Brain feature extraction method, system and equipment of MRI (Magnetic Resonance Imaging) image and medium

Abstract

The invention discloses a brain feature extraction method, a brain feature extraction system, brain feature extraction equipment and a medium for an MRI (Magnetic Resonance Imaging) image, and relates to the technical field of intelligent biomedical signal processing. Deep features of a plurality of MRI sequence images are fully excavated, and the extracted imaging features related to brain lymphatic system functions and brain structure morphologies include diffusion degree values when bilateral brain tissues in the brain of a patient are converted into fiber bundles and fiber bundle reference values causing fiber bundle deviation when the brain of the patient discharges. The reference value of the fiber bundle can reflect which parameters are diffusion parameters when bilateral brain tissues are abnormal, and the diffusion degree value and the diffusion parameters reflected by the imaging characteristics are closely related to the epilepsy language barrier function of the patient and can be used as standards for predicting the language barrier of the epilepsy patient.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent biomedical signal processing, and in particular to a method, system, device and medium for extracting brain features from MRI images. Background Art

[0002] Epilepsy is one of the most common central nervous system disorders. The occurrence of epilepsy not only reduces the patient's quality of life, but also brings tremendous pressure and heavy burden to the family and society. In childhood epilepsy, Rolandic epilepsy is characterized by spikes in the Rolandic area on the electroencephalogram. It is the most common epilepsy syndrome in childhood, accounting for about 15.7% of epilepsy. The age of onset of Rolandic epilepsy is mostly between 3 and 13 years old, with a peak of 7 to 8 years old. Studies in recent years have shown that up to 12-65% of children with Rolandic epilepsy have cognitive impairment, especially language impairment. Even if the epileptic seizure stops and the child's cognitive function is significantly improved, the language impairment persists. Rolandic epilepsy is more common during school age, and the abnormal electrical activity is in the key language pathway, so almost all language-related levels are affected. In addition, school age is a critical period for brain development. Therefore, Rolandic epilepsy has a serious and far-reaching impact on the lifelong development of children.

[0003] At present, the diagnosis of language disorders in children with Rolandic epilepsy is often made 18-32 months after the onset of epilepsy, which is a lag and greatly affects the prognosis of children. At the same time, there is a lack of effective biomarkers for predicting language disorders in Rolandic epilepsy. 5-6 years old is the "critical point" of neural plasticity in the process of brain development, with strong plasticity, and is the golden period for intervention. If the risk of language disorders in children with Rolandic epilepsy can be predicted in the early stage of the disease, early intervention will be of great significance and value in reducing the burden on families and society and improving prognosis. At present, neuropsychological assessment is mostly used to evaluate the language function of patients with Rolandic epilepsy, but it has the characteristics of strong subjectivity of manual assessment and lacks objective evaluation methods. At the same time, the brain changes closely related to Rolandic epilepsy patients with language dysfunction in current research are not yet fully clear. Moreover, current research lacks the prediction of language disorders in Rolandic epilepsy patients in the early stage of the disease.

[0004] In response to the problems existing in the above research, the researchers extracted data from Magnetic Resonance Imaging (MRI) to predict language disorders in epilepsy patients. However, the current methods usually focus on extracting shallow features such as shape changes within a single MRI sequence in MRI images, and it is difficult to fully explore the deep features of multiple MRI sequences in MRI images, and it is difficult to apply them to the prediction of language disorders in epilepsy patients. Summary of the invention

[0005] The embodiments of the present invention provide a method, system, device and medium for extracting brain features from MRI images, which can solve the problem in the prior art that the current methods usually focus on extracting shallow features such as shape changes within a single MRI sequence in MRI images, and it is difficult to fully explore the deep features of multiple MRI sequences in MRI images.

