A method for identifying mental illness based on spike structure-function brain network coupling

Abstract

The present invention provides a method for identifying mental illness based on pulse structure-function brain network coupling, which belongs to the field of intelligent auxiliary medical diagnosis technology and effectively solves the technical problem of the neurobiological mechanism between structural connection and functional connection that is often ignored in the traditional diagnosis of mental illness. Its technical solution is: first, functional and structural brain networks are extracted from functional magnetic resonance imaging and diffusion tensor imaging; then, the information feature maps of these two brain networks are extracted through BrainNetCNN; then a pulse coupled neural network is constructed to learn the brain structure-function coupling mechanism, so as to derive the pulse structure-function coupling; finally, the obtained coupling information is input into the classification layer to obtain the disease identification result, and the cross-entropy loss function is used to train and optimize the result. The beneficial effects of the present invention are: the present invention helps to deeply understand the neural mechanism of mental illness and has a wide range of application prospects in clinical applications.

Description

Technical Field

[0001] The present invention relates to the field of intelligent assisted medical diagnosis technology, and in particular to a method for identifying mental illness based on pulse structure-function brain network coupling. Background Art

[0002] Mental illness refers to disorders in which brain function is disrupted by various biological, psychological, and social factors, leading to varying degrees of impairment in cognitive, emotional, volitional, and behavioral mental activities. Individuals with mental illness may have altered brain structure and function, or exhibit varying neurochemical responses. Furthermore, numerous studies have confirmed that patients with mental illness have enlarged ventricles and atrophied gray matter. Thus, the complexity of mental illness lies primarily in changes in brain structure and function.

[0003] The brain is a complex network composed of interplaying structural and functional connections. Structural connectivity primarily refers to the white matter fibers that connect gray matter regions, while functional connectivity is defined as the statistical dependencies between different brain regions. The relationship between structural and functional connectivity is known as structure-function coupling, and this coupling plays a crucial role in the diagnosis of psychiatric disorders.

[0004] Current traditional structure-function coupling methods primarily aim to identify statistical correlations between topological patterns of structural and functional connectivity, lacking principled, systems-level integration to characterize the coupling mechanisms of how neuronal populations communicate and produce significant brain functions across the structural connectome. Furthermore, most existing deep learning models of structure-function coupling fail to account for the naturally complex connections between structure and function, neglecting the neurobiological mechanisms underlying these connections.

[0005] The paper "Learning tensor-based features for whole-brain fMRI classification" proposes using multilinear principal component analysis to investigate the mechanism of structure-function coupling. This approach combines the structural and functional brain network matrices into a three-dimensional tensor, extracts feature vectors through multilinear principal component analysis, and finally uses a support vector machine for classification to achieve accuracy. This approach only considers the statistical correlation between structural and functional connectivity and fails to fully capture the complex interactions and dynamic changes between brain structure and functional connectivity.

[0006] The paper "Learning to Model the Relationship Between Brain Structural and Functional Connectomes" uses a supervised graph representation learning framework based on graph convolutional networks to investigate the mechanism of structure-function coupling. An encoder learns node-level structural connectivity embeddings to generate a whole-brain graph representation for reconstructing functional brain networks. Finally, a multi-objective loss function is used to jointly reconstruct the functional brain network and learn a discriminant graph representation of the structure-function coupling mapping for graph-level classification. This approach ignores the neurobiological mechanisms between structural and functional connectivity and does not fully consider the biological properties of brain connections and neural transmission processes.

[0007] Therefore, using the pulse transmission mechanism in spiking neurons to simulate the action potential transmission in the brain can better study the brain structure-function coupling mechanism and significantly improve the accuracy of mental illness diagnosis. Summary of the Invention

[0008] Aiming at the technical problem of the neurobiological mechanism between structural connectivity and functional connectivity that is often overlooked in the traditional diagnosis of mental illness, the purpose of the present invention is to provide a mental illness identification method based on pulse structure-function brain network coupling to improve the accuracy of mental illness identification.

