A method and system for analyzing flight training quality based on brain magnetic resonance imaging

Abstract

The present application relates to the technical field of physiological signal recognition, and particularly relates to a flight training quality analysis method and system based on brain magnetic resonance imaging. The method collects fMRI data before and after the flight training of students, defines the brain functional areas dACC and PoCG_L, accurately extracts the BOLD signal time sequence corresponding to the functional areas, simultaneously performs resting state functional connection analysis on the BOLD signal time sequence of the two key brain areas before and after the training by using the Pearson correlation coefficient, obtains a high-credibility connection strength difference value, and then outputs an individualized training quality score through neural-behavioral joint modeling, forms a structured evaluation report, realizes the change of the training quality evaluation from experience judgment to data driving and mechanism support, enhances the objectivity and scientificity of the system, and compared with the traditional subjective scoring system, the index has the advantages of physiological interpretability and strong repeatability, and can accurately analyze the flight training quality of students.

Description

Technical Field

[0001] This invention relates to the field of physiological signal recognition technology, and in particular to a method and system for analyzing flight training quality based on brain magnetic resonance imaging. Background Technology

[0002] Flight is a complex mission with high time pressure and cognitive load, requiring pilots to continuously monitor and make real-time decisions in rapidly changing cockpit and external environments. Because operational errors in flight can have serious consequences, this profession demands far higher operational precision and cognitive response than most other occupations. With the increasing complexity of flight missions and the rising information density of the modern aviation environment, the quality of pilot training is becoming increasingly crucial for ensuring flight safety and improving mission execution efficiency.

[0003] Currently, the assessment of flight training quality mainly relies on methods such as manual scoring, behavioral performance rating, and flight data statistics. However, these methods suffer from certain drawbacks in practical application, including high subjectivity, inconsistent standards, and a lack of physiological basis. For example, manual evaluation is often limited by the assessor's experience and subjective judgment, making it difficult to accurately capture the internal states of pilots during training, such as attention allocation, changes in cognitive load, and neural function regulation. These traditional assessment methods cannot comprehensively and objectively reflect the changes in brain function induced by individual flight training, thus limiting the accuracy of training feedback and the targeted nature of improvement measures.

[0004] In recent years, functional magnetic resonance imaging (fMRI) has been widely used in cognitive science and skill learning research. fMRI is a non-invasive imaging technique that indirectly reflects brain activity based on changes in blood oxygen levels. It is suitable for analyzing the functional connectivity of brain regions after a specific task or training. In particular, "resting-state functional connectivity" analysis (i.e., the consistency of activity between different brain regions when a person is resting quietly and not performing a task) is widely used to detect plasticity changes in brain network structure after training. Neuroscience research has found that the strength of functional connectivity between different brain regions can serve as an indicator of adaptive changes in the nervous system, reflecting how the brain optimizes resource allocation during a specific task training process. The anterior cingulate cortex (ACC) plays a crucial role in maintaining alertness and resolving conflict under high cognitive load. Neuroimaging evidence suggests that it participates in conflict monitoring during information processing and signals other control centers (such as the prefrontal cortex) to implement behavioral adjustments. In particular, the dorsal anterior cingulate cortex (dACC) has specialized functions in high-conflict aviation operations under high uncertainty or high-risk decision-making situations. The dACC is specifically used to detect response conflicts, update action plans under uncertainty, and switch between manual and automated processing—mechanisms directly related to flight. The left postcentral gyrus (PoCG_L), as an important component of the sensorimotor cortex, is primarily responsible for somatosensory information processing and motor execution regulation. Existing research indicates that after long-term flight training, the resting-state functional connectivity between the dACC and PoCG_L regions typically decreases. This "functional decoupling" phenomenon suggests that as flight skills become more proficient, the brain no longer relies on high-intensity cross-regional coordination but shifts to a more efficient automated processing mode; this change can be seen as an improvement in neural efficiency.

