform B corresponding to the left and right brain magnetic resonance imaging data and the vth segment of the reference waveform C; As weight;

[0030] In this context, the waveform corresponding to the right brain magnetic resonance image data is denoted as A, and the reference waveform C is obtained by mirroring waveform A. In equation (2) The calculation logic is the same as that of equation (1), and the weights are... The value follows The longer the corresponding waveform length, the higher the weight. The larger the value, the more it follows the rules. , and The larger the value, the higher the waveform symmetry, which means a lower risk of developing glioma; conversely, the smaller the value, the lower the waveform symmetry, which means a higher risk of developing glioma.

[0031] Furthermore, the evaluation module has sub-modules at its lower level, including:

[0032] Nuclear calculation unit, used to combine and A comprehensive assessment of the risk of developing glioma;

[0033] The logic for comprehensively assessing the risk of glioma in the aforementioned nuclear unit is as follows:

[0034] ;

[0035] In the formula: To comprehensively assess the risk of developing glioma; , As a weighting factor;

[0036] Among them, weighting factors , The weighting factor is user-defined on the system side. , The sum is 1. Always less than And weighting factors The value of the weight factor depends on the number of waveform segments in the waveform image. The larger the value, the lower the weighting factor. The smaller the value.

[0037] Furthermore, the glioma risk assessment result received in the calibration module is a comprehensive assessment of glioma risk obtained from the operation of the nuclear counting unit. ;

[0038] Each set of user brain MRI images acquired by the acquisition module yields a set of results. The results obtained from the brain MRI images of each group of users are denoted as follows: ;

[0039] The logical representation of the calibration module performing further calibration on the evaluation results is as follows:

[0040] ;

[0041] In the formula: For calibrated risk of developing glioma; To retrieve the maximum value within the parentheses; To adjust the index; The results were obtained for the corresponding brain MRI images of each group of users;

[0042] Among them, the adjustment index The value is 1 or -1, adjusting the exponent. In the fraction where the numerator is greater than the denominator, the exponent is adjusted. The value is -1; otherwise, the index is adjusted. The value is 1.

[0043] Furthermore, the diagnostic module performs calibration on the data calibrated in the calibration module. Record data and simultaneously set a judgment threshold. Based on the judgment threshold and the recorded data... The comparison helps diagnose whether a user is at risk of developing glioma.

[0044] Among them, any two consecutive records in the diagnostic module Previous group Next group When the value is high, the user is diagnosed with a risk of developing glioma.

[0045] Compared with known public technologies, the technical solution provided by this invention has the following beneficial effects:

[0046] This invention provides a glioma diagnostic system based on resting-state brain function contralateral localization. During operation, the system analyzes the user's brain magnetic resonance imaging data to predict the user's risk of developing glioma, which largely replaces manual work. Its diagnostic accuracy is no longer affected by the accumulation of professional knowledge and experience of human personnel, and it can more accurately predict the risk of patients developing glioma.

[0047] In the process of predicting the risk of glioma based on the user's brain magnetic resonance imaging (MRI) data, the overall analysis of the user's brain MRI images and the segmented analysis of the corresponding waveform images are used to comprehensively assess the user's risk of glioma. This allows the assessment results to more accurately reflect the actual situation shown by the user's brain MRI image data, providing doctors with more favorable data references and supporting the diagnosis of the user's condition. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0049] Figure 1 This is a schematic diagram of a glioma diagnostic system based on contralateral localization of resting-state brain function. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0051] The present invention will be further described below with reference to embodiments.

[0052] Example 1:

[0053] This embodiment of the glioma diagnostic system based on resting-state brain function contralateral localization, such as... Figure 1 As shown, it includes:

[0054] The acquisition module is used to acquire magnetic resonance imaging data of the user's brain;

[0055] The acquisition module collects the user's brain MRI image data from the MRI equipment. The acquisition module has sub-modules, including:

[0056] The preprocessing unit is used to receive the user's brain magnetic resonance image data acquired by the acquisition module and to smooth the user's brain magnetic resonance image data.

[0057] The database is used to obtain and store the user's brain magnetic resonance image data after smoothing in the preprocessing unit.

