STARFormer: A Novel Spatio-Temporal Aggregation Reorganization Transformer of FMRI for Brain Disorder Diagnosis

2024-12-31

AI Summary

Existing fMRI analysis methods typically model the spatial and temporal dependencies of BOLD signals separately, limiting diagnostic accuracy for autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD). To address this, we propose STARFormer—a novel framework that jointly models the dynamic topological structure and temporal evolution of functional brain connectivity. Specifically, it (1) reorders regions of interest (ROIs) spatially based on eigenvector centrality to enhance structural representation; (2) employs a variable-length sliding window coupled with cross-window attention to reorganize multi-scale temporal features; and (3) adopts a dual-branch parallel Transformer architecture to enable fine-grained spatiotemporal joint modeling. Evaluated on public ASD and ADHD fMRI datasets, STARFormer achieves statistically significant improvements in classification accuracy and F1-score over state-of-the-art methods, establishing a new paradigm for precise neurodevelopmental disorder diagnosis.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Many existing methods that use functional magnetic resonance imaging (fMRI) classify brain disorders, such as autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD), often overlook the integration of spatial and temporal dependencies of the blood oxygen level-dependent (BOLD) signals, which may lead to inaccurate or imprecise classification results. To solve this problem, we propose a Spatio-Temporal Aggregation eorganization ransformer (STARFormer) that effectively captures both spatial and temporal features of BOLD signals by incorporating three key modules. The region of interest (ROI) spatial structure analysis module uses eigenvector centrality (EC) to reorganize brain regions based on effective connectivity, highlighting critical spatial relationships relevant to the brain disorder. The temporal feature reorganization module systematically segments the time series into equal-dimensional window tokens and captures multiscale features through variable window and cross-window attention. The spatio-temporal feature fusion module employs a parallel transformer architecture with dedicated temporal and spatial branches to extract integrated features. The proposed STARFormer has been rigorously evaluated on two publicly available datasets for the classification of ASD and ADHD. The experimental results confirm that the STARFormer achieves state-of-the-art performance across multiple evaluation metrics, providing a more accurate and reliable tool for the diagnosis of brain disorders and biomedical research. The codes will be available at: https://github.com/NZWANG/STARFormer.

Problem

• fMRI analysis
• neurological disorders
• spatiotemporal correlation

Innovation

• STARFormer
• spatiotemporal analysis
• brain disease diagnosis