System for evaluating correlation between brain network function connection and step speed of Parkinson's disease patient

Abstract

The invention discloses a system for evaluating correlation between brain network function connection and step speed of a Parkinson's disease patient, and relates to the technical field of medical diagnosis. The data acquisition module is connected with the data collection module; the data preprocessing module is connected with the data acquisition module; the data analysis module is connected with the data preprocessing module; and the correlation evaluation module is respectively connected with the data acquisition module and the data analysis module. According to the method, the correlation between the brain network function connection and the step speed of the Parkinson's disease patient is evaluated based on the functional magnetic resonance imaging and the step speed of the Parkinson's disease patient, so that the specific brain network function activity mode and region related to the abnormal step speed of the Parkinson's disease patient can be more accurately observed; the pathophysiological change of the Parkinson's disease patient is further clarified. Subsequent detection and intervention are carried out on related positions, so that illness monitoring and symptom improvement of the patient can be facilitated.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and more specifically to a system for evaluating the correlation between brain network functional connectivity and walking speed in patients with Parkinson's disease. Background Art

[0002] Parkinson's disease (PD) is the second most common neurodegenerative disease with a series of motor and non-motor symptoms and is a serious social health problem.

[0003] Gait disorder is one of the most common disabling symptoms of PD. It worsens with the progression of the disease and becomes the main reason affecting patients' independence and daily functions. Training in walking tasks can improve the physical and cognitive functions of PD patients. Some studies have investigated the relationship between gait speed and other clinical characteristics, but the results are inconsistent, and few studies have studied the underlying mechanisms in depth.

[0004] Resting-state functional magnetic resonance imaging (rs-fMRI) is a rapidly developing imaging technology with high sensitivity. It can identify brain degeneration at an early stage and plays an important role in the study of disease mechanisms. Considering the continuous development of imaging technology and gait detection technology and their clinical research potential, and to fill the knowledge gap in this field, there is an urgent need for a system that can effectively evaluate the correlation between brain network functional connectivity and gait speed in Parkinson's disease patients, so as to provide further technical support for the study of the mechanism of Parkinson's disease. Summary of the invention

[0005] In order to overcome the defects existing in the above-mentioned prior art, the present invention discloses a system for evaluating the correlation between brain network functional connectivity and gait speed in Parkinson's patients. The present invention can evaluate the correlation between brain network functional connectivity and gait speed in Parkinson's patients. For example, the specific location of the brain network related to the abnormal gait speed of Parkinson's patients can be clearly identified, which is helpful for subsequent detection and intervention of related brain network functions to observe or improve the symptoms of Parkinson's patients.

[0006] In order to achieve the above objectives, the technical solution adopted by the present invention is: The system used to evaluate the correlation between brain network functional connectivity and gait speed in patients with Parkinson's disease includes: Data collection module, used to collect data of Parkinson's disease patients; A data acquisition module, connected to the data collection module, for sequentially acquiring the gait parameter data and functional magnetic resonance imaging data of the Parkinson's disease patient according to the Parkinson's disease patient data; A data preprocessing module, connected to the data acquisition module, for preprocessing functional magnetic resonance imaging data; A data analysis module, connected to the data preprocessing module, for sequentially performing independent component analysis and brain network functional connectivity analysis on the preprocessed functional magnetic resonance imaging data; The correlation evaluation module is connected to the data acquisition module and the data analysis module respectively, and uses the brain network functional connection analysis data and the walking speed parameter data to evaluate the correlation between the brain network functional connection and the walking speed of Parkinson's disease patients.

[0007] Specifically, the modules are as follows: 1. Data Collection Module Preferably, the Parkinson's disease patient data collected by the data collection module include: Parkinson's disease patients' age, gender, education level, course of disease, Parkinson's disease motor function score and medication status, as well as healthy control data matching the Parkinson's disease patients' age, gender and education level.

[0008] In the present invention, the data collection module can adopt a patient electronic medical record system in a computer, in which the patient's data is collected. The data collection module is connected to the data acquisition module, and the collected data is used for subsequent use.