[0058] The preprocessing unit includes a smoothing logic for user brain MRI image data. Based on this logic, the user brain MRI image data is preprocessed. Each set of user brain MRI image data is marked with an acquisition timestamp. When the database stores user brain MRI image data, it generates a storage sequence based on the acquisition timestamps corresponding to each user brain MRI image data. The user brain MRI image data is then sorted and stored based on the storage sequence.

[0059] The smoothing logic for the user's brain MRI image data in the preprocessing unit is represented as follows:

[0060] ;

[0061] In the formula: The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image after smoothing. Weights for grayscale differences; The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image.

[0062] in, , For sensitivity parameters; The grayscale value of a pixel in a brain MRI image; sensitivity parameter. The value is defined by the system user, and the sensitivity parameter The value ranges from 0.1 to 1. Based on the above formula, each pixel in the user's brain magnetic resonance image data is smoothed to output the user's brain magnetic resonance image data after smoothing.

[0063] The conversion module is used to retrieve the user's brain magnetic resonance image data acquired by the acquisition module and convert the user's brain magnetic resonance image data into waveform images;

[0064] Each time the conversion module runs, it retrieves at least two sets of user brain MRI images from the database, with the images stored in the center of the sequence. The conversion module contains sub-modules, including:

[0065] The segmentation unit is used to acquire the user's brain magnetic resonance image data retrieved by the conversion module, and to symmetrically segment the user's brain magnetic resonance image data to obtain the user's left and right brain magnetic resonance image data.

[0066] The segmentation unit segments the user's brain MRI image data, and then the system allows the user to define the ROI or perform waveform image conversion on the image data globally.

[0067] When the system user defines the ROI in the left and right brain magnetic resonance image data for waveform image conversion, the selected ROI in the left and right brain magnetic resonance image data is symmetrically distributed. After the user's brain magnetic resonance image data is segmented, the waveform images corresponding to the left and right brain magnetic resonance image data are converted respectively based on Fourier transform.

[0068] The segmentation module is used to receive the waveform image obtained by converting the user's brain magnetic resonance image data from the conversion module, and to segment the waveform image.

[0069] The assessment module is used to acquire waveform images of the segments processed in the segmentation module, and to assess the risk of glioma based on the waveform images.

[0070] After the assessment module obtains the waveform image after segmentation processing, the assessment logic for the risk of glioma is as follows:

[0071] ;

[0072] In the formula: Pearson correlation coefficients between waveform B and reference waveform C in the left and right brain MRI images; The set of midpoints of the waveform; This represents the value of the g-th sampling point in waveform B; The average value of the sampling points of waveform B; The value of the g-th sampling point in the reference waveform C; The average value of the sampling points of the reference waveform C; The overall Pearson correlation coefficient of the waveform obtained by segmenting the segmentation module; This represents the total number of waveform segments; Pearson correlation coefficients of waveform B corresponding to the left and right brain magnetic resonance imaging data and the vth segment of the reference waveform C; As weight;

[0073] In this context, the waveform corresponding to the right brain magnetic resonance image data is denoted as A, and the reference waveform C is obtained by mirroring waveform A. In equation (2) The calculation logic is the same as that of equation (1), and the weights are... The value follows The longer the corresponding waveform length, the higher the weight. The larger the value, the more it follows the rules. , and The larger the value, the higher the waveform symmetry, which means a lower risk of developing glioma; conversely, the smaller the value, the lower the waveform symmetry, which means a higher risk of developing glioma.

[0074] The evaluation module has sub-modules, including:

[0075] Nuclear calculation unit, used to combine and A comprehensive assessment of the risk of developing glioma;

[0076] The logic for comprehensively assessing the risk of glioma within the accounting unit is as follows:

[0077] ;

[0078] In the formula: To comprehensively assess the risk of developing glioma; , As a weighting factor;

[0079] Among them, weighting factors , The weighting factor is user-defined on the system side. , The sum is 1. Always less than And weighting factors The value of the weight factor depends on the number of waveform segments in the waveform image. The larger the value, the lower the weighting factor. The smaller the value;

[0080] The calibration module is used to receive the glioma risk assessment results from the assessment module and to further calibrate the assessment results.

