Decoding visual stimuli from human brain activity is a fundamental challenge in cognitive neuroscience and neuroimaging. While recent advances in deep learning have significantly improved the performance of fMRI-to-image decoding, most existing methods overlook the issue of inter-subject variability in fMRI data, which leads to poor generalization across subjects. Current approaches often rely on partially shared model architectures that offer limited generalization and still require subject-specific components, restricting their applicability to unseen subjects. To address this limitation, we propose BrainX, a universal brain decoding framework that constructs a unified fMRI encoder and image generator to achieve subject-agnostic modeling. Specifically, we introduce a feature disentanglement mechanism that extracts subject-shared features from the fMRI embeddings, which are then fed into the image generator to reconstruct visual stimuli. This design eliminates the need for subject-specific models and significantly enhances cross-subject generalization. Additionally, we develop a neuro-geometric fMRI representation learning method that projects 3D cortical structures onto a 2D surface space, effectively mitigating the inaccuracies caused by imprecise geodesic distance estimation in 3D Euclidean space. Extensive experiments on the Natural Scenes Dataset (NSD) demonstrate that BrainX consistently outperforms existing state-of-the-art methods across three decoding settings: within-subject, cross-subject with finetuning, and cross-subject without finetuning.

Decoding natural language text from non-invasive brain signals, such as functional magnetic resonance imaging (fMRI), remains a central challenge in brain-computer interface research. While recent advances in large language models (LLMs) have enabled open-vocabulary fMRI-to-text decoding, existing frameworks typically process the entire fMRI sequence in a single step, leading to performance degradation when handling long input sequences due to memory overload and semantic drift. To address this limitation, we propose a brain-inspired sequential fMRI-to-text decoding framework that mimics the human cognitive strategy of segmented and inductive language processing. Specifically, we divide long fMRI time series into consecutive segments aligned with optimal language comprehension length. Each segment is decoded incrementally, followed by a wrap-up mechanism that summarizes the semantic content and incorporates it as prior knowledge into subsequent decoding steps. This sequence-wise approach alleviates memory burden and ensures semantic continuity across segments. In addition, we introduce a text-guided masking strategy integrated with a masked autoencoder (MAE) framework for fMRI representation learning. This method leverages attention distributions over key semantic tokens to selectively mask the corresponding fMRI time points, and employs MAE to guide the model toward focusing on neural activity at semantically salient moments, thereby enhancing the capability of fMRI embeddings to represent textual information. Experimental results on the two datasets demonstrate that our method significantly outperforms state-of-the-art approaches, with performance gains increasing as decoding length grows.

Diffusion magnetic resonance imaging (dMRI), as a powerful non-invasive white matter imaging technology, plays an important role in studying brain white matter. The fiber orientation distribution functions (fODFs) derived from dMRI data provide the key directional information of fiber tracts for revealing the 3D geometric structure of brain white matter. The estimation of fODFs faces two challenges, including (i) the demand for dMRI data densely sampled in q-space and (ii) the joint consideration of x-q space. To address these challenges, we propose a mixture learning framework with q-space sparely sampled dMRI data as input. Specifically, we propose an x-space learning module based on 3D U-Net to learn x-space features and a q-space learning module based on spherical convolutional neural networks to learn q-space features. Two kinds of features are then fused with a mixture learning fusion module for fODFs estimation. The whole framework is supervised with an x-q space loss function. Our framework makes full use of joint x-q space information for fODFs estimation with clinically available q-space sparsely sampled dMRI data. Extensive experiments on three public datasets show that our framework is effective in fODFs estimation and outperforms cutting-edge models.

Predicting individual behavior is a crucial area of research in neuroscience. Graph Neural Networks (GNNs), as powerful tools for extracting graph-structured features, are increasingly being utilized in various functional connectivity (FC) based behavioral prediction tasks. However, current predictive models primarily focus on enhancing GNNs' ability to extract features from FC networks while neglecting the importance of upstream individual network construction quality. This oversight results in constructed functional networks that fail to adequately represent individual behavioral capacity, thereby affecting the subsequent prediction accuracy. To address this issue, we proposed a new GNN-based behavioral prediction framework, named Dual Multi-Hop Graph Convolutional Network (D-MHGCN). Through the joint training of two GCNs, this framework integrates individual functional network construction and behavioral prediction into a unified optimization model. It allows the model to dynamically adjust the individual functional cortical parcellation according to the downstream tasks, thus creating task-aware, individual-specific FCNs that largely enhance its ability to predict behavior scores. Additionally, we employed multi-hop graph convolution layers instead of traditional single-hop methods in GCN to capture complex hierarchical connectivity patterns in brain networks. Our experimental evaluations, conducted on the large, public Human Connectome Project dataset, demonstrate that our proposed method outperforms existing methods in various behavioral prediction tasks. Moreover, it produces more functionally homogeneous cortical parcellation, showcasing its practical utility and effectiveness. Our work not only enhances the accuracy of individual behavioral prediction but also provides deeper insights into the neural mechanisms underlying individual differences in behavior.