[0009] 2. Data Acquisition Module Preferably, the data acquisition module includes a motor function quantitative evaluation system and a nuclear magnetic resonance imaging scanner, the motor function quantitative evaluation system acquires gait parameter data of Parkinson's patients, and the nuclear magnetic resonance imaging scanner acquires resting-state functional magnetic resonance imaging data of Parkinson's patients.

[0010] 2.1. The quantitative evaluation system for motor function collects pace parameter data Preferably, the motor function quantitative assessment system includes a red, green, and blue camera, a depth camera, and a processing terminal; the red, green, and blue camera and the depth camera are all connected to the processing terminal, the red, green, and blue camera and the depth camera collect three-dimensional motion image data of the subject, and send the collected three-dimensional motion image data to the processing terminal, the processing terminal combines a deep learning algorithm to locate bone points, and simultaneously tracks multiple bones, visually perceives and estimates 3D joints and landmarks, and calculates the subject's walking speed parameter data.

[0011] Preferably, the motor function quantitative assessment system collects data from Parkinson's disease patients including a low gait speed subgroup and a high gait speed subgroup.

[0012] In the present invention, the walking speed parameter data is objectively analyzed and collected by the above-mentioned motor function quantitative evaluation system. Walking speed is a basic characteristic of gait, which is defined as the distance / time between the starting point and the end point. It is a simple, reliable and easy-to-measure parameter that reflects overall activity ability and health status. In clinical practice, it is often used as a rapid screening tool to evaluate the functional status of individuals, which is helpful for clinical diagnosis, efficacy evaluation, mechanism research, and guiding rehabilitation evaluation and treatment. In the gait test, the subject will conduct a practice test before the actual test, and then walk along a 3-meter-long sidewalk at a usual speed. There are no obstacles during the walking process and no sensors need to be worn.

[0013] 2.2. MRI Scanner Acquiring fMRI Data Preferably, the MRI scanner is equipped with a 32-channel head coil, and its three-dimensional T1-weighted sequence parameters are: repetition time = 2300 ms, echo time = 2.01 ms, flip angle = 8°, field of view = 256 × 256 cm 2 , matrix size = 256 × 256, number of slices = 192, slice thickness = 1 mm, voxel size = 1.0 × 1.0 × 1.0 mm 3 ; Functional magnetic resonance imaging data used an echo planar imaging sequence with the following parameters: repetition time = 2000 ms, echo time = 30 ms, flip angle = 90°, field of view = 224 × 224 mm 2 , matrix size = 64 × 64, number of slices = 36, slice thickness = 3.5 mm, slice gap = 0.7 mm, voxel size = 3.5 × 3.5 × 3.5 mm 3 .

[0014] 3. Data Preprocessing Module Preferably, the data preprocessing module includes data preprocessing software, and the data preprocessing software preprocesses the functional magnetic resonance imaging data including the following steps: A1. Delete the first 10 time points of each subject's functional magnetic resonance imaging data; A2, performing time layer correction on the functional magnetic resonance imaging data after deleting the first 10 time points, and aligning the time axis of the functional magnetic resonance imaging data; A3. Perform head motion correction on the time-layer corrected functional magnetic resonance imaging data, expand the head motion parameter limit to a maximum displacement of <2 mm in the x, y or z plane, and an angular rotation of <2° on each axis, and obtain the average functional image data; A4. The T1 structural image was co-registered to the motion-corrected average functional image data. The functional image was then normalized from the individual original space to the Montreal Neurological Institute space and sampled into 3 × 3 × 3 mm 3 ; A5. Use a 6-mm full-width half-maximum Gaussian kernel to spatially smooth the sampled data to obtain functional magnetic resonance imaging data for data analysis.

[0015] In the present invention, the purpose of preprocessing functional magnetic resonance imaging data is to remove various non-physiological noises and artifacts to ensure the quality and consistency of the data and improve the effectiveness of statistical analysis.

[0016] Specifically, the purpose of step A1 is to remove the interference of initial fluctuations in functional magnetic resonance imaging data on the analysis results and ensure the stability and reliability of the data.