[0005] However, existing research is mostly qualitative, lacking a complete technical system for quantitative modeling based on changes in functional connectivity strength and for reverse evaluation of flight training quality. Especially in the absence of pre- and post-training imaging comparisons, it is impossible to determine whether changes in connectivity strength originate from flight training, resulting in weak traceability and interpretability of the evaluation. Therefore, there is an urgent need for a method and system that can quantify changes in brain functional connectivity and combine training duration with behavioral performance indicators to establish a training quality scoring model, thereby improving the scientific rigor, objectivity, and individual adaptability of training evaluation. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a method for analyzing flight training quality based on brain magnetic resonance imaging (MRI). By analyzing brain activity data before and after flight training, it extracts changes in functional connectivity across key brain regions and, combined with behavioral performance indicators, establishes a training quality assessment model. The method includes the following steps: S1. By sampling with resting-state functional magnetic resonance imaging, the same trainee was sampled with brain magnetic resonance imaging before and after flight training to obtain the first resting-state imaging data before flight training and the second resting-state imaging data after flight training. S2. The obtained first resting-state imaging data and second resting-state imaging data are corrected and mapped to the space of the Montreal Neuroscience Institute. The first time series matrix of the change of trainee brain voxels over time before flight training and the second time series matrix of the change of trainee voxels over time after flight training are extracted respectively. S3. Based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix respectively, and construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix respectively. S4. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, the resting-state functional connectivity strength of the BOLD signal between the dACC brain region and the PoCG_L brain region before and after flight training is calculated using the Pearson correlation coefficient algorithm, and the difference in resting-state functional connectivity strength before and after flight training is obtained. S5. Using the difference in resting-state functional connectivity before and after flight training, along with flight training duration and quantitative indicators of flight training performance, as variables, construct a linear model to evaluate training effectiveness and output the results of student flight training quality analysis.

[0007] Furthermore, step S2 includes the following steps: S201. Perform data correction on the first imaging data and the second imaging data respectively. The data correction includes: magnetization balance processing, slice time correction and head motion correction, in order to eliminate physical and motion artifacts. S202. Map the corrected first imaging data and the second imaging data to the unified Montreal Institute for Neuroscience space, that is, the unified brain template coordinate system (MNI space), to ensure that the data before and after training are comparable; S203. Perform interference variable regression processing on the spatial data of the Montreal Institute of Neuroscience using a Gaussian kernel function to remove non-neural source signal interference, including white matter signals, cerebrospinal fluid signals and Friston-24 head motion parameter signals constructed based on a rigid body motion model; S204. The spatial data of the Montreal Neuroscience Institute after regression processing of interference variables is transformed into two-dimensional structured data, and the first time series matrix of the changes of trainees' brain voxels over time before flight training and the second time series matrix of the changes of trainees' voxels over time after flight training are extracted respectively.

[0008] Furthermore, step S3 includes the following steps: S301. Based on the standard brain atlas, the dACC and PoCG_L regions are defined as region sets respectively, and the coordinates of the dACC brain region and the PoCG_L brain region are obtained; S302. Based on the dACC brain region coordinates and the PoCG_L brain region coordinates, extract the average BOLD signal time series in the dACC brain region and the PoCG_L brain region from the first time series matrix and the second time series matrix, respectively. S303. Based on the obtained average BOLD signal time series, construct the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix respectively, and calculate the connectivity strength for subsequent comparison before and after training.

[0009] Furthermore, step S4 includes the following steps: S401. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, the mean and standard deviation of the BOLD signal time series of the dACC brain region and the PoCG_L brain region in the connectivity matrix are respectively normalized to zero. S402. Using the Pearson correlation coefficient method, calculate the functional link strengths of the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix respectively, and obtain the first functional link strength and the second functional link strength. The calculation formula is as follows:

[0010] Where FC represents the functional connectivity strength, n is the total length of the BOLD signal time series, and t is the time point index of the BOLD signal time series. Let be the standardized mean of the BOLD signal in the dACC brain region at time t. The normalized mean of the BOLD signal in the PoCG_L brain region at time t; S403. Based on the calculated first functional link strength and second functional link strength, calculate the difference in resting-state functional link strength before and after training.