[0081] The glioma risk assessment results received in the calibration module are a comprehensive assessment of glioma risk obtained from the operation of the nuclear unit. ;

[0082] Each set of user brain MRI images acquired by the acquisition module yields a set of results. The results obtained from the brain MRI images of each group of users are denoted as follows: ;

[0083] The logic for the calibration module to further calibrate the evaluation results is as follows:

[0084] ;

[0085] In the formula: For calibrated risk of developing glioma; To retrieve the maximum value within the parentheses; To adjust the index; The results were obtained for the corresponding brain MRI images of each group of users;

[0086] Among them, the adjustment index The value is 1 or -1, adjusting the exponent. In the fraction where the numerator is greater than the denominator, the exponent is adjusted. The value is -1; otherwise, the index is adjusted. The value is 1;

[0087] The diagnostic module is used to obtain the evaluation results of the calibration module and diagnose whether the user is at risk of developing glioma based on the evaluation results;

[0088] The acquisition module has a preprocessing and database connected to it via a wireless network. The acquisition module also has a conversion module connected to it via a wireless network. The conversion module has a segmentation unit connected to it via a wireless network. The conversion module also has a segmentation module and an evaluation module connected to it via a wireless network. The evaluation module has a calculation unit connected to it via a wireless network. The evaluation module also has a calibration module and a diagnostic module connected to it via a wireless network. The calibration module is connected to the calculation unit via a wireless network.

[0089] In this embodiment, the acquisition module acquires the user's brain MRI image data. The preprocessing unit simultaneously receives the acquired brain MRI image data and smooths it. The database retrieves the smoothed brain MRI image data output from the preprocessing unit in real time and stores it. The conversion module then retrieves the acquired brain MRI image data and converts it into a waveform image. The segmentation unit simultaneously retrieves the converted brain MRI image data and performs symmetrical segmentation to obtain the left and right brain MRI image data. The segmentation module then receives the waveform image obtained from the converted brain MRI image data and segments it. The evaluation module further acquires the segmented waveform image from the segmentation module and assesses the risk of glioma based on the waveform image. The calculation unit simultaneously combines... and The system comprehensively assesses the risk of developing glioma. The calibration module further receives the risk assessment results of glioma from the assessment module, calibrates the assessment results, and finally obtains the assessment results calibrated by the calibration module through the diagnosis module. Based on the assessment results, the system diagnoses whether the user has a risk of developing glioma.

[0090] The operation of the above system provides predictive diagnostic opinions for the diagnosis of gliomas, effectively achieving the prevention of this type of disease, and largely replacing the step of manually observing brain MRI images, reducing the need for manual intervention, and making the diagnosis and predictive diagnosis of gliomas faster and more accurate.

[0091] Meanwhile, the operation of the brain magnetic resonance image processing module recorded by the system provides precision adjustment and improvement for the predictive diagnosis of gliomas, ensuring that the system can bring more effective reference information for the diagnosis of gliomas.

[0092] Example 2:

[0093] At the implementation level, based on Example 1, this example refers to... Figure 1 The following provides a further detailed explanation of the glioma diagnostic system based on contralateral localization of resting-state brain function in Example 1:

[0094] The segmentation module provides a segmentation precision of 2~ for the waveform image. A segment represents a wavy line of a waveform;

[0095] L represents the total number of wave lines that make up the waveform in the waveform image;

[0096] In the segmentation module, the segmentation accuracy of the waveform image is defined by the system user and follows the segmentation logic in the evaluation module: the higher the accuracy requirement for assessing the risk of glioma, the lower the segmentation accuracy, and vice versa.

[0097] The above settings further limit the segmentation processing logic of the converted waveform image in the segmentation module, and use it as a means to control the accuracy of the system's output results, thereby further constraining the system's operating efficiency and providing convenience for different system usage scenarios.

[0098] like Figure 1 As shown, the diagnostic module runs the calibration module to check the calibration results. Record data and simultaneously set a judgment threshold. Based on the judgment threshold and the recorded data... The comparison helps diagnose whether a user is at risk of developing glioma.

