Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification
This work addresses timely and accurate diagnosis of ASD, a prevalent psychiatric condition, by improving classification performance on a specific dataset, representing an incremental advance in medical imaging analysis.
The study tackled autism spectrum disorder (ASD) classification using resting-state fMRI data from the ABIDE I dataset, achieving an average accuracy of 83.7% and an AUC-score of 0.832 with a novel Multi-Atlas Enhanced Transformer framework that includes self-supervised pretraining.
Autism spectrum disorder (ASD) is a prevalent psychiatric condition characterized by atypical cognitive, emotional, and social patterns. Timely and accurate diagnosis is crucial for effective interventions and improved outcomes in individuals with ASD. In this study, we propose a novel Multi-Atlas Enhanced Transformer framework, METAFormer, ASD classification. Our framework utilizes resting-state functional magnetic resonance imaging data from the ABIDE I dataset, comprising 406 ASD and 476 typical control (TC) subjects. METAFormer employs a multi-atlas approach, where flattened connectivity matrices from the AAL, CC200, and DOS160 atlases serve as input to the transformer encoder. Notably, we demonstrate that self