[0011] Furthermore, step S5 includes the following steps: S501. Collect behavioral parameters to obtain the total flight training time (Ttotal) and pre-determined quantitative indicators of flight training performance, including behavioral performance data such as operational scores (Pscore). S502. Based on the difference in resting-state functional connectivity strength before and after training, construct a linear regression model of training volume, expressed as:

[0012]

[0013] Where Q is the flight training quality assessment value, For learnable parameters representing resting-state functional connectivity poorness, The resting state functional connectivity is poor. For the first functional link strength, For the second functional link strength, Learnable parameters for flight training duration. For the duration of flight training for trainees, To train learnable parameters for performance quantification metrics, Quantify trainees’ training performance with b as the paranoia parameter; S503. Based on the linear regression model of training volume, calculate the flight training quality assessment value of the trainees, and use it as the result of the flight training quality analysis.

[0014] A flight training quality analysis system based on brain magnetic resonance imaging, the system being implemented based on any one of the aforementioned flight training quality analysis methods based on brain magnetic resonance imaging, comprising: The magnetic resonance data acquisition module is used to perform brain magnetic resonance imaging sampling on trainees before and after flight training through functional magnetic resonance imaging sampling. The magnetic resonance data preprocessing module is used to preprocess the imaging data and normalize it to the Montreal Neuroscience Institute space, generating a first time series matrix and a second time series matrix, respectively. The brain region time series extraction module is used to extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix, respectively, based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, and to construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix, respectively. The functional connectivity analysis module is used to calculate the resting-state functional connectivity strength before and after training based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, and to obtain the difference in resting-state functional connectivity strength before and after training. The quality analysis module is used to perform joint modeling based on the difference in resting-state functional linkage strength before and after training, combined with the academy's flight training duration and training performance indicators. This involves linear regression analysis based on multiple variables to output flight training quality analysis results.

[0015] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the flight training quality analysis method based on brain magnetic resonance imaging as described above.

[0016] A storage medium storing a computer program, which, when executed by a processor, implements the flight training quality analysis method based on brain magnetic resonance imaging as described above.

[0017] The beneficial effects of this invention are as follows: by collecting fMRI data before and after flight training and performing rigorous preprocessing, data quality and cross-sample consistency are effectively improved. By precisely defining brain functional areas (dACC and PoCG_L) and accurately extracting the corresponding BOLD signal time series, precise focusing and quantification of training-related brain regions are achieved. Simultaneously, Pearson correlation coefficients are used to perform resting-state functional connectivity analysis on the BOLD signal time series of two key brain regions before and after training, obtaining highly reliable connectivity strength differences. This enables quantitative characterization of neural functional remodeling induced by flight training. Furthermore, individualized training quality scores are output through neuro-behavioral joint modeling, generating structured evaluation reports that can be used for pilot training result archiving and optimizing training intensity or content. This represents a shift in training quality assessment from experience-based judgment to data-driven, mechanism-supported methods, enhancing the objectivity and scientific rigor of the system. Compared to traditional subjective scoring systems, this indicator has the advantages of strong physiological interpretability and repeatability, enabling accurate analysis of trainees' flight training quality. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of a flight training quality analysis method based on brain magnetic resonance imaging according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of a flight training quality analysis system based on brain magnetic resonance imaging according to an embodiment of the present invention.

[0020] Figure 3 This is a diagram showing the calculation results of the resting state functional connection between dACC and PoCG_L in an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of a terminal device for flight training quality analysis based on magnetic resonance imaging, according to an embodiment of the present invention.

[0022] Figure 5 This is a schematic diagram of a computer-readable storage medium structure for a flight training quality analysis method based on brain magnetic resonance imaging according to an embodiment of the present invention.

[0023] In the diagram, 200 is the terminal device, 210 is the memory, 211 is the RAM, 212 is the cache memory, 213 is the ROM, 214 is the program / utility, 215 is the program module, 220 is the processor, 230 is the bus, 240 is the external device, 250 is the I / O interface, 260 is the network adapter, and 300 is the program product. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention; that is, the described embodiments are only a part of the embodiments of the invention, and not all of them. The components of the embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention. It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0026] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or machine that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or machine. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or machine that includes said element.