[0099] Among them, any two consecutive records in the diagnostic module Previous group Next group When the value is high, the user is diagnosed with a risk of developing glioma.

[0100] The above settings further limit the operating logic and output of the diagnostic module, enabling the valuable data obtained from the system operation to be summarized and output, providing comprehensive data reference for system users, and thus enabling faster predictive diagnosis of glioma.

[0101] In summary, the system described in the above embodiments, during operation, predicts the risk of a user developing glioma by analyzing the user's brain MRI image data, largely replacing manual intervention. Its diagnostic accuracy is no longer affected by the accumulation of professional knowledge and experience of human personnel, enabling a more accurate prediction of the patient's risk of developing glioma. In the process of predicting the risk of glioma based on the user's brain MRI image data, the system comprehensively assesses the user's risk of developing glioma through overall analysis of the user's brain MRI images and segmented analysis of the corresponding waveform images. This allows the assessment results to more realistically correspond to the actual situation presented by the user's brain MRI image data, providing doctors with more favorable data references and supporting the diagnosis of the user's condition.

[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A glioma diagnostic system based on resting-state contralateral brain function localization, characterized in that, include: The acquisition module is used to acquire magnetic resonance imaging data of the user's brain; The conversion module is used to retrieve the user's brain magnetic resonance image data acquired by the acquisition module and convert the user's brain magnetic resonance image data into waveform images; The segmentation module is used to receive the waveform image obtained by converting the user's brain magnetic resonance image data from the conversion module, and to segment the waveform image. The assessment module is used to acquire waveform images of the segments processed in the segmentation module, and to assess the risk of glioma based on the waveform images. The calibration module is used to receive the glioma risk assessment results from the assessment module and to further calibrate the assessment results. The diagnostic module is used to obtain the evaluation results of the calibration module and diagnose whether the user is at risk of developing glioma based on the evaluation results; After the evaluation module obtains the waveform image after segmentation processing, the evaluation logic for the risk of glioma is as follows: ； In the formula: Pearson correlation coefficients between waveform B and reference waveform C in the left and right brain MRI images; The set of midpoints of the waveform; This represents the value of the g-th sampling point in waveform B; The average value of the sampling points of waveform B; The value of the g-th sampling point in the reference waveform C; The average value of the sampling points of the reference waveform C; The overall Pearson correlation coefficient of the waveform obtained by segmenting the segmentation module; This represents the total number of waveform segments; Pearson correlation coefficients of waveform B corresponding to the left and right brain magnetic resonance imaging data and the vth segment of the reference waveform C; As weight; In this context, the waveform corresponding to the right brain magnetic resonance image data is denoted as A, and the reference waveform C is obtained by mirroring waveform A. In equation (2) The calculation logic is the same as that of equation (1), and the weights are... The value follows The longer the corresponding waveform length, the higher the weight. The larger the value, the more it follows the rules. , and The larger the value, the higher the waveform symmetry, which means a lower risk of developing glioma; conversely, the smaller the value, the lower the waveform symmetry, which means a higher risk of developing glioma. The evaluation module has sub-modules, including: Nuclear calculation unit, used to combine and A comprehensive assessment of the risk of developing glioma; The logic for comprehensively assessing the risk of glioma in the aforementioned nuclear unit is as follows: ； In the formula: To comprehensively assess the risk of developing glioma; , As a weighting factor; Among them, weighting factors , The weighting factor is user-defined on the system side. , The sum is 1. Always less than And weighting factors The value of the weight factor depends on the number of waveform segments in the waveform image. The larger the value, the lower the weighting factor. The smaller the value; The glioma risk assessment result received in the calibration module is a comprehensive assessment of glioma risk obtained from the operation of the nuclear unit. ; Each set of user brain MRI images acquired by the acquisition module yields a set of results. The results obtained from the brain MRI images of each group of users are denoted as follows: ; The logical representation of the calibration module performing further calibration on the evaluation results is as follows: ； In the formula: For calibrated risk of developing glioma; To retrieve the maximum value within the parentheses; To adjust the index; The results were obtained for the corresponding brain MRI images of each group of users; Among them, the adjustment index The value is 1 or -1, adjusting the exponent. In the fraction where the numerator is greater than the denominator, the exponent is adjusted. The value is -1; otherwise, the index is adjusted. The value is 1; The diagnostic module performs calibration on the modules calibrated in the calibration module. Record data and simultaneously set a judgment threshold. Based on the judgment threshold and the recorded data... The comparison helps diagnose whether a user is at risk of developing glioma. Among them, any two consecutive records in the diagnostic module Previous group Next group When the value is high, the user is diagnosed with a risk of developing glioma.