Fatigue driving is a significant cause of road traffic accidents and associated casualties. Automatic assessment of driver drowsiness by monitoring electroencephalography (EEG) signals offer a more objective way to improve driving safety. However, most existing measures are based on multi-channel EEG signals, which are more difficult to apply in practical scenarios as it usually lacks better portability and comfort. In addition, due to the relatively parsimonious and non-stationary characteristics, it is still challenging to effectively accomplish drowsiness recognition by exploiting single-channel EEG signals alone. To this end, we propose a novel temporal-frequential attentional convolutional neural network (TFAC-Net) to take full advantage of spectral-temporal features for single-channel EEG driver drowsiness recognition. Specifically, to capture the potentially valuable information contained in single-channel EEG, the continuous wavelet transform is first employed to generate a corresponding spectral-temporal representation. Then, the temporal-frequential attention mechanism is adopted to reveal critical time-frequency regions in terms of the driver’s mental state. Finally, an adaptive feature fusion module is considered to recalibrate and integrate the most relevant feature channels for final prediction. Extensive experimental results on a widely used public EEG driving dataset demonstrate that the TFAC-Net approach is superior to the state-of-the-art methods, and could discover some discriminative temporal-frequential regions. Moreover, this study also sheds light on the development of portable EEG devices and practical driver drowsiness recognition.

Brain networks, describing the functional or structural interactions of brain with graph theory, have been widely used for brain imaging analysis. Currently, several network representation methods have been developed for describing and analyzing brain networks. However, most of these methods ignored the valuable weighted information of the edges in brain networks. In this paper, we propose a new representation method (i.e., ordinal pattern tree) for brain network analysis. Compared with the existing network representation methods, the proposed ordinal pattern tree (OPT) can not only leverage the weighted information of the edges but also express the hierarchical relationships of nodes in brain networks. On OPT, nodes are connected by ordinal edges which are constructed by using the ordinal pattern relationships of weighted edges. We represent brain networks as OPTs and further develop a new graph kernel called optimal transport (OT) based ordinal pattern tree (OT-OPT) kernel to measure the similarity between paired brain networks. In OT-OPT kernel, the OT distances are used to calculate the transport costs between the nodes on the OPTs. Based on these OT distances, we use exponential function to calculate OT-OPT kernel which is proved to be positive definite. To evaluate the effectiveness of the proposed method, we perform classification and regression experiments on ADHD-200, ABIDE and ADNI datasets. The experimental results demonstrate that our proposed method outperforms the state-of-the-art graph methods in the classification and regression tasks.

Predicting fluid intelligence via neuroimaging data is important to understand neural mechanisms underlying diverse complex cognitive tasks in human brain. Functional connectivity (FC) reflects interactions among brain regions providing rich information of brain organization, which has been widely used in various behavior predictions. With the success of deep neural networks, graph convolutional network (GCN) is regarded as a promising feature learning method in FC networks (FCNs). However, as a challenging task, the existing GCN models cannot achieve a satisfactory performance in fluid intelligence predication due to the insufficient information utilization of brain connectivity and the limitation of graph convolution layer. To tackle these problems, this paper developed a Multi-Scale Multi-Hop GCN (MS-MH-GCN) to estimate fluid intelligence score by using FC. In the proposed method, we considered the hierarchy of brain system and thus utilized FCs from multiple spatial scales as input for the subsequent feature learning to achieve a complete characterize of brain organization for each individual. We also designed a new multi-hop graph convolution layer that uses multi-hop neighbors instead of l-hop neighbor in traditional GCN to guide message passing of nodal feature at every step. The introduction of high-order graph information benefits to the model learning ability improvement. Additionally, it is also worth emphasizing that, during feature learning process, we added contrast constraint to multi-scale FCNs to improve the similarity of feature representations across different spatial scales within a subject. Experimental results showed that our proposed method performed much better than the other four art-of-the-state methods.

Detecting the time-varying community structure of brain functional network is very important to reveal dynamic properties of the human brain. Although several community detection methods have been proposed, they are limited in real application due to their poor performance in large dynamic network and difficulty in parameter setting without prior knowledge. To address these problems, this paper proposes a novel dynamic community detection method for the brain network based on random walk, named as ML-RW. This method uses local community discovery instead of global community detection to improve its ability to deal with large dynamic networks. Specifically, ML-RW first selects a query brain region and sends out multiple random walkers starting from this region to explore local community structures of all networks in dynamic network simultaneously. It updates the visiting probability vector of each walker by aggregating the transition probabilities from itself and two temporally adjacent networks. Since the influence strength from one network to another is adaptively tuned according to the relevance of visiting histories of two networks, ML-RW could guarantee the temporal smoothness of the detected modular structure without introducing the hyper-parameter and thus avoids the problem of parameter setting in existing methods. Experiments on two public real neuroimaging datasets demonstrate that our proposed method has more potential to capture subtle community variations in the brain region, stronger ability to discover biomarkers for brain diseases, and higher test-retest reliability than the conventional method.

Detecting community structure has become one important technique for studying complex networks. Although many community detection algorithms have been proposed, most of them focus on separated communities, where each node can belong to only one community. However, in many real-world networks, communities are often overlapped with each other. Developing overlapping community detection algorithms thus becomes necessary. Along this avenue, this paper proposes a maximal clique based multiobjective evolutionary algorithm (MOEA) for overlapping community detection. In this algorithm, a new representation scheme based on the introduced maximal-clique graph is presented. Since the maximal-clique graph is defined by using a set of maximal cliques of original graph as nodes and two maximal cliques are allowed to share the same nodes of the original graph, overlap is an intrinsic property of the maximal-clique graph. Attributing to this property, the new representation scheme allows MOEAs to handle the overlapping community detection problem in a way similar to that of the separated community detection, such that the optimization problems are simplified. As a result, the proposed algorithm could detect overlapping community structure with higher partition accuracy and lower computational cost when compared with the existing ones. The experiments on both synthetic and real-world networks validate the effectiveness and efficiency of the proposed algorithm.