[0027] In the embodiments, “functional magnetic resonance imaging (fMRI)” refers to a non-invasive imaging method that indirectly reflects the activity intensity of different brain regions by monitoring changes in blood oxygen levels (i.e., BOLD signal, blood oxygen-dependent signal), and is used to observe changes in neural function induced by training or tasks. The “time series matrix” mentioned in the embodiment refers to the format of brain image data extracted from fMRI scans after preprocessing. This matrix reflects the signal change trajectory of a specific brain region throughout the scanning process and is the basic data structure for functional connectivity analysis. "Standard brain atlases" (such as the MNI space) are internationally recognized brain template coordinate systems used to ensure spatial consistency of brain region data among different subjects; "Functional connectivity strength" is usually calculated using the Pearson correlation coefficient to measure the similarity between BOLD signals in two brain regions. The higher the value, the more synchronized the activities between the two regions are, indicating that they may cooperate in performing certain functions.

[0028] Therefore, the embodiments of the present invention shown below in conjunction with the accompanying drawings are merely one specific form of the technical solution of the present invention, and not a limitation on the scope of protection. Equivalent adjustments to the structure, steps, or data processing methods without departing from the core idea of ​​the present invention should be included within the scope of protection of the present invention.

[0029] Example 1: like Figure 1 As shown, Embodiment 1 of the present invention provides a method for analyzing flight training quality based on brain magnetic resonance imaging, including the following steps: S1. First imaging data is obtained by performing brain MRI sampling on trainees before flight training through functional magnetic resonance imaging (fMRI); second imaging data is obtained by performing brain MRI sampling on trainees after flight training through fMRI sampling. S2. The first imaging data and the second imaging data are preprocessed and normalized to the Montreal Neuroscience Institute space to generate the first time series matrix and the second time series matrix, respectively. Furthermore, step S2 includes the following steps: S201. Perform data correction based on the first imaging data and the second imaging data respectively; S202. Spatial registration is performed on the corrected imaging data, and the data is normalized to the space of the Montreal Neuroscience Institute. S203. Regression of the Montreal Neuroscience Institute space using a Gaussian kernel function to handle interference variables; S204. Based on the Montreal Neuroscience Institute space after regression processing of interference variables, extract the time series of the first imaging data and the second imaging data respectively, and construct the first time series matrix and the second time series matrix; Specifically, the data correction includes magnetization balance correction, interlayer time correction, and rigid body motion correction; the interference variables include: white matter signal, cerebrospinal fluid signal, and Friston 24 motion parameters.

[0030] Specifically, MRI preprocessing was performed using RESTplus software. The first 10 functional time points (volumes) were discarded to allow magnetization to reach equilibrium. Interslice time correction was performed to address staggered acquisition issues (35 slices; reference slice: slice 35; TR = 2 s), followed by rigid body motion correction to compensate for head movement. Participants with translational displacement exceeding 2 mm or rotational displacement exceeding 2° were excluded. Structural T1-weighted images were segmented into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). Functional images were registered with the GM template and normalized to the Montreal Neurological Institute (MNI) space (bounding box: [-90, -126, -72; 90, 90, 108]; voxel size: 3 × 3 × 3 mm³). Spatial smoothing was performed using a 6 mm full width at half height (FWHM) Gaussian kernel. Temporal preprocessing included linear detrending and bandpass filtering (0.01–0.08 Hz), followed by perturbation regression to remove the effects of WM, CSF, and 24 Friston head motion parameters.

[0031] S3. Based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix respectively, and construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix respectively. Specifically, step S3 includes the following steps: S301. Based on the standard brain atlas, the dACC and PoCG_L regions are defined as region sets respectively, and the coordinates of the dACC brain region and the PoCG_L brain region are obtained; S302. Based on the dACC brain region coordinates and the PoCG_L brain region coordinates, extract the average BOLD signal time series in the dACC brain region and the PoCG_L brain region from the first time series matrix and the second time series matrix, respectively. S303. Based on the obtained average BOLD signal time series, construct the first resting-state functional connection matrix and the second resting-state functional connection matrix respectively.