2. The glioma diagnostic system based on resting-state contralateral brain function localization according to claim 1, characterized in that, The acquisition module collects the user's brain MRI image data from an MRI machine. The acquisition module has sub-modules, including: The preprocessing unit is used to receive the user's brain magnetic resonance image data acquired by the acquisition module and to smooth the user's brain magnetic resonance image data. The database is used to obtain and store the user's brain magnetic resonance image data after smoothing in the preprocessing unit. The preprocessing unit includes a smoothing logic for user brain MRI image data. Based on this logic, the user brain MRI image data is preprocessed. Each set of user brain MRI image data is marked with an acquisition timestamp. When storing user brain MRI image data in the database, a storage sequence is generated based on the acquisition timestamps corresponding to each user brain MRI image data. The user brain MRI image data is then sorted and stored based on the storage sequence.

3. The glioma diagnostic system based on resting-state contralateral brain function localization according to claim 2, characterized in that, The smoothing logic for the user's brain MRI image data in the preprocessing unit is represented as follows: ； In the formula: The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image after smoothing. Weights for grayscale differences; The grayscale value of a pixel in a brain magnetic resonance imaging (MRI) image. in, , For sensitivity parameters; The grayscale value of a pixel in a brain MRI image; sensitivity parameter. The value is defined by the system user, and the sensitivity parameter The value ranges from 0.1 to 1. Based on the above formula, each pixel in the user's brain magnetic resonance image data is smoothed to output the user's brain magnetic resonance image data after smoothing.

4. The glioma diagnostic system based on resting-state contralateral brain function localization according to claim 1, characterized in that, Each time the conversion module runs, it retrieves at least two sets of user brain MRI image data at the center position of the stored sequence from the database. The conversion module internally includes sub-modules, including: The segmentation unit is used to acquire the user's brain magnetic resonance image data retrieved by the conversion module, and to symmetrically segment the user's brain magnetic resonance image data to obtain the user's left and right brain magnetic resonance image data. The segmentation unit segments the user's brain MRI image data, and then the system allows the user to define the ROI or perform waveform image conversion on the image data globally. When the system user customizes the ROI in the user's left and right brain magnetic resonance image data for waveform image conversion, the selected ROI in the user's left and right brain magnetic resonance image data is symmetrically distributed. After the user's brain magnetic resonance image data is segmented, the waveform images corresponding to the user's left and right brain magnetic resonance image data are converted based on Fourier transform.

5. The glioma diagnostic system based on resting-state contralateral brain function localization according to claim 1, characterized in that, The segmentation module has a segmentation precision of 2~ for the waveform image. A segment represents a wavy line of a waveform; L represents the total number of wave lines that make up the waveform in the waveform image; In the segmentation module, the segmentation accuracy of the waveform image is defined by the system user and follows the segmentation logic in the evaluation module: the higher the accuracy requirement for assessing the risk of glioma, the lower the segmentation accuracy, and vice versa.

6. The glioma diagnostic system based on resting-state contralateral brain function localization according to claim 1, characterized in that, The acquisition module is connected to a preprocessing and database via a wireless network. The acquisition module is also connected to a conversion module via a wireless network. The conversion module contains a segmentation unit via a wireless network. The conversion module is further connected to a segmentation module and an evaluation module via a wireless network. The evaluation module is connected to a calculation unit via a wireless network. The evaluation module also contains a calibration module and a diagnostic module via a wireless network. The calibration module is connected to the calculation unit via a wireless network.

Images