[0017] The purpose of step A2 is to correct time differences and realign the signals of each voxel to a reference time point, thereby ensuring that data from different time layers can consistently reflect changes in neural activity on the time axis.

[0018] The purpose of step A3 is to align the data at all time points to a reference position, reduce artifacts and errors caused by head movement, and ensure the spatial consistency of the data.

[0019] The purpose of step A4 is to accurately align high-resolution anatomical information with low-resolution functional data to facilitate the location of specific brain areas in the functional data, so that data from different subjects can be compared in the same spatial framework.

[0020] The purpose of step A5 is to enhance the signal-to-noise ratio of the spatial signal and help improve the statistical power.

[0021] 4. Data Analysis Module Preferably, the brain network functional connectivity analysis of the data analysis module includes functional connectivity analysis within the brain network and between brain networks.

[0022] Preferably, the data analysis module includes a brain functional magnetic resonance imaging tool, and the brain functional magnetic resonance imaging tool performs independent component analysis and brain network functional connectivity analysis on the pre-processed functional magnetic resonance imaging data, including the following steps: B1. Estimate independent components using the minimum description length criterion; B2, using a two-step principal component analysis method to reduce the dimensionality of the functional magnetic resonance imaging data used for data analysis; B3, using the ICASSO algorithm to repeat the calculation 100 times on the independent components obtained by the minimum description length standard estimation and dimensionality reduction processing in steps B1 and B2 to obtain stable independent components; B4. Use stable independent components to reconstruct the time series and spatial distribution of each independent component of each patient; B5. Identify the spatial distribution of the reconstructed independent components and identify the network components therein; B6. From the identified network components, extract the average functional connectivity values ​​within the brain networks with significant differences in Parkinson's disease patients, as well as the functional connectivity between brain networks.

[0023] In the present invention, independent components refer to the independent time series and spatial distribution patterns of different brain networks separated from functional magnetic resonance imaging data by independent component analysis. The purpose of analyzing independent components is to extract independent functional networks from complex functional magnetic resonance imaging data to help understand brain activity at rest. The purpose of analyzing brain network functional connectivity is to explore the interactions within and between different brain networks, reveal the functional connectivity patterns of the brain in healthy and diseased states, and is of great significance to the study of neurological diseases such as Parkinson's disease.

[0024] In the present invention, the purpose of step B1 is to determine the number of independent components and ensure the accuracy of the model.

[0025] The purpose of step B2 is to reduce the dimensionality of high-dimensional data, reduce noise and extract representative data information.

[0026] The purpose of step B3 is to verify the stability of independent components through repeated operations and ensure the reliability of the analysis results.

[0027] The purpose of step B4 is to reconstruct the brain activity pattern of each patient and obtain the time series and spatial distribution of independent components.

[0028] The purpose of step B5 is to identify and analyze the spatial distribution of independent components and reveal the functional distribution of different brain networks.

[0029] The purpose of step B6 is to extract brain network connections with significant differences in Parkinson's disease patients and study the impact of Parkinson's disease on brain functional connections.

[0030] Preferably, step B6 includes: performing a one-sample t-test on each network with age, gender and education level as covariates, determining specific brain regions significantly associated with each network, with significance thresholds of voxel-based p1<0.001 and cluster-based p2<0.05, extracting the mean values ​​of functional connectivity within brain networks with significant differences in the Parkinson's disease patient group, as well as the functional connectivity between brain networks; wherein p is statistical significance.

[0031] In the present invention, p is used to measure the probability of an observed result occurring under random circumstances, and is used here to detect whether the differences in certain brain network connections reach a statistically significant level.

[0032] Preferably, the brain networks among the independent components identified by the independent component analysis of the data analysis module include: sensorimotor network, cerebellar network, anterior default mode network, posterior default mode network, medial visual network, lateral visual network, left frontoparietal network, right frontoparietal network, dorsal attention network, auditory network and salience network.