[0006] An embodiment of the present invention provides a method for extracting brain features from MRI images, comprising the following steps: Acquire original MRI images of the patient's brain and MRI images after abnormal brain discharge, wherein the MRI images include T1WI sequence images including the cerebral cortex, T2WI sequence images including cerebral blood vessels, and DTI sequence images; The original DTI sequence images and the DTI sequence images after abnormal brain discharge were converted into anisotropic fractional FA images, and the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images were projected into fiber bundles. Obtain the diffusion rate of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharge; The fiber bundles on both sides of the brain in the original DTI sequence images and the DTI sequence images after abnormal brain discharge are quantified, and the range of changes in the fiber bundle quantification values ​​before and after abnormal brain discharge is obtained. Each change value in the range of changes in the fiber bundle quantification value corresponds to a diffusion parameter of the brain white matter microstructure. The number and volume of the spaces around the cerebral blood vessels were extracted from the T2WI sequence images after abnormal brain discharge, and used together with the diffusion rate of the fiber bundles on both sides of the brain as the structural characteristics of the cerebral blood vessels; the size, volume and morphology of the cerebral cortex structure were extracted from the T1WI sequence images after abnormal brain discharge, and used together with the diffusion parameters of the white matter microstructure as the structural characteristics of the cerebral cortex, and the structural characteristics of the cerebral cortex and the structural characteristics of the cerebral blood vessels were used as brain characteristics.

[0007] Preferably, the steps of converting the original DTI sequence images and the DTI sequence images after abnormal brain discharge into anisotropic fractional FA images, and projecting the brain tissue parts in the spaces around cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images into fiber bundles respectively include: The motion artifact correction method is used to correct the motion artifacts in the original DTI sequence images and the DTI sequence images after abnormal brain discharge, and the color-coded anisotropy fractional FA maps corresponding to the original DTI sequence images and the DTI sequence images after abnormal brain discharge are generated according to the corrected original DTI sequence images and the DTI sequence images after abnormal brain discharge; The lateral ventricle body layer of the pseudo-color image of the color-coded fractional anisotropy FA map corresponding to the original DTI sequence images and the DTI sequence images after abnormal brain discharge, and the fiber bundles were projected in the bilateral cerebral hemispheres.

[0008] Preferably, the step of obtaining the diffusion rates of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharge includes: After the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropy fraction FA map corresponding to the DTI sequence image after abnormal brain discharge are projected into fiber bundles, the area corresponding to the fiber bundles is taken as the joint fiber area; Regions of interest of 4 × 3 pixels were drawn in the combined fiber area, and the diffusivity of each fiber in the X-axis, Y-axis, and Z-axis directions was obtained according to the regions of interest.

[0009] Preferably, the diffusion parameters of the brain white matter microstructure include: The anisotropy fraction FA, mean diffusivity MD, axial diffusivity AD and radial diffusivity RD of the white matter microstructural regions.

[0010] Preferably, the extraction of the size, volume and shape of the cerebral cortex structure includes: Segment the T1WI sequence images after abnormal brain discharge into gray matter area, white matter area and cerebrospinal fluid area, and remove the skull area in the T1WI sequence images; The cortical volume, cortical thickness, gyrification index, sulcus depth, type dimension and folding curvature index in each tissue in the T1WI sequence images were identified and used as the size, volume and morphology of the cerebral cortical structure.

[0011] Preferably, the extraction of the number and volume of perivascular spaces includes: The skull region in the T2WI sequence images after abnormal brain discharge is removed, and the remaining brain tissue region after the skull region is removed from the T2WI sequence images is segmented to obtain the white matter region, gray matter region and cerebrospinal fluid region; Identify the number and volume of white matter areas, gray matter areas, cerebrospinal fluid areas, and perivascular spaces.

[0012] Preferably, the extraction of brain features includes: The structural features of cerebral blood vessels are used as imaging features related to the function of the cerebral lymphatic system, and the structural features of the cerebral cortex are used as imaging features related to the brain structure morphology; Among the imaging features related to the function of the glymphatic system and the brain structure and morphology, the t-test was used to preliminarily screen out the features with significant correlation ≤ 0.05, and Lasso regression analysis was performed on the basis of the features screened by the t-test to obtain the features with strong correlation with brain neural changes; Features that are strongly correlated with brain neural changes are set as brain features.

