Graph Transformer shows remarkable potential in brain network analysis due to its ability to model graph structures and complex node relationships. Most existing methods typically model the brain as a flat network, ignoring its modular structure, and their attention mechanisms treat all brain region connections equally, ignoring distance-related node connection patterns. However, brain information processing is a hierarchical process that involves local and long-range interactions between brain regions, interactions between regions and sub-functional modules, and interactions among functional modules themselves. This hierarchical interaction mechanism enables the brain to efficiently integrate local computations and global information flow, supporting the execution of complex cognitive functions. To address this issue, we propose BrainHGT, a hierarchical Graph Transformer that simulates the brain’s natural information processing from local regions to global communities. Specifically, we design a novel long-short range attention encoder that utilizes parallel pathways to handle dense local interactions and sparse long-range connections, thereby effectively alleviating the over-globalizing issue. To further capture the brain’s modular architecture, we designe a prior-guided clustering module that utilizes a cross-attention mechanism to group brain regions into functional communities and leverage neuroanatomical prior to guide the clustering process, thereby improving the biological plausibility and interpretability. Experimental results indicate that our proposed method significantly improves performance of disease identification, and can reliably capture the sub-functional modules of the brain, demonstrating its interpretability.

High-quality neuroimaging data is vital for robust brain disease identification, yet the presence of outliers in functional magnetic resonance imaging (fMRI) datasets often degrades performance and reliability of identification models. Existing unsupervised outlier detection methods struggle with parameter sensitivity and data distributional complexity, while supervised detection is hindered by the scarcity of labeled outliers. To address this challenge, a novel self-supervised frame-work named Variational Autoencoder Graph Outlier Detection (VAGOD) is proposed, in which pseudo-labeled normal and outlier samples are first generated by a conditional variational autoencoder with hierarchical batch-wise attention, and then a reachability-based graph neural network uses these labels to learn local structures and find subtle outliers in the functional connectivity network. Extensive experiments on the ADHD-200 and ADNI2 datasets demonstrate that removing outliers with VAGOD significantly improves downstream brain disease classification accuracy and stability. Furthermore, group-level analysis reveals that detected outliers exhibit distinct neurobiological signatures, validating the method's interpretability and its practical value for clinical neuroimaging applications.

Dynamic temporal information and static connectivity information derived from functional magnetic resonance imaging (fMRI) can assist in the diagnosis of neurological disorders. However, existing disease diagnosis methods primarily rely on information from a single view, neglecting the advantages of multi-view information fusion. In this work, we propose an end-to-end multi-view fusion method that pre-trains on one view of fMRI data and fine-tunes on another view for disease identification. First, the dynamic temporal information and static connectivity information are integrated during the pre-training stage based on the consistency between the two views, effectively combining complementary information from both data types to improve disease identification accuracy. Finally, in the fine-tuning stage, for different fine-tuning datasets, we combine the residual connections in the model with the self-attention mechanism through the hadamard product. This guides the learning process and can be seen as a form of regularization or inductive bias, enhancing the models ability to learn from the data. Experiments conducted on the ADHD-200 dataset demonstrate that: 1) our method effectively fuses temporal and connectivity information from fMRI, improving the accuracy of brain disorder identification; 2) analyzing the consistency between the two views validates the effectiveness of the pre-training strategy and its positive impact on accuracy; 3) the residual attention maps of the model fine-tuned with functional connectivity networks (FCN) capture distinct symmetrical connections, which align with the inherent symmetry of FCN, supporting the rationale for using the hadamard product.

Abnormal brain functional network is an effective biomarker for brain disease diagnosis. Most existing methods focus on mining discriminative information from whole-brain connectivity patterns. However, multi-level collaboration is the foundation of efficient brain function, in addition to the whole-brain network, there are multiple sub-networks that can quickly integrate and process specific cognitive functions, forming the modular community structure of the brain. To address this gap, we propose a novel method, community-aware graph Transformer (CAGT), that integrates the community information of sub-networks and the topological information of brain graph into the Transformer architecture for better brain disorder identification. CAGT enhances information exchange within and between functional communities through dual-scale feature fusion, capturing interactive information across various scales. Additionally, it incorporates prior knowledge to design brain region position encoding and guide the self-attention, thereby enhancing the spatial awareness of the Transformer and aligning it with the brain's natural information transfer process. Experimental results indicate that our proposed method significantly improves performance on both large and small datasets, and can reliably capture the interactions between sub-networks, demonstrating its generalization and interpretability.