[0032] S4. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, calculate the resting-state functional connectivity strength before and after training, and obtain the difference in resting-state functional connectivity strength before and after training; Specifically, step S4 includes the following steps: S401. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, the time series of BOLD signals in the dACC brain region and the PoCG_L brain region in the connectivity matrix are mean-reduced and standardized respectively; S402. Using the Pearson correlation coefficient method, calculate the functional link strengths of the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix respectively, and obtain the first functional link strength and the second functional link strength. The calculation formula is as follows:

[0033] Where FC represents the functional connectivity strength, n is the total length of the BOLD signal time series, and t is the time point index of the BOLD signal time series. The normalized mean of the BOLD signal time series in the dACC brain region. The time-series normalized average of the BOLD signal in the PoCG_L brain region; S403. Based on the calculated first functional link strength and second functional link strength, calculate the difference in resting-state functional link strength before and after training.

[0034] S5. Based on the difference in resting-state functional linkage strength before and after training, and combined with the academy's flight training duration and training performance indicators, a joint model is constructed to output the flight training quality analysis results.

[0035] Specifically, step S5 includes the following steps: S501. Obtain the student's flight training duration and pre-determined quantitative indicators of training performance; S502. Based on the difference in resting-state functional connectivity strength before and after training, construct a linear regression model of training volume, expressed as:

[0036]

[0037] Where Q is the flight training quality assessment value, For learnable parameters representing resting-state functional connectivity poorness, The resting state functional connectivity is poor. For the first functional link strength, For the second functional link strength, Learnable parameters for flight training duration. For the duration of flight training for trainees, To train learnable parameters for performance quantification metrics, Quantify trainees’ training performance with b as the paranoia parameter; S503. Based on the linear regression model of training volume, calculate the flight training quality assessment value of the trainees, and use it as the result of the flight training quality analysis.

[0038] Example 2

[0039] like Figure 2As shown, based on Example 1, Example 2 of the present invention proposes a flight training quality analysis system based on brain magnetic resonance imaging, which is implemented based on a method for analyzing flight training quality based on brain magnetic resonance imaging.

[0040] Specifically, the system includes a magnetic resonance data acquisition module, which is used to perform brain magnetic resonance imaging sampling on trainees before and after flight training through functional magnetic resonance imaging sampling. The magnetic resonance data preprocessing module is used to preprocess the imaging data and normalize it to the Montreal Neuroscience Institute space, generating a first time series matrix and a second time series matrix, respectively. The brain region time series extraction module is used to extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix, respectively, based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, and to construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix, respectively. The functional connectivity analysis module is used to calculate the resting-state functional connectivity strength before and after training based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, and to obtain the difference in resting-state functional connectivity strength before and after training. The quality analysis module is used to perform joint modeling based on the difference in resting-state functional linkage strength before and after training, combined with the academy's flight training duration and training performance indicators, and output flight training quality analysis results.

[0041] Specifically, the workflow of this system is as follows: First, magnetic resonance imaging images of the trainee's brain are acquired using the magnetic resonance data acquisition module. Then, the imaging data was preprocessed using RESTplus software through the magnetic resonance data preprocessing module. The structural T1-weighted image was segmented into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). The functional image was registered with the GM template and normalized to the Montreal Neuroscience Institute (MNI) space to generate the first time series matrix and the second time series matrix, respectively. Next, using the brain region time series extraction module, based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, a 5 mm spherical seed region centered at MNI coordinates (-1, 19, 39) is specifically defined. These coordinates represent the spatial method of brain region extraction. The average BOLD signal time series in the dACC brain region and PoCG_L brain region are extracted from the first time series matrix and the second time series matrix, respectively, and the first resting state functional connectivity matrix and the second resting state functional connectivity matrix are constructed. Subsequently, through the functional connectivity analysis module, the resting-state functional connectivity strengths before and after training are calculated based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, and the difference in resting-state functional connectivity strengths before and after training is obtained. Finally, through the quality analysis module, based on the difference in resting-state functional linkage strength before and after training, and combined with the academy's flight training duration and training performance indicators, a joint model is constructed to output the flight training quality analysis results.