[0013] The embodiment of the present invention further provides a brain feature extraction system for MRI images, comprising: An imaging module is used to obtain original MRI images of the patient's brain and MRI images after abnormal brain discharge, wherein the MRI images include T1WI sequence images including the cerebral cortex, T2WI sequence images including cerebral blood vessels, and DTI sequence images; A parameter extraction module is used to convert the original DTI sequence images and the DTI sequence images after abnormal brain discharge into anisotropic fractional FA images, and project the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images into fiber bundles; Obtain the diffusion rate of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharge; The fiber bundles on both sides of the brain in the original DTI sequence images and the DTI sequence images after abnormal brain discharge are quantified, and the range of changes in the fiber bundle quantification values ​​before and after abnormal brain discharge is obtained. Each change value in the range of changes in the fiber bundle quantification value corresponds to a diffusion parameter of the brain white matter microstructure. The feature construction module is used to extract the number and volume of the spaces around the cerebral blood vessels from the T2WI sequence images after abnormal brain discharge, and use them together with the diffusion rate of the fiber bundles on both sides of the brain as the structural characteristics of the cerebral blood vessels; extract the size, volume and morphology of the cerebral cortex structure from the T1WI sequence images after abnormal brain discharge, and use the diffusion parameters of the white matter microstructure as the structural characteristics of the cerebral cortex, and use the structural characteristics of the cerebral cortex and the structural characteristics of the cerebral blood vessels as brain characteristics.

[0014] An embodiment of the present invention further provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is used to implement the steps of the above-mentioned method for extracting brain features from MRI images when executing the computer program stored in the memory.

[0015] An embodiment of the present invention further provides a computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, the steps of the method for extracting brain features from MRI images as described above are implemented.

[0016] The embodiments of the present invention provide a method, system, device and medium for extracting brain features from MRI images. Compared with the prior art, the beneficial effects thereof are as follows: The present invention first obtains T1WI sequence images, T2WI sequence images and DTI sequence images of the patient's brain, and extracts the number and volume of the perivascular spaces and the diffusion rate of the bilateral fiber bundles in the brain from each sequence image to obtain imaging features related to the function of the cerebral lymphatic system; extracts the structural features of the cerebral cortex and the diffusion parameters of the white matter microstructure from each sequence image to obtain imaging features related to the brain structure morphology; the present invention extracts the imaging features related to the function of the cerebral lymphatic system and the brain structure morphology from the T1WI sequence images, T2WI sequence images and DTI sequence images. When imaging brain features, we fully explore the deep features of multiple MRI sequence images. The extracted imaging features related to the function of the cerebral lymphatic system and the brain structure morphology include the diffusion degree values ​​of the bilateral brain tissue in the patient's brain when they are converted into fiber bundles, and the fiber bundle reference values ​​that cause the fiber bundles to deviate when the patient's brain discharges. The fiber bundle reference values ​​can reflect which parameters are the diffusion parameters when the bilateral brain tissue is abnormal. The diffusion degree values ​​and diffusion parameters reflected by these imaging features are closely related to the patient's epileptic language disorder function and can be used as a standard for predicting language disorders in epileptic patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the overall process of a method for extracting brain features from MRI images provided by an embodiment of the present invention; Figure 2 A simplified flowchart of a method for extracting brain features from MRI images provided by an embodiment of the present invention; Figure 3 A schematic diagram of a process of PVS quantitative analysis of a brain feature extraction method of an MRI image provided by an embodiment of the present invention; Figure 4 A schematic diagram of a DTI-ALPS index processing flow of a method for extracting brain features from MRI images provided by an embodiment of the present invention; Figure 5 A schematic diagram of feature screening of a method for extracting brain features from MRI images provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0019] See also Figure 1 , an embodiment of the present invention provides a method for extracting brain features from MRI images, comprising: 1. Obtain clinical data, brain MRI image datasets, and neuropsychological scores of newly diagnosed Rolandic epilepsy patients. Specifically:

[0020] 1. Recruit subjects with Rolandic epilepsy and set inclusion and exclusion criteria.

[0021] Inclusion criteria included: ①Right-handed children aged 6-9 whose mother tongue is Chinese.

[0022] ②The clinical diagnosis is in accordance with the Rolandic diagnostic criteria established by the International League Against Epilepsy.

[0023] ③No previous use of anti-epileptic drugs.