[0033] 5. Relevance Assessment Module Preferably, the correlation evaluation module includes statistical data analysis software, and the statistical data analysis software evaluates the correlation between brain network functional connectivity and walking speed of Parkinson's disease patients by: The extracted intra-brain network and inter-brain network functional connections were correlated with gait speed to evaluate the correlation between brain network functional connections and gait speed in Parkinson's disease patients.

[0034] Preferably, the correlation assessment module is also used to compare the functional connections of brain networks in Parkinson's disease patients and healthy controls, including: compared with healthy controls, the functional connections within the medial visual network and cerebellar network in Parkinson's disease patients are reduced; the functional connections between the lateral visual network and the sensorimotor network, and between the posterior default mode network and the salience network are all reduced, and the functional connection between the cerebellar network and the sensorimotor network / left frontoparietal network is increased.

[0035] Preferably, the correlation evaluation module is also used to compare the functional connections of brain networks between the low gait speed subgroup and the high gait speed subgroup of Parkinson's disease patients, including: compared with the high gait speed subgroup of Parkinson's disease patients, the low gait speed subgroup of Parkinson's disease patients has increased functional connectivity within the sensorimotor network, increased functional connectivity between the sensorimotor network and the left fronto-parietal network, and decreased functional connectivity between the medial visual network and the anterior default mode network.

[0036] Preferably, the correlation evaluation module evaluates the correlation between the brain network functional connectivity and the walking speed of Parkinson's disease patients, including: the functional connectivity within the cerebellar network is negatively correlated with the walking speed, and the functional connectivity between the cerebellar network and the sensorimotor network is positively correlated with the walking speed.

[0037] In the present invention, the functional connectivity within the brain network refers to the functional connectivity within the network represented by each independent component extracted by independent component analysis.

[0038] Functional connectivity between brain networks refers to the functional connectivity between different brain networks represented by independent components extracted through independent component analysis.

[0039] The purpose of correlation analysis between functional connectivity within and between brain networks and gait speed is to explore the relationship between these functional connectivity patterns and the patient's motor function. The results of the correlation analysis can reveal which brain regions or networks are associated with motor symptoms (such as gait disorders), thereby providing a basis for understanding the disease mechanism and clinical intervention.

[0040] In the present invention, in order to evaluate the correlation between walking speed and brain network functional connectivity, the extracted functional connectivity within and between brain networks is analyzed for correlation with the patient's walking speed. The degree of association between the brain functional network and walking speed is evaluated by calculating the Pearson correlation coefficient between the functional connectivity strength and walking speed. This analysis will help reveal which brain network functional connectivity strength is associated with the patient's motor function (walking speed) and identify the significant correlation between walking speed and brain network functional connectivity.

[0041] Beneficial effects of the present invention: The present invention evaluates the correlation between brain network functional connectivity and gait speed of Parkinson's patients based on functional magnetic resonance imaging and gait speed of Parkinson's patients, and can more accurately observe the specific brain network functional activity patterns and regions related to abnormal gait speed of Parkinson's patients, and further clarify the pathophysiological changes of Parkinson's patients. Subsequently, such as testing and intervention of relevant positions, it can help monitor the patient's condition and improve symptoms.

[0042] The system for evaluating the correlation between brain network functional connectivity and gait speed of Parkinson's disease patients provided by the present invention is beneficial for relevant medical personnel to use the system to evaluate the correlation between brain network functional connectivity and gait speed parameters of Parkinson's disease patients, thereby exploring the neural mechanism of Parkinson's disease and providing functional imaging evidence for clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a system for evaluating the correlation between brain network functional connectivity and walking speed in patients with Parkinson's disease according to the present invention; Figure 2 is a resting-state brain network determined by independent component analysis in an embodiment of the present invention; wherein SMN is a sensorimotor network, mVN is a medial visual network, DAN is a dorsal attention network, CN is a cerebellar network, IVN is a lateral visual network, AUN is an auditory network, aDMN is an anterior default mode network, IFPN is a left frontoparietal network, SN is a salience network, pDMN is a posterior default mode network, and rFPN is a right frontoparietal network; Figure 3 It is a schematic diagram of the results of the correlation analysis between the functional connectivity within the brain network and the walking speed of the present invention; the abscissa represents the walking speed characteristics (meters / second), and the ordinate represents the functional connectivity within the cerebellar network; Figure 4 This is a schematic diagram of the analysis results of the correlation between the functional connectivity between brain networks and the walking speed of the present invention; the abscissa represents the walking speed characteristics (meters / second), and the ordinate represents the functional connectivity between the cerebellar network and the sensorimotor network; Among them, p is the statistical significance (p-value), which is used here to judge the statistical significance of the correlation results; the r value (Pearson correlation coefficient) is used to measure the linear relationship between two variables. DETAILED DESCRIPTION