[0009] The inventive concept of the present invention is that the structure-function coupling of the brain plays an important role in the diagnosis of mental illness. It involves the relationship between the structural connections and functional connections of the brain. In the diagnosis of mental illness, the analysis of structure-function coupling can provide important information about how brain networks support or deviate from normal functions. Most current structure-function coupling analysis methods do not comprehensively consider the naturally complex connections between structural connections and functional connections, and ignore the neurobiological mechanisms between structural connections and functional connections. A spiking neural network is a computational model inspired by biological nervous systems. The pulse transmission mechanism in a spiking neural network can simulate the interaction between structural connections and functional connections in the brain. Therefore, based on the spiking neural network, a pulse coupled neural network is proposed. It uses the dense interconnection of spiking neurons and synaptic weights to simulate the interaction between structural connections and functional connections in the brain to obtain spiking structure-function coupling, providing a new perspective for the study of structure-function coupling.

[0010] In order to better achieve the above-mentioned purpose of the invention, the present invention is implemented by the following technical solution: a method for identifying mental illness based on pulse structure-function brain network coupling, the specific steps of which are as follows:

[0011] A. Functional brain networks were constructed using functional magnetic resonance imaging (fMRI). The fMRI data were processed using spm12 in the DPARSF toolbox. The initial functional time series were slice-time corrected, realigned, and normalized to the EPI template. A detrending process was then performed to remove sources of spurious variance, namely six head motion parameters, the average signal of the CSF and white matter, and the global brain signal. The time series were bandpass filtered at 0.01-0.08 Hz. The resulting volume had 240 time points and was divided into 90 regions of interest using the automated anatomical labeling atlas (AAL). Structural brain networks were constructed using diffusion tensor imaging (DTI). DTI data were processed using the PANDA suite and DTI distortion correction was performed using the FSL toolbox. Fiber images were then obtained using a deterministic tracking method using TrackVis. Anatomical regions were defined using the AAL convention based on the registered T1 images of each subject.

[0012] B. Use BrainNetCNN to obtain information feature maps of structural brain networks and functional brain networks. α=1,2, where A 1 Represents the adjacency matrix of the structural brain network, A 2 Represents the adjacency matrix of the functional brain network, where N corresponds to the node set of the brain region. To obtain the complex features in the two brain network data, edge-to-edge convolution E2E and edge-to-node convolution E2N operations are used to obtain the feature maps of the two brain networks;

[0013] C. Use the Leaky-Integrate-and-Fire pulse neuron model to build a pulse coupled neural network. The structural feature map λ after the E2E and E2N convolution operations sc and functional feature map λ fc Repeat T times as input and perform implicit pulse encoding through internal spiking neurons, where T is the time step. Then use pulse coupled neural networks to learn the structure-function coupling mechanism from the structure and function feature graphs to find the spike structure-function coupling;

[0014] D. The obtained spike structure-function coupling is input into the classification layer, the predicted category is determined by the spike output sequence, and the cross-entropy loss between the predicted category and the true category is used as the loss function for training. This obtains a neural network model that can identify the subtle relationship between healthy and disease connectomes based on spike structure-function coupling.

[0015] As the method for identifying mental illness based on pulse structure-function brain network coupling provided by the present invention, the specific steps of step B are as follows:

[0016] a. Edge-to-edge E2E convolution, which aims to extract edge features from the original adjacency matrix. It takes advantage of the topological structure of the network and performs filtering operations by combining the weights of the edges of shared nodes. The formula is as follows:

[0017]

[0018] in, and is the learning weight, f n Represents the nonlinear activation function of the nth filter, and the feature maps of the structural brain network and the functional brain network after E2E convolution are recorded as and Where C1 / C1′ is the number of filters in the E2E convolution operation;

[0019] b. Edge-to-node E2N convolution aims to aggregate edge features into node features. It extracts information from the adjacent edges of each node and generates a representation of each node. The formula is as follows:

[0020]

[0021] in, is the learning weight, (m,n) represents each pair of input and output feature maps of each layer, and the feature map after E2N convolution is recorded as and Where C2 / C2' is the number of filters in the E2N convolution operation;

[0022] As the method for identifying mental illness based on pulse structure-function brain network coupling provided by the present invention, the specific steps of step C are as follows:

[0023] a. Use the Leaky-Integrate-and-Fire (LIF) spiking neuron model to construct a pulse-coupled neural network. The LIF spiking neuron can be described by a differential function:

[0024]

[0025] Where τ represents the time constant, U(t) represents the membrane potential of the postsynaptic neuron, and I(t) represents the total input received from the ensemble of presynaptic neurons at any given time. After solving this differential equation, the dynamics of the LIF neuron layer is governed by the following formula:

[0026] U[t]=βU[t-1]+X[t]-S out [t-1]θ (17)

[0027] Where t is the time step, X[t] is the spatial input information, U[t] is the membrane potential, θ is the threshold, and β = e -1 / τis the attenuation factor, S out [t]∈{0,1} is the output pulse generated by the neuron, which will be generated if the membrane potential exceeds the threshold:

[0028]

[0029] If activated, the reset term subtracts the threshold θ from the membrane potential. Otherwise, the reset term has no effect;

[0030] b. The structural feature map after E2E and E2N convolution operations and functional feature maps As the input of the pulse coupled neural network, where T is the time step, it converts λ 1 and λ 2 Repeat T times as input:

[0031]

[0032] Where D is the feature dimension, is the spiking neuron layer, U′ sc and U′ fc It is through Obtained, so they are a binarized impulse tensor;

[0033] c. Through And the linear layer Liner(·) can get the structure and function impulse tensor:

[0034]

[0035] Among them, X sc represents the structured brain network spike tensor, X fc represents the functional brain network spike tensor,

[0036] d, X sc and X fc They are both binary spike tensors that contain important characteristic information of structural and functional brain networks. They simulate the interaction between structural and functional connections in the brain through dense interconnection of spike neurons and synaptic weights to obtain spike structure-function coupling:

[0037]

[0038] in, is the Hadmard product, SP sc-fc It is the spike structure-function coupling obtained by learning structural and functional brain networks in the form of spike trains, which enables us to identify subtle patterns of network dysfunction between healthy and disease connectomes.

[0039] As the method for identifying mental illness based on pulse structure-function brain network coupling provided by the present invention, the specific steps of step D are as follows:

[0040] a. Order Denotes the spikes emitted by each output neuron over time, which is a time-varying vector where m is the number of output categories. Let The spike count for each output neuron can be obtained by Summing to obtain:

[0041]

[0042] b. The largest count The index of corresponds to the predicted class y:

[0043]

[0044] c. For binary classification tasks, the cross entropy loss is calculated as follows:

[0045]

[0046] Among them, L c is the cross entropy loss function, and y is the true category.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The method for identifying mental illness based on pulse structure-function brain network coupling proposed in this invention, compared with most previous structure-function coupling analysis models, not only fully considers the multimodal interaction between structural and functional connections, but also further studies the neurobiological mechanism between structural and functional connections.

[0049] 2. In view of the complex data characteristics of structural and functional brain networks, the pulse-coupled neural network proposed in this invention provides a powerful analysis tool that can capture and simulate the dynamic interactions and time dependencies in brain networks. By simulating the pulse activity of neurons, it can more accurately reflect the complexity of the brain at the structural and functional levels, thereby providing a new perspective for understanding how the brain achieves specific functions through its structure.

[0050] 3. The research on pulse structure-function coupling proposed in this invention helps to better understand the pathophysiological mechanisms of brain diseases. It not only significantly improves the accuracy of identifying mental illnesses, but also assists doctors in diagnostic analysis to achieve efficient treatment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention but do not constitute a limitation of the present invention.

[0052] Figure 1 This is the overall framework diagram of the mental illness identification method based on pulse structure-function brain network coupling of the present invention;

[0053] Figure 2 This is a model diagram of the mental illness identification method based on pulse structure-function brain network coupling of the present invention. DETAILED DESCRIPTION

[0054] In order to deepen the understanding of the present invention, the present invention will be further described in detail below with reference to embodiments and drawings. The embodiments are only used to explain the present invention and do not constitute a limitation on the scope of protection of the present invention.