[0024] ④No other neuropsychiatric disorders.

[0025] ⑤There are no contraindications to MRI examination.

[0026] Exclusion criteria include: ①The MRI image is incomplete or cannot be interpreted due to motion artifacts.

[0027] ② Neuropsychological assessment data are incomplete.

[0028] ③Conventional MRI of the head shows abnormalities.

[0029] 2. Collection of clinical data, including: age, gender, onset time of epileptic seizures, duration of seizures and frequency of seizures.

[0030] 3. Brain MRI images of Rolandic epilepsy patients were acquired using a 3.0T MRI high-resolution magnetic resonance scanner (SignaHDxt 3.0T MRI, GE Healthcare). The scanning sequence included: 3D-T1WI data, T2WI data, and DTI. The specific scanning parameters are shown in Table 1.

[0031] Table 1 Scanning parameters 4. Neuropsychological evaluation: specifically, neuropsychological assessment of the children at the beginning of the disease and 18 months after the onset of the disease.

[0032] The specific assessment scale is: Wechsler Intelligence Scale for Children (Chinese Fourth Edition): It includes tests such as decoding, vocabulary, letter-number sequencing, matrix reasoning, comprehension, symbol retrieval, building blocks, similarities, memorizing numbers, and drawing. It can obtain the subject's verbal IQ and verbal comprehension factor, thereby evaluating children's verbal comprehension ability.

[0033] 2. Process the images in the data set, obtain multiple imaging features, and perform feature screening; specifically including: 1. By processing T1WI images, the cortical volume, thickness, gyration index, and folding curvature index can be obtained.

[0034] The SBM method was used to analyze 3D-T1WI data, and the CAT12 toolkit was used for processing based on the MATLAB platform, which mainly included image format conversion, spatial standardization, brain tissue segmentation, image modulation, and smoothing. The specific process is as follows:

[0035] ① Image format conversion: convert all image formats from DICOM to NIfTI format.

[0036] ② Spatial standardization: Standardization is to align the brains of subjects of different volumes and shapes to the standard brain template space MNI to unify the coordinate space of all images.

[0037] ③ Brain tissue segmentation: Remove the skull and automatically segment each subject’s 3D-T1WI image into gray matter, white matter, and cerebrospinal fluid.

[0038] ④ Image modulation: multiply each spatially normalized image by the relative volume before and after normalization to maintain the total amount of each tissue.

[0039] ⑤ Smoothing: The smoothing kernel size for cortical thickness and sulcus depth feature image processing is 15 mm, and the smoothing kernel size for feature dimension and folding degree image processing is 25 mm.

[0040] Use Get TIV in the Statistical Analysis module in the CAT12 panel to extract the specific values ​​of cortical volume; use Wrriting options in the Segment module to extract the specific values ​​of cortical thickness; and use the Extract Additional surface Parameters module in the Surface Tools module to extract the specific values ​​of sulcus depth, classification dimension, and gyratory index.

[0041] 2. Processing T2WI images can obtain the number and volume of the spaces around cerebral blood vessels. The main steps include preprocessing and quantitative index extraction. The specific process is as follows: Figure 3 Specifically including:

[0042] ① Use ITK software to remove the braincase from the skull MRI image.

[0043] ② Using the Segment under the fMRI module in the spm 12 toolkit based on the MATLAB platform, the brain tissue can be segmented to obtain white matter, gray matter and cerebrospinal fluid.

[0044] ③ Based on the MATLAB platform and the 2D Frangi filter algorithm, the axial T2WI images were segmented to obtain the perivascular space (PVS).

[0045] ④Based on the FSL platform, the number and volume of segmented PVS are quantitatively analyzed according to the following instructions.

[0046] fslmaths ${f} -mul ${f}-mask ${f}_roi cluster -i ${f}_roi -t 0.5 --mm>>${f}_clusters.msf 3. Based on the DTI images, the diffusion tensor image analysis along the perivascular space index (DTI-ALPS index) is calculated; Figure 4 As shown, specifically including: ① Use motion artifact correction method to correct motion artifacts.

[0047] ② Use FSL software to generate color-coded fractional anisotropy (FA) maps.