[0044] The concept, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and drawings to fully understand the purpose, characteristics and effects of the present invention.

[0045] Example 1 A system for evaluating the correlation between brain network functional connectivity and gait speed in patients with Parkinson's disease, such as Figure 1 As shown, including: Data collection module, used to collect data of Parkinson's disease patients; A data acquisition module, connected to the data collection module, for sequentially acquiring the gait parameter data and functional magnetic resonance imaging data of the Parkinson's disease patient according to the Parkinson's disease patient data; A data preprocessing module, connected to the data acquisition module, for preprocessing functional magnetic resonance imaging data; A data analysis module, connected to the data preprocessing module, for sequentially performing independent component analysis and brain network functional connectivity analysis on the preprocessed functional magnetic resonance imaging data; The correlation evaluation module is connected to the data acquisition module and the data analysis module respectively, and uses the brain network functional connection analysis data and the walking speed parameter data to evaluate the correlation between the brain network functional connection and the walking speed of Parkinson's disease patients.

[0046] In this embodiment, the data collection module, data acquisition module, data preprocessing module, data analysis module and correlation evaluation module can all be executed using computers and other devices, so the system of the present invention can be applied in industry.

[0047] For example, the data collection module can use the electronic medical record system to collect Parkinson's disease patient data; the data acquisition module can use the motor function quantitative assessment system and the MRI scanner; the data preprocessing module can use the DPABI in Matlab R2022b; the data analysis module can use the GIFT toolbox and SPM12; and the correlation evaluation module can use SPSS 24.0 software.

[0048] Example 2 This embodiment further explains the data collection module based on the embodiment 1.

[0049] In this embodiment, the data collection module can use the patient electronic medical record system in the computer, which collects the patient's data, including: the age, gender, education level, course of disease, Parkinson's disease motor function score and medication of the Parkinson's disease patient, and the data of healthy controls matching the age, gender and education level of the Parkinson's disease patient. The data collection module is connected to the data acquisition module, and the data collected by it is used for subsequent use.

[0050] Example 3 This embodiment further explains the data acquisition module based on the embodiment 2.

[0051] The data acquisition module includes a motor function quantitative evaluation system and a nuclear magnetic resonance imaging scanner. The motor function quantitative evaluation system collects walking speed parameter data of Parkinson's patients, and the nuclear magnetic resonance imaging scanner collects resting functional magnetic resonance imaging data of Parkinson's patients.

[0052] Objective gait speed measurement was performed using the ReadyGo motor function quantitative assessment system (Beijing Zhongke Ruiyi Information Technology Co., Ltd.). The system uses red, green, and blue cameras and depth cameras to capture three-dimensional motion, and combines deep learning algorithms to locate skeletal points. By simultaneously tracking multiple skeletons, visual perception accurately estimates 3D joints and landmarks. In the gait test, each participant performed a practice trial before the actual test, and then walked along a 3-meter corridor at a daily pace.

[0053] For further analysis, half of the PD patients were divided into a low gait speed subgroup and the other half into a high gait speed subgroup according to the median gait speed of all PD patients.