[0042] Example 3

[0043] Based on Example 1, there is an application scenario for analyzing the flight training quality of flight trainees. This scenario employs a flight training quality analysis method and system based on brain magnetic resonance imaging, as described in the above examples. Figure 3 This study shows the changes in the functional connectivity between the dACC and PoCG_L brain regions of the same trainee before flight training (sampling time: 2019) and after three years of flight training (sampling time: 2022). To further demonstrate the analytical results, a control group of trainees who would not participate in flight training was also included, and data was collected simultaneously with the trainees who did participate in flight training. The specific implementation method is as follows: Magnetic resonance imaging (MRI) images of the brains of two groups of trainees were acquired using the MRI data acquisition module. High-resolution T1-weighted structural images were acquired using a 3D perturbed gradient echo sequence. Specifically, the repetition time (TR) was 5.976 ms, the echo time (TE) was 1.976 ms, the flip angle was 9°, the field of view (FOV) was 256 × 256 × 154 mm, the matrix size was 256 × 256, 154 slices, and the isotropic voxel size was 1 × 1 × 1 mm. Resting-state fMRI data were acquired using a gradient echo planar imaging sequence: TR = 2,000 ms, TE = 30 ms, flip angle = 90°, FOV = 240 × 240 × 140 mm, matrix = 64 × 64, 35 slices, slice thickness 4 mm (without gaps), and in-plane resolution of 3.75 × 3.75 × 4 mm.

[0044] Each participant completed 255 time points (volumes) during the 8.5-minute scan period; Then, MRI preprocessing was performed using RESTplus software via the MRI data preprocessing module. The first 10 functional time points (volumes) were discarded to allow magnetization to reach equilibrium. Interslice time correction was performed to address staggered acquisition issues (35 slices; reference slice: slice 35; TR = 2 s), followed by rigid body motion correction to correct for head movement. Participants with translational displacement exceeding 2 mm or rotational displacement exceeding 2° were excluded. Structural T1-weighted images were segmented into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). Functional images were registered with the GM template and normalized to the Montreal Neurological Institute (MNI) space (bounding box: [-90, -126, -72; 90, 90, 108]; voxel size: 3 × 3 × 3 mm³). Spatial smoothing was performed using a 6 mm full width at half height (FWHM) Gaussian kernel. Temporal preprocessing included linear detrending and bandpass filtering (0.01–0.08 Hz), followed by perturbation regression to remove the effects of WM, CSF, and 24 Friston head motion parameters.

[0045] Next, using the brain region time series extraction module, based on the anatomically determined coordinates of the dACC and PoCG_L brain regions in the standard brain atlas, a 5 mm spherical seed region centered at MNI coordinates (-1, 19, 39) was defined. This location is considered related to error awareness and conflict resolution in the Error Awareness Task (Orr & Hester, 2012; Ridderinkhof et al., 2004). This coordinate system represents the spatial method of brain region extraction. The average BOLD signal time series in the dACC and PoCG_L brain regions were extracted from the first and second time series matrices, respectively, to construct the first and second resting-state functional connectivity matrices. This voxel-based analysis quantifies the temporal coherence between the seed point and each voxel, reflecting the strength of functional coupling. Time series were extracted from dACC, and correlation analysis was performed using Pearson correlation coefficients with all other voxels. The correlation plots were converted to z-scores by Fisher to improve normality for subsequent group-level analysis.

[0046] Subsequently, using the functional connectivity analysis module, based on the first and second resting-state functional connectivity matrices, the time series of BOLD signals from the dACC and PoCG_L brain regions in the connectivity matrices were mean-reduced and standardized. The functional link strengths of the first and second resting-state functional connectivity matrices were calculated using the Pearson correlation coefficient method, yielding the first and second functional link strengths. Based on the calculated first and second functional link strengths, the difference in resting-state functional connectivity strength before and after training was calculated.

[0047] Finally, the quality analysis module obtains the trainees' flight training duration and pre-determined quantitative indicators of training performance; based on the difference in resting-state functional connectivity before and after training, a linear regression model of training volume is constructed, expressed as: ; Where Q is the flight training quality assessment value, For learnable parameters representing resting-state functional connectivity poorness, The resting state functional connectivity is poor. For the first functional link strength, For the second functional link strength, Learnable parameters for flight training duration. For the duration of flight training for trainees, To train learnable parameters for performance quantification metrics, The training performance of trainees is quantified, and b is the bias parameter. Based on the linear regression model of training volume, the flight training quality assessment value of trainees is calculated and used as the result of flight training quality analysis.