[0048] ③ In the lateral ventricle body level of the FA pseudo-color image, 4×3 pixel regions of interest were outlined in the projection fiber and association fiber areas of the bilateral cerebral hemispheres, and the diffusion rate of each fiber in the X-axis, Y-axis and Z-axis directions could be obtained.

[0049] ④ Calculate according to the formula DTI-ALPS, the formula is expressed as: index = .

[0050] Where: Dxxproj and Dxxassoci represent the diffusivities of the projected fibers and the associated fibers in the X-axis direction, respectively; Dyyproj represents the diffusivity of the projected fibers in the Y-axis direction; and Dzzassoci represents the diffusivity of the associated fibers in the Z-axis direction.

[0051] 4. Parameter calculation based on diffusion MRI. Specifically including:

[0052] ① Perform brain region extraction, eddy current correction, head motion correction and artifact removal on DTI.

[0053] ②Acquire brain white matter microstructural parameters (FA, MD, AD, RD) based on DTI sequence images.

[0054] 5. Further filter the brain T1WI, T2WI and DTI sequence images to obtain filtered images.

[0055] 6. Based on the filtered images, image omics features of brain T1WI, T2WI and DTI sequences were extracted to obtain omics features.

[0056] 7. Combine t-test and Lasso method to preliminarily screen the most representative features, further combine with neuropsychological scores, eliminate features with low correlation with prognosis, and thus obtain a small number of important features with strong correlation with the prediction results of Rolandic epilepsy language disorder; Figure 5 shown.

[0057] Third, the important features are input into the machine learning model, and the disease is classified according to the classification label to obtain the classification results of Rolandic epilepsy with or without language disorder.

[0058] Fourth, calculate the area under the curve, sensitivity, specificity, accuracy and other indicators of the training set and validation set of each model, evaluate the prediction effect, and select the optimal model.

[0059] The specific steps include: 1. Data collection.

[0060] 1.1 Data collection: As mentioned above, this method collected brain MRI imaging data of a group of subjects with Rolandic epilepsy. At the same time, the age, gender, onset time, duration and frequency of epileptic seizures were collected. Neuropsychological assessments were performed on the children at the beginning of the disease and 18 months after the onset.

[0061] 2. Build a model to predict language impairment in patients with Rolandic epilepsy.

[0062] 2.1 Based on the results of neuropsychological assessment 18 months after onset, the subjects with Rolandic epilepsy were divided into Rolandic epilepsy patients with language disorders and Rolandic patients without language disorders; 2.2 The subjects with Rolandic epilepsy with and without language disorders were further randomly divided into a training set and a test set in a ratio of 8:2. The sample selection and data set distribution of the two groups are shown in Table 2.

[0063] Table 2 Prediction of language impairment in Rolandic epilepsy dataset 2.3 The cranial MRI imaging data were analyzed and processed, and univariate and multivariate logistic regression analyses were performed to determine that the cortical thickness of the left supramarginal gyrus and superior temporal gyrus, the number and volume of perivascular spaces PVS, were highly correlated with patients with Rolandic epilepsy with language disorders.

[0064] 2.4 The head MRI image data in DICOM format were imported into 3D Slicer software, and a senior physician manually outlined the region of interest (the left superior temporal gyrus region on the T1WI sequence, and the perivascular space VRS at the level of the centrum semiovale on the T2WI sequence), which was then reviewed by another senior physician. If there were any objections, they communicated and negotiated with each other to reach a final result.

[0065] 2.5 Use Python's PyRadiomics toolkit to extract radiomic features of the region of interest. The extracted features were summarized, and the features with significant correlation ≤ 0.05 were preliminarily screened out using the t-test. Then, Lasso regression analysis was performed on the basis of the features screened by the t-test to obtain fewer features with strong correlation with the prediction results of Rolandic epilepsy language disorder. In this step, by extracting the omics features of the image, the omics features were gradually screened using the t-test and Lasso regression analysis, and a small number of omics features with strong correlation with Rolandic epilepsy language disorder were obtained as important features. Finally, 5 radiomic features were screened out as the optimal feature subset.

[0066] 2.6 Training a machine learning model for classification of Rolandic epileptic language disorders.