[0054] All MRI scans were performed using an identical 3.0 Tesla MRI scanner (Magnetom Skyra; Siemens Healthineers, Erlangen, Germany) equipped with a 32-channel head coil. High-resolution three-dimensional T1-weighted sequence parameters were: repetition time (TR) = 2300 ms, echo time (TE) = 2.01 ms, flip angle (FA) = 8°, field of view (FOV) = 256 × 256 cm 2 , matrix size = 256 × 256, number of slices = 192, slice thickness = 1 mm, voxel size = 1.0 × 1.0 × 1.0 mm 3 .

[0055] The rs-fMRI data used an echo planar imaging sequence with parameters of TR = 2000 ms, TE = 30 ms, FA = 90°, and FOV = 224 × 224 mm. 2 , matrix size = 64 × 64, number of slices = 36, slice thickness = 3.5 mm, slice gap = 0.7 mm, voxel size = 3.5 × 3.5 × 3.5 mm 3 Foam pads were used to reduce head movement during the scans, and earplugs were provided to reduce noise during the examination. Participants were asked to close their eyes and lie comfortably in their back.

[0056] Example 4 This embodiment further describes the data preprocessing module based on the embodiment 3.

[0057] The rs-fMRI data were preprocessed using DPABI in Matlab R2022b. The preprocessing steps included: A1. Delete the first 10 time points of each subject's functional magnetic resonance imaging data; A2, performing time layer correction on the functional magnetic resonance imaging data after deleting the first 10 time points, and aligning the time axis of the functional magnetic resonance imaging data; A3. Perform head motion correction on the time-layer corrected functional magnetic resonance imaging data, expand the head motion parameter limit to a maximum displacement of <2 mm in the x, y or z plane, and an angular rotation of <2° on each axis, and obtain the average functional image data; A4. The T1 structural image was co-registered to the motion-corrected average functional image data. The functional image was then normalized from the individual original space to the Montreal Neurological Institute space and sampled into 3 × 3 × 3 mm 3 ; A5. Use a 6-mm full-width half-maximum Gaussian kernel to spatially smooth the sampled data to obtain functional magnetic resonance imaging data for data analysis.

[0058] Example 5 This embodiment further explains the data analysis module based on the embodiment 4.

[0059] The preprocessed rs-fMRI data were subjected to independent component analysis and brain network functional connectivity analysis using the GIFT toolbox. The independent component analysis steps included: estimating independent components using the minimum description length criterion (the number of independent components estimated in this example was 37); reducing the dimension of the data using principal component analysis; repeating the operation of the obtained components 100 times using the ICASSO algorithm; and reconstructing the time series and spatial distribution of each independent component of each patient based on the data components and the dimensionality reduction results. Finally, 11 independent components were selected based on spatial correlation and visual detection. The functional connectivity within each brain network was evaluated by analyzing the reconstructed spatial z-map. With age, gender, and education level as covariates, a single-sample t-test was performed on each network using SPM12 to identify specific brain regions significantly associated with each network, with a significance threshold of voxel-based p1<0.001 and cluster-based p2<0.05 (FWE correction). The mean values ​​of functional connectivity within the significantly different brain networks in the PD group and the functional connectivity between brain networks were extracted.

[0060] Example 6 This embodiment further describes the correlation evaluation module based on Embodiment 5.

[0061] SPSS 24.0 software was used to analyze the clinical data and gait speed of the subjects, and Pearson correlation analysis was used to evaluate the relationship between functional connectivity and gait speed within and between networks. All tests were two-tailed, and p < 0.05 was considered significant.

[0062] Among the 42 PD patients, the average age of the low gait speed subgroup was 51.81 years, the average disease duration was 3.52 years, and the average age of the high gait speed subgroup was 52.05 years, the average disease duration was 2.62 years. Compared with the healthy population, the gait speed of both groups of PD patients decreased significantly.

[0063] The 11 independent components screened out specifically include sensorimotor network, cerebellar network, anterior default mode network, posterior default mode network, medial visual network, lateral visual network, left frontoparietal network, right frontoparietal network, dorsal attention network, auditory network and salience network, such as Figure 2 shown.