[0055] Example 1

[0056] See also Figure 1 , Figure 2 This embodiment is specifically implemented through the following technical solutions:

[0057] like Figure 1 and Figure 2 As shown in Figure 1, the method for identifying mental illness based on pulse structure-function brain network coupling has the following specific steps:

[0058] A. Functional brain networks were constructed using functional magnetic resonance imaging (fMRI). The fMRI data were processed using spm12 in the DPARSF toolbox. The initial functional time series were slice-time corrected, realigned, and normalized to the EPI template. A detrending process was then performed to remove sources of spurious variance, namely six head motion parameters, the mean signal of the CSF and white matter, and the global brain signal. The time series were bandpass filtered at 0.01–0.08 Hz. The resulting volume had 240 time points and was divided into 90 regions of interest using the automated anatomical labeling atlas (AAL). Structural brain networks were constructed using diffusion tensor imaging (DTI). DTI data were processed using the PANDA suite and DTI distortion correction was performed using the FSL toolbox. Fiber images were then obtained using a deterministic tracking method using TrackVis. Anatomical regions were defined using the AAL convention based on the registered T1 images for each subject.

[0059] The above model was tested on a dataset of psychiatric brain maps acquired on a 3.0T Siemens Trio MRI scanner. The DTI scan parameters were as follows: repetition time = 6100ms, interval = 93ms, flip angle = 90°, voxel size = 0.94×0.94×3mm. 3fMRI scan parameters were as follows: repetition time = 2000 ms, interval = 30 ms, flip angle = 90°, voxel size = 3.75 × 3.75 × 3.75 mm 3 .

[0060] B. Use BrainNetCNN to obtain information feature maps of structural brain networks and functional brain networks. α=1,2, where A 1 Represents the adjacency matrix of the structural brain network, A 2 Represents the adjacency matrix of the functional brain network, where N corresponds to the node set of the brain region. To obtain the complex features in the two brain network data, the edge-to-edge convolution (E2E) and edge-to-node convolution (E2N) operations proposed by Kawahara et al. are used to obtain the feature maps of the two brain networks; the specific steps are as follows:

[0061] a. Edge-to-edge E2E convolution, which aims to extract edge features from the original adjacency matrix. It takes advantage of the topological structure of the network and performs filtering operations by combining the weights of the edges of shared nodes. The formula is as follows:

[0062]

[0063] in, and is the learning weight, f n Represents the nonlinear activation function of the nth filter, and the feature maps of the structural brain network and the functional brain network after E2E convolution are recorded as and Where C1 / C1′ is the number of filters in the E2E convolution operation;

[0064] b. Edge-to-node E2N convolution aims to aggregate edge features into node features. It extracts information from the adjacent edges of each node and generates a representation of each node. The formula is as follows:

[0065]

[0066] in, is the learning weight, (m,n) represents each pair of input and output feature maps of each layer, and the feature map after E2N convolution is recorded as and Where C2 / C2' is the number of filters in the E2N convolution operation;

[0067] The number of samples in the mental illness brain map dataset is 217, and the decision attributes are divided into two categories: patients with confirmed mental illness and normal people. The connection matrices of the structural brain network and the functional brain network are and The E2E convolutional layer consists of 32 1×90 and 32 90×1 filters, and the generated structural and functional feature maps are and The E2N convolutional layer consists of 64 1×90×32 filters, and the generated structural and functional feature maps are and

[0068] C. Use the Leaky-Integrate-and-Fire (LIF) pulse neuron model to build a pulse coupled neural network. The structural feature map λ after the E2E and E2N convolution operations is converted into sc and functional feature map λ fc Repeat T times as input and perform implicit pulse encoding through internal spiking neurons, where T is the time step. Then use pulse coupled neural networks to learn the structure-function coupling mechanism from the structure and function feature graphs to find the spiking structure-function coupling; the specific steps are as follows:

[0069] a. Use the Leaky-Integrate-and-Fire (LIF) spiking neuron model to construct a pulse-coupled neural network. The LIF spiking neuron can be described by a differential function:

[0070]

[0071] Where τ represents the time constant, U(t) represents the membrane potential of the postsynaptic neuron, and I(t) represents the total input received from the presynaptic neuron ensemble at any given time. After solving this differential equation, the dynamics of the LIF neuron layer is governed by the following formula:

[0072] U[t]=βU[t-1]+X[t]-S out [t-1]θ (30)

[0073] Where t is the time step, X[t] is the spatial input information, U[t] is the membrane potential, θ is the threshold, and β = e -1 / τ is the attenuation factor, S out [t]∈{0,1} is the output pulse generated by the neuron, which will be generated if the membrane potential exceeds the threshold:

[0074]

[0075] If activated, the reset term subtracts the threshold θ from the membrane potential; otherwise, the reset term has no effect;

[0076] b. The structural feature map after E2E and E2N convolution operations and functional feature maps As the input of the pulse coupled neural network, where T is the time step, it converts λ 1 and λ 2 Repeat T times as input:

[0077]

[0078] Where D is the feature dimension, is the spiking neuron layer, U′ sc and U′ fc It is through Obtained, so they are a binarized impulse tensor;

[0079] c. Through And the linear layer Liner(·) can get the structure and function impulse tensor:

[0080]

[0081] Among them, X sc represents the structured brain network spike tensor, X fc represents the functional brain network spike tensor,

[0082] d, X sc and X fc They are both binary spike tensors that contain important characteristic information of structural and functional brain networks. They simulate the interaction between structural and functional connections in the brain through dense interconnection of spike neurons and synaptic weights to obtain spike structure-function coupling:

[0083]

[0084] in, is the Hadmard product, SP sc-fc It is the spike structure-function coupling obtained by learning structural and functional brain networks in the form of spike trains, which enables us to identify subtle patterns of network dysfunction between healthy and disease connectomes.

[0085] Design a fully connected pulse-coupled neural network with 90 × 64 neurons in the input layer, 800 to 1200 neurons in the hidden layer, and two output neurons for classification. Use a dropout of 0.5 for each layer. The decay factor β for LIF neurons is 0.9, and the time step T = {32, 64, ..., 256}.

[0086] D. The obtained spike structure-function coupling is input to the classification layer. The predicted category is determined by the spike output sequence. The cross entropy loss between the predicted category and the true category is used as the loss function for training. This results in a neural network model that can identify the subtle relationship between healthy and diseased connectomes based on spike structure-function coupling. The specific steps are as follows:

[0087] a. Order Denotes the spikes emitted by each output neuron over time, which is a time-varying vector where m is the number of output categories. Let The spike count for each output neuron can be obtained by Summing to obtain:

[0088]

[0089] b. The largest count The index of corresponds to the predicted class y:

[0090]

[0091] c. For binary classification tasks, the cross entropy loss is calculated as follows:

[0092]

[0093] Among them, L c is the cross entropy loss function, and y is the true category.