[0067] The extracted omics features were input into the machine learning algorithm for training, and model training was performed through logistic regression analysis (LRA), K-Nearest Neighbour (KNN), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Light Gradient Boosting machine (LightGBM), and Extreme Gradient Boosting (XGBoost).

[0068] The diagnostic performance of the model was evaluated using sensitivity, specificity, accuracy, area under the receiver operating characteristic curve (AUC), F1-score, and Table 3 shows the comparison of the prediction results of each algorithm.

[0069] Table 3 Prediction results of each algorithm The present invention extracts imaging omics features based on multiple MRI sequences (T1WI, T2WI and DTI), and performs three feature screenings in combination with the Lasso method and neuropsychological assessment results, thereby constructing an optimal clinical-imaging-neuropsychological multimodal visualization model of Rolandic epilepsy with language disorders. This model can realize individualized assessment of the language function of children with Rolandic epilepsy and achieve objectivity in clinical assessment. This model can be used to conduct a preliminary assessment of the language function of children with Rolandic epilepsy in the early stages of the disease.

[0070] The present invention explored the relationship between changes in brain fine structure and language function, namely, the node efficiency of the left superior temporal gyrus, the node efficiency of the left inferior frontal gyrus, the anisotropy fraction of the bilateral superior longitudinal fasciculus, and the left uncinate fasciculus were closely related to language function; further, imaging genomics features were extracted based on multiple MRI sequences (T1WI, T2WI and DTI), and two feature screenings were performed in combination with the Lasso method and neuropsychological assessment results, thereby constructing the optimal clinical-imaging-neuropsychological multimodal visualization model of Rolandic epilepsy with language disorders. This model can realize individualized evaluation of the language function of children with Rolandic epilepsy, and can also achieve objectivity in clinical evaluation. This model can be used to conduct a preliminary evaluation of the language function of children with Rolandic epilepsy in the early stage of the disease.

[0071] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for extracting brain features from MRI images, characterized in that: The following steps are involved: Acquire original MRI images of the patient's brain and MRI images after abnormal brain discharge, wherein the MRI images include T1WI sequence images including the cerebral cortex, T2WI sequence images including cerebral blood vessels, and DTI sequence images; The original DTI sequence images and the DTI sequence images after abnormal brain discharge were converted into anisotropic fractional FA images, and the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images were projected into fiber bundles. Obtain the diffusion rate of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharge; The fiber bundles on both sides of the brain in the original DTI sequence images and the DTI sequence images after abnormal brain discharge are quantified, and the range of changes in the fiber bundle quantification values ​​before and after abnormal brain discharge is obtained. Each change value in the range of changes in the fiber bundle quantification value corresponds to a diffusion parameter of the brain white matter microstructure. The number and volume of the spaces around the cerebral blood vessels were extracted from the T2WI sequence images after abnormal brain discharge, and used together with the diffusion rate of the fiber bundles on both sides of the brain as the structural characteristics of the cerebral blood vessels; the size, volume and morphology of the cerebral cortex structure were extracted from the T1WI sequence images after abnormal brain discharge, and used together with the diffusion parameters of the white matter microstructure as the structural characteristics of the cerebral cortex, and the structural characteristics of the cerebral cortex and the structural characteristics of the cerebral blood vessels were used as brain characteristics.

2. The method for extracting brain features from MRI images according to claim 1, characterized in that: The method converts the original DTI sequence images and the DTI sequence images after abnormal brain discharge into anisotropic fractional FA images, and projects the brain tissue parts in the spaces around the cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images into fiber bundles, including: The motion artifact correction method is used to correct the motion artifacts in the original DTI sequence images and the DTI sequence images after abnormal brain discharge, and the color-coded anisotropy fractional FA maps corresponding to the original DTI sequence images and the DTI sequence images after abnormal brain discharge are generated according to the corrected original DTI sequence images and the DTI sequence images after abnormal brain discharge; The lateral ventricle body layer of the pseudo-color image of the color-coded fractional anisotropy FA map corresponding to the original DTI sequence images and the DTI sequence images after abnormal brain discharge, and the fiber bundles were projected in the bilateral cerebral hemispheres.