Dynamic functional connectivity network (FCN) can effectively mine meta-stable state transition within the period of data acquisition time, which is related to neurological diseases. However, conventional FCN directly describes the correlation between two brain regions in a meta-stable state, it is low-order FCN. In fact, the connection between two brain regions within the meta-stable state also has a changing pattern, which can reveal the functional consistency between two connections over time, we denote the changing pattern between two regions as high-order FCN. Here, we propose an end-to-end method that integrates low-order and high-order dynamic FCNs for better brain disorder identification. First, a sliding window operation is adopted to capture meta-stable states. Then, a matrix variate normal distribution based approach is employed to construct the low-order and high-order FCNs for each meta-stable state. Finally, a two-stage Transformer is designed to extract meta-stable state transition feature for classification. Experimental results on the ADHD-200 and ABIDE datasets indicate that: 1) our proposed method integrate multi-level connectivity information of dynamic brain functions, thereby effectively improving the identification of brain disorders; 2) the proposed two-stage Transformer is more effective in feature extraction than the well-known CNN-LSTM architecture; 3) high-order FCN help locate biomarkers that low-order FCN cannot be determine, including brain regions as well as functional connections between brain regions, which contribute significantly to the diagnosis of brain disorders.

About 70 million people around the world are suffering from autism, which is about one in every 160 children. The causes of autism are complex, and there is no specific drug treatment. However, for an individual with autism, the earlier the age of treatment, the greater the improvement. In this paper, we collected an autism speech dataset and conducted a study on speech feature classification of autistic and normal children. We built a deep neural network, using Convolutional Recurrent Neural Network as the front-end encoder, and added Convolutional Block Attention Module to it. Integrate local features using recurrent neural networks. To prevent overfitting, we add Connectionist Temporal Classification based speech recognition auxiliary task during training. After introducing the loss function in the field of face recognition, the best classification accuracy reached 94.76%.

With the rise of Autism Spectrum Disorders (ASD) incidence rate, a new screening method that is capable of diagnosing ASD in a more accurate and convenient way is urgently needed. Unlike traditional scales, electroencephalogram (EEG), and eye movement based methods, the acoustic analysis based method has inherent advantages in data collection and rich algorithms that can be employed in speech processing. In this paper, three methods are compared for the construction of acoustic features based on time-frequency independent component analysis (TF-ICA): (1) extracting and combining the rows of the unmixing matrix of each frequency point to build the feature vector; (2) using the separation results of each frequency point as time-frequency feature; (3) extracting time-domain features from the outputs of TF-ICA. Finally, the features are compared by a deep learning classifier on an ASD speech dataset. It is concluded from the experimental results that method 1 obtained the hiehest recognition rate of 98.51%.

With the rapid development of various computing technologies, the constraints of data processing capabilities gradually disappeared, and more data can be simultaneously processed to obtain better performance compared to conventional methods. As a standard statistical analysis method that has been widely used in many fields, Independent Component Analysis (ICA) provides a new way for motion detection by extracting the foreground without precisely modeling the background. However, most existing ICA-based motion detection algorithms use only two-channel data for source separation and simply generate the observation vectors by decomposing and reconstructing the images by row, hence they cannot obtain an integrated and accurate shape of the moving objects in complex scenes. In this article, we propose a refined ICA algorithm for motion detection (RICA-MD), which fuses a larger number of channels than conventional ICA-based motion detection algorithms to provide more effective information for foreground extraction. Meanwhile, we propose four novel methods for generating observation vectors to further cover the diverse motion styles of the moving objects. These improvements enable RICA-MD to effectively deal with slowly moving objects, which are difficult to detect using conventional methods. Our quantitative evaluation in multiple scenes shows that our proposed method is able to achieve a better performance at an acceptable cost of false alarms.

This paper is focused on the experimental approach to explore the potential of independent component analysis (ICA) in the context of motor imagery (MI)-based brain-computer interface (BCI). We presented a simple and efficient algorithmic framework of ICA-based MI BCI (ICA-MIBCI) for the evaluation of four classical ICA algorithms (Infomax, FastICA, Jade, and Sobi) as well as a simplified Infomax (sInfomax). Two novel performance indexes, self-test accuracy and the number of invalid ICA filters, were employed to assess the performance of MIBCI based on different ICA variants. As a reference method, common spatial pattern (CSP), a commonly-used spatial filtering method, was employed for the comparative study between ICA-MIBCI and CSP-MIBCI. The experimental results showed that sInfomax-based spatial filters exhibited significantly better transferability in session to session and subject to subject transfer as compared to CSP-based spatial filters. The online experiment was also introduced to demonstrate the practicability and feasibility of sInfomax-based MIBCI. However, four classical ICA variants, especially FastICA, Jade, and Sobi, performed much worse as compared to sInfomax and CSP in terms of classification accuracy and stability. We consider that conventional ICA-based spatial filtering methods tend to be overfitting while applied to real-life electroencephalogram data. Nevertheless, the sInfomax-based experimental results indicate that ICA methods have a great space for improvement in the application of MIBCI. We believe that this paper could bring forth new ideas for the practical implementation of ICA-MIBCI.