[0048] Example 4

[0049] like Figure 4 As shown in Example 1, Example 3 proposes a terminal device for a flight training quality analysis method based on brain magnetic resonance imaging. The terminal device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0050] The memory 210 may include a readable medium in the form of volatile memory, such as RAM 211 and / or cache memory 212, and may further include ROM 213.

[0051] The memory 210 also stores a computer program that can be executed by the processor 220, causing the processor 220 to execute any of the above-described flight training quality analysis methods based on brain magnetic resonance imaging in the embodiments of this application. The specific implementation method and the achieved technical effects are consistent with those described in the embodiments of the above methods, and some details will not be repeated here. The memory 210 may also include a program / utility 214 having a set (at least one) of program modules 215. Such program modules include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0052] Accordingly, processor 220 can execute the aforementioned computer program, as well as executable program / utility 214.

[0053] Bus 230 can represent one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any of the various bus structures.

[0054] Terminal device 200 can also communicate with one or more external devices 240, such as keyboards, pointing devices, Bluetooth devices, etc., and with one or more devices capable of interacting with it, and / or with any device that enables it to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via I / O interface 250. Furthermore, terminal device 200 can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of terminal device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0055] Example 5

[0056] like Figure 5 As shown, based on Embodiment 1, this embodiment proposes a computer-readable storage medium for a flight training quality analysis method based on brain magnetic resonance imaging. The computer-readable storage medium stores instructions that, when executed by a processor, implement any of the aforementioned flight training quality analysis methods based on brain magnetic resonance imaging. Its specific implementation method is consistent with the implementation methods and achieved technical effects described in the embodiments of the above methods, and some details will not be repeated.

[0057] Figure 5 The present embodiment illustrates a program product 300 for implementing the above-described method, which may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited thereto. In this embodiment, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. The program product 300 may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0058] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0059] This invention is described from the perspectives of its intended use, effectiveness, progress, and novelty. Its practical and progressive features meet the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings are merely preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc., that are similar to or identical to those of this application, i.e., all equivalent substitutions or modifications made in accordance with the scope of this patent application, shall fall within the scope of protection of this patent application.

[0060] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing flight training quality based on brain magnetic resonance imaging, characterized in that, Includes the following steps: S1. By sampling with resting-state functional magnetic resonance imaging, the same trainee was sampled with brain magnetic resonance imaging before and after flight training to obtain the first resting-state imaging data before flight training and the second resting-state imaging data after flight training. S2. The obtained first resting-state imaging data and second resting-state imaging data are corrected and mapped to the space of the Montreal Neuroscience Institute. The first time series matrix of the change of trainee brain voxels over time before flight training and the second time series matrix of the change of trainee voxels over time after flight training are extracted respectively. S3. Based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix respectively, and construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix respectively. S4. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, the resting-state functional connectivity strength of the BOLD signal between the dACC brain region and the PoCG_L brain region before and after flight training is calculated using the Pearson correlation coefficient algorithm, and the difference in resting-state functional connectivity strength before and after flight training is obtained. S5. Using the difference in resting-state functional connectivity before and after flight training, along with flight training duration and quantitative indicators of flight training performance, as variables, construct a linear model to evaluate training effectiveness and output the results of student flight training quality analysis.

2. The method for analyzing flight training quality based on brain magnetic resonance imaging according to claim 1, characterized in that, Step S2 includes the following steps: S201. Perform data correction on the first imaging data and the second imaging data respectively. The data correction includes: magnetization balance processing, slice time correction and head motion correction. S202. Map the corrected first imaging data and the second imaging data to a unified Montreal Neuroscience Institute space; S203. Spatial smoothing of the spatial data of the Montreal Institute of Neuroscience is performed using a Gaussian kernel function, and non-neural source signal interference is removed by regression of interference variables. The non-neural source signals include white matter signals, cerebrospinal fluid signals and Friston-24 head motion parameter signals constructed based on a rigid body motion model. S204. The spatial data of the Montreal Neuroscience Institute after regression processing of interference variables is transformed into two-dimensional structured data, and the first time series matrix of the changes of trainees' brain voxels over time before flight training and the second time series matrix of the changes of trainees' voxels over time after flight training are extracted respectively.