[0064] Compared with healthy controls, PD patients showed significantly reduced functional connectivity within the medial visual network and cerebellar network; reduced functional connectivity between the lateral visual network and the sensorimotor network, and between the posterior default mode network and the salience network, while increased functional connectivity between the cerebellar network and the sensorimotor network / left frontoparietal network. Compared with the high-gait PD subgroup, the low-gait PD subgroup showed increased functional connectivity within the sensorimotor network, increased functional connectivity between the sensorimotor network and the left frontoparietal network, and decreased functional connectivity between the medial visual network and the anterior default mode network.

[0065] The results of correlation analysis showed that the functional connectivity within the cerebellar network was negatively correlated with gait speed, such as Figure 3 As shown in Figure 2, the functional connectivity between the cerebellar network and the sensorimotor network is positively correlated with walking speed. Figure 4 This result further deepens the understanding of the role of the cerebellum in gait disorders in PD patients and supports that targeting the cerebellar network and sensorimotor network pathways may help improve gait disorders in PD patients.

[0066] The above is a specific description of the implementation mode of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention, and these equivalents or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A system for evaluating the correlation between brain network functional connectivity and gait speed in patients with Parkinson's disease, characterized in that: include: Data collection module, used to collect data of Parkinson's disease patients; A data acquisition module, connected to the data collection module, for sequentially acquiring the gait parameter data and functional magnetic resonance imaging data of the Parkinson's disease patient according to the Parkinson's disease patient data; A data preprocessing module, connected to the data acquisition module, for preprocessing functional magnetic resonance imaging data; A data analysis module, connected to the data preprocessing module, for sequentially performing independent component analysis and brain network functional connectivity analysis on the preprocessed functional magnetic resonance imaging data; The correlation evaluation module is connected to the data acquisition module and the data analysis module respectively, and uses the brain network functional connection analysis data and the walking speed parameter data to evaluate the correlation between the brain network functional connection and the walking speed of Parkinson's disease patients, including: the functional connection within the cerebellar network is negatively correlated with the walking speed, and the functional connection between the cerebellar network and the sensorimotor network is positively correlated with the walking speed.

2. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 1, characterized in that: The data acquisition module includes a motor function quantitative evaluation system and a nuclear magnetic resonance imaging scanner. The motor function quantitative evaluation system collects walking speed parameter data of Parkinson's patients, and the nuclear magnetic resonance imaging scanner collects resting functional magnetic resonance imaging data of Parkinson's patients.

3. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 2, characterized in that: The motor function quantitative assessment system includes a red, green, and blue camera, a depth camera, and a processing terminal; the red, green, and blue camera and the depth camera are connected to the processing terminal, the red, green, and blue camera and the depth camera collect three-dimensional motion image data of the subject, and send the collected three-dimensional motion image data to the processing terminal, the processing terminal combines a deep learning algorithm to locate the bone points, and simultaneously tracks multiple bones, visually perceives and estimates 3D joints and landmarks, and calculates the subject's walking speed parameter data; The motor function quantitative assessment system collects data from Parkinson's disease patients, including low gait speed subgroup and high gait speed subgroup.

4. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 2, characterized in that: The MRI scanner was equipped with a 32-channel head coil, and the parameters of the three-dimensional T1-weighted sequence were as follows: repetition time = 2300 ms, echo time = 2.01 ms, flip angle = 8°, and field of view = 256 × 256 cm 2 , matrix size = 256 × 256, number of slices = 192, slice thickness = 1 mm, voxel size = 1.0 × 1.0 × 1.0 mm 3 ; Functional magnetic resonance imaging data used an echo planar imaging sequence with the following parameters: repetition time = 2000 ms, echo time = 30 ms, flip angle = 90°, field of view = 224 × 224 mm 2 , matrix size = 64 × 64, number of slices = 36, slice thickness = 3.5 mm, slice gap = 0.7 mm, voxel size = 3.5 × 3.5 × 3.5 mm 3 .

5. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 1, characterized in that: The data preprocessing module includes data preprocessing software, and the data preprocessing software preprocesses the functional magnetic resonance imaging data including the following steps: A1. Delete the first 10 time points of each subject's functional magnetic resonance imaging data; A2, performing time layer correction on the functional magnetic resonance imaging data after deleting the first 10 time points, and aligning the time axis of the functional magnetic resonance imaging data; A3. Perform head motion correction on the time-layer corrected functional magnetic resonance imaging data, expand the head motion parameter limit to a maximum displacement of < 2 mm in the x, y or z plane, and an angular rotation of < 2° on each axis, and obtain the average functional image data; A4. The T1 structural image was co-registered to the average functional image data after head motion correction. The functional image was then standardized from the individual original space to the Montreal Neurological Institute space and sampled into 3×3×3 mm 3 ; A5. Use a 6-mm full-width half-maximum Gaussian kernel to spatially smooth the sampled data to obtain functional magnetic resonance imaging data for data analysis.

6. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 1, characterized in that: The brain network functional connectivity analysis of the data analysis module includes intra-brain network and inter-brain network functional connectivity analysis; The data analysis module includes a brain functional magnetic resonance imaging tool, and the brain functional magnetic resonance imaging tool performs independent component analysis and brain network functional connection analysis on the pre-processed functional magnetic resonance imaging data, including the following steps: B1. Estimate independent components using the minimum description length criterion; B2, using a two-step principal component analysis method to reduce the dimensionality of the functional magnetic resonance imaging data used for data analysis; B3, using the ICASSO algorithm to repeat the calculation 100 times on the independent components obtained by the minimum description length standard estimation and dimensionality reduction processing in steps B1 and B2 to obtain stable independent components; B4. Use stable independent components to reconstruct the time series and spatial distribution of each independent component of each patient; B5. Identify the spatial distribution of the reconstructed independent components and identify the network components therein; B6. From the identified network components, extract the average functional connectivity values ​​within the brain networks with significant differences in Parkinson's disease patients, as well as the functional connectivity between brain networks.

7. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 6, characterized in that: Step B6 includes: using age, gender and education level as covariates, performing a one-sample t-test on each network to determine the specific brain regions significantly associated with each network, with a significance threshold of voxel-based p1 < 0.001 and cluster-based p2 < 0.05, extracting the mean functional connectivity values ​​within the significantly different brain networks in the Parkinson's disease patient group, as well as the functional connectivity between brain networks; where p is statistical significance.

8. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 1, characterized in that: The brain networks in the independent components identified by the independent component analysis of the data analysis module include: sensorimotor network, cerebellar network, anterior default mode network, posterior default mode network, medial visual network, lateral visual network, left frontoparietal network, right frontoparietal network, dorsal attention network, auditory network and salience network.

9. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 1, characterized in that: The correlation evaluation module includes statistical data analysis software, and the statistical data analysis software evaluates the correlation between brain network functional connectivity and walking speed of Parkinson's disease patients including: The extracted intra-brain network and inter-brain network functional connections were correlated with gait speed to evaluate the correlation between brain network functional connections and gait speed in Parkinson's disease patients.

10. The system for evaluating the correlation between brain network functional connectivity and walking speed of patients with Parkinson's disease as claimed in claim 8, characterized in that: The correlation assessment module was also used to compare the functional connectivity of brain networks in Parkinson's disease patients and healthy controls, including: compared with healthy controls, Parkinson's disease patients had reduced functional connectivity within the medial visual network and cerebellar network; reduced functional connectivity between the lateral visual network and the sensorimotor network, and between the posterior default mode network and the salience network, and increased functional connectivity between the cerebellar network and the sensorimotor network / left frontoparietal network; The correlation assessment module was also used to compare the functional connectivity of brain networks between the low gait speed subgroup and the high gait speed subgroup of Parkinson's disease patients, including: compared with the high gait speed subgroup of Parkinson's disease patients, the low gait speed subgroup of Parkinson's disease patients had increased functional connectivity within the sensorimotor network, increased functional connectivity between the sensorimotor network and the left frontoparietal network, and decreased functional connectivity between the medial visual network and the anterior default mode network.

Images