Topology-Guided Graph Masked Autoencoder Learning for Population-Based Neurodevelopmental Disorder Diagnosis

Exploring the pathogenic mechanisms of brain disorders within population is an important research in the field of neuroscience. Existing methods either combine clinical information to assist analysis or use data augmentation for sample expansion, ignoring the mining of individual information and the exploration of inter-individual associations in population. To solve these problems, this work proposes a novel approach for detecting abnormal neural circuits associated with brain diseases, named Topology-guided Graph Masked autoencoder Learning method (TGML), which focuses on individual representation and intra-population association, to achieve the effective diagnosis of brain diseases within the population. Concretely, the TGML comprises 1) the topology-guided group association module (T ${G}^{{2}}$ AM) that reconstructs the edges and update the initial population graph, 2) the intra-population interaction masked autoencoder network (IPI_MAE) captures the discriminative characteristics of subjects based on the novel Masked Autoencoder, which incorporates traditional masked autoencoders into a task-related process. The proposed method is evaluated on two neurodevelopmental disorder diagnosis tasks of Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD). The results show that the proposed TGML achieves significant improvements and surpasses the state-of-the-art methods.