3. The method for analyzing flight training quality based on brain magnetic resonance imaging according to claim 1, characterized in that, Step S3 includes the following steps: S301. Based on the standard brain atlas, the dACC and PoCG_L regions are defined as region sets respectively, and the coordinates of the dACC brain region and the PoCG_L brain region are obtained; S302. Based on the dACC brain region coordinates and the PoCG_L brain region coordinates, extract the average BOLD signal time series in the dACC brain region and the PoCG_L brain region from the first time series matrix and the second time series matrix, respectively. S303. Based on the obtained average BOLD signal time series, construct the first resting-state functional connection matrix and the second resting-state functional connection matrix respectively.

4. The method for analyzing flight training quality based on brain magnetic resonance imaging according to claim 1, characterized in that, Step S4 includes the following steps: S401. Based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, the mean and standard deviation of the BOLD signal time series of the dACC brain region and the PoCG_L brain region in the connectivity matrix are respectively normalized to zero. S402. Using the Pearson correlation coefficient method, calculate the functional connectivity strengths of the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix respectively, and obtain the first functional connectivity strength and the second functional connectivity strength. The calculation formula is as follows: Where FC represents the functional connectivity strength, n is the total length of the BOLD signal time series, and t is the time point index of the BOLD signal time series. Let be the standardized average of the BOLD signal in the dACC brain region at time t. The normalized mean of the BOLD signal in the PoCG_L brain region at time t; S403. Based on the calculated first functional connectivity strength and second functional connectivity strength, calculate the difference in resting-state functional connectivity strength before and after training.

5. The method for analyzing flight training quality based on brain magnetic resonance imaging according to claim 1, characterized in that, Step S5 includes the following steps: S501. Collect behavioral parameters to obtain the total flight training time of trainees and pre-determined quantitative indicators of flight training performance; S502. Based on the difference in resting-state functional connectivity strength before and after training, construct a linear regression model of training volume, expressed as: Where Q is the flight training quality assessment value, Learnable parameters for resting-state functional connectivity poorness. The resting state functional connectivity is poor. Learnable parameters for flight training duration. For the duration of flight training for trainees, To train learnable parameters for performance quantification metrics, Quantify trainees’ training performance using indicators, where b is the bias parameter; S503. Based on the linear regression model of training volume, calculate the flight training quality assessment value of the trainees, and use it as the result of the flight training quality analysis.

6. A flight training quality analysis system based on brain magnetic resonance imaging, the system being implemented based on the flight training quality analysis method based on brain magnetic resonance imaging as described in any one of claims 1-5, characterized in that, include: The magnetic resonance data acquisition module is used to perform brain magnetic resonance imaging sampling on trainees before and after flight training through functional magnetic resonance imaging sampling. The magnetic resonance data preprocessing module is used to preprocess the imaging data and normalize it to the Montreal Neuroscience Institute space, generating a first time series matrix and a second time series matrix, respectively. The brain region time series extraction module is used to extract the average BOLD signal time series in the dACC brain region and PoCG_L brain region from the first time series matrix and the second time series matrix, respectively, based on the dACC brain region coordinates and PoCG_L brain region coordinates determined by anatomical location in the standard brain atlas, and to construct the first resting state functional connectivity matrix and the second resting state functional connectivity matrix, respectively. The functional connectivity analysis module is used to calculate the resting-state functional connectivity strength before and after training based on the first resting-state functional connectivity matrix and the second resting-state functional connectivity matrix, and to obtain the difference in resting-state functional connectivity strength before and after training. The quality analysis module is used to perform joint modeling based on the difference in resting-state functional connectivity before and after training, combined with the trainee's flight training duration and training performance indicators, and output flight training quality analysis results.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for analyzing flight training quality based on brain magnetic resonance imaging as described in any one of claims 1-5.

8. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for analyzing flight training quality based on brain magnetic resonance imaging as described in any one of claims 1-5.

Images