3. The method for extracting brain features from MRI images according to claim 2, characterized in that: The method of obtaining the diffusion rates of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharges includes: After the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropy fraction FA map corresponding to the DTI sequence image after abnormal brain discharge are projected into fiber bundles, the area corresponding to the fiber bundles is taken as the joint fiber area; Regions of interest of 4 × 3 pixels were drawn in the combined fiber area, and the diffusivity of each fiber in the X-axis, Y-axis, and Z-axis directions was obtained according to the regions of interest.

4. The method for extracting brain features from MRI images according to claim 1, characterized in that: The diffusion parameters of the brain white matter microstructure include: The anisotropy fraction FA, mean diffusivity MD, axial diffusivity AD and radial diffusivity RD of the white matter microstructural regions.

5. The method for extracting brain features from MRI images according to claim 1, characterized in that: The extraction of the size, volume and shape of the cerebral cortex structure includes: Segment the T1WI sequence images after abnormal brain discharge into gray matter area, white matter area and cerebrospinal fluid area, and remove the skull area in the T1WI sequence images; The cortical volume, cortical thickness, gyrification index, sulcus depth, type dimension and folding curvature index in each tissue in the T1WI sequence images were identified and used as the size, volume and morphology of the cerebral cortical structure.

6. The method for extracting brain features from MRI images according to claim 1, characterized in that: The extraction of the number and volume of the perivascular spaces includes: The skull region in the T2WI sequence images after abnormal brain discharge is removed, and the remaining brain tissue region after the skull region is removed from the T2WI sequence images is segmented to obtain the white matter region, gray matter region and cerebrospinal fluid region; Identify the number and volume of white matter areas, gray matter areas, cerebrospinal fluid areas, and perivascular spaces.

7. The method for extracting brain features from MRI images according to claim 1, characterized in that: The extraction of brain features includes: The structural features of cerebral blood vessels are used as imaging features related to the function of the cerebral lymphatic system, and the structural features of the cerebral cortex are used as imaging features related to the brain structure morphology; Among the imaging features related to the function of the glymphatic system and the brain structure and morphology, the t-test was used to preliminarily screen out the features with significant correlation ≤ 0.05, and Lasso regression analysis was performed on the basis of the features screened by the t-test to obtain the features with strong correlation with brain neural changes; Features that are strongly correlated with brain neural changes are set as brain features.

8. A brain feature extraction system for MRI images, characterized in that: include: An imaging module is used to obtain original MRI images of the patient's brain and MRI images after abnormal brain discharge, wherein the MRI images include T1WI sequence images including the cerebral cortex, T2WI sequence images including cerebral blood vessels, and DTI sequence images; A parameter extraction module is used to convert the original DTI sequence images and the DTI sequence images after abnormal brain discharge into anisotropic fractional FA images, and project the brain tissue parts in the space around the cerebral blood vessels on both sides of the brain in the anisotropic fractional FA images into fiber bundles; Obtain the diffusion rate of the fiber bundles on both sides of the brain in the DTI sequence images after abnormal brain discharge; The fiber bundles on both sides of the brain in the original DTI sequence images and the DTI sequence images after abnormal brain discharge are quantified, and the range of changes in the fiber bundle quantification values ​​before and after abnormal brain discharge is obtained. Each change value in the range of changes in the fiber bundle quantification value corresponds to a diffusion parameter of the brain white matter microstructure. The feature construction module is used to extract the number and volume of the spaces around the cerebral blood vessels from the T2WI sequence images after abnormal brain discharge, and use them together with the diffusion rate of the fiber bundles on both sides of the brain as the structural characteristics of the cerebral blood vessels; extract the size, volume and morphology of the cerebral cortex structure from the T1WI sequence images after abnormal brain discharge, and use the diffusion parameters of the white matter microstructure as the structural characteristics of the cerebral cortex, and use the structural characteristics of the cerebral cortex and the structural characteristics of the cerebral blood vessels as brain characteristics.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is used to implement the steps of the brain feature extraction method of MRI images as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the steps of a method for extracting brain features from MRI images as described in any one of claims 1 to 7.

Images