[0094] Using a five-fold cross-validation approach, the model underwent five independent rounds of training and testing, each split into different training, test, and validation sets. Across these rounds, the highest accuracy recorded was 97.13%, with an overall average accuracy of 92.68%. These data demonstrate that the model can significantly improve the accuracy of mental illness identification.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying mental illness based on pulse structure-function brain network coupling, characterized in that: The following steps are involved: S1. Functional brain networks were constructed by functional magnetic resonance imaging (fMRI). The fMRI data were processed by spm12 in the DPARSF toolbox. The initial functional time series were slice-time-corrected, realigned, and normalized to the EPI template. A detrending process was then performed to remove sources of spurious variance. The time series were band-pass filtered at 0.01-0.08 Hz. The resulting volume had 240 time points and was divided into 90 regions of interest using the automated anatomical labeling atlas (AAL). Structural brain networks were constructed by diffusion tensor imaging (DTI). DTI data were processed using the PANDA suite and DTI distortion correction was performed using the FSL toolbox. Fiber images were then obtained using a deterministic tracking method using TrackVis. Anatomical regions were defined using the AAL convention based on the registered T1 images of each subject. S2, use BrainNetCNN to obtain the information feature map of the structural brain network and functional brain network, let Among them A 1 Represents the adjacency matrix of the structural brain network, A 2 Represents the adjacency matrix of the functional brain network, where N corresponds to the node set of the brain region. To obtain the complex features in the two brain network data, edge-to-edge convolution E2E and edge-to-node convolution E2N operations are used to obtain the feature maps of the two brain networks; S3. A pulse-coupled neural network is constructed using the Leaky-Integrate-and-Fire spiking neuron model. The structural feature map λsc and the functional feature map λfc after E2E and E2N convolution operations are repeated T times as input, and implicit pulse encoding is performed through internal spiking neurons, where T is the time step. The pulse-coupled neural network is then used to learn the structure-function coupling mechanism from the structural and functional feature maps to obtain the pulse structure-function coupling. The specific steps of constructing the pulse coupled neural network described in step S3 are as follows: S31. Use the Leaky-Integrate-and-Fire spiking neuron model to construct a pulse-coupled neural network, and use differential functions to describe the LIF spiking neuron: Where τ represents the time constant, U(t) represents the membrane potential of the postsynaptic neuron, and I(t) represents the total input received from the ensemble of presynaptic neurons at any given time. After solving this differential equation, the dynamics of the LIF neuron layer is governed by the following formula: U[t]=βU[t-1]+X[t]-S out [t-1]θ (4) Where t is the time step, X[t] is the spatial input information, U[t] is the membrane potential, θ is the threshold, β = e- 1 τ is the decay factor, Sout[t]∈{0,1} is the output pulse generated by the neuron, and a pulse is generated if the membrane potential exceeds the threshold: If activated, the reset term subtracts the threshold θ from the membrane potential; otherwise, the reset term has no effect; S32, the structural feature map after E2E and E2N convolution operations and functional feature maps As the input of the pulse coupled neural network, where T is the time step, it converts λ 1 and λ 2 Repeat T times as input: Where D is the feature dimension, is the spike neuron layer, Us′c and U′fc are Obtained, so they are a binarized impulse tensor; S33, through And the linear layer Liner(·) to obtain the structure and function impulse tensor: Among them, Xsc represents the structural brain network pulse tensor, Xfc represents the functional brain network pulse tensor, S34, Xsc, and Xfc are all binary spike tensors that contain important characteristic information of structural and functional brain networks. They simulate the interaction between structural and functional connections in the brain through the dense interconnection of spike neurons and synaptic weights to obtain spike structure-function coupling: in, is the Hadmard product, SP sc-fc It is the spike structure-function coupling obtained by learning the structural and functional brain networks in the form of spike trains, which is used to identify subtle network dysfunction patterns between healthy and diseased connectomes; S4. The obtained spike structure-function coupling is input into the classification layer, the predicted category is determined by the spike output sequence, and the cross-entropy loss between the predicted category and the true category is used as the loss function for training, thereby obtaining a neural network model that can identify the subtle relationship between healthy and disease connectomes based on spike structure-function coupling.

2. The method for identifying mental illness based on pulse structure-function brain network coupling according to claim 1, characterized in that: The specific steps for using BrainNetCNN to obtain two brain network information feature maps in step S2 are as follows: S21, edge-to-edge E2E convolution, is designed to extract edge features from the original adjacency matrix. It utilizes the topological structure of the network and performs filtering operations by combining the weights of the edges of shared nodes. The formula is as follows: in, and is the learning weight, fn represents the nonlinear activation function of the nth filter, and the feature maps of the structural brain network and the functional brain network after E2E convolution are recorded as and Where C1 / C1′ is the number of filters in the E2E convolution operation; S22, edge-to-node E2N convolution, aims to aggregate edge features into node features. It extracts information from the adjacent edges of each node and generates a representation of each node. The formula is as follows: in, is the learning weight, (m,n) represents each pair of input and output feature maps of each layer, and the feature map after E2N convolution is recorded as and where C2 / C2' is the number of filters in the E2N convolution operation.

3. The method for identifying mental illness based on pulse structure-function brain network coupling according to claim 1, characterized in that: The specific steps of determining the predicted category from the pulse output sequence described in step S4 are as follows: S41, Order Denotes the spikes emitted by each output neuron over time, which is a time-varying vector, where m is the number of output categories, let For each output neuron, the spike count is calculated by Summing to obtain: S42, the largest count The index of corresponds to the predicted class y: S43. For binary classification tasks, the cross entropy loss is calculated as follows: Among them, Lc is the cross entropy loss function and y is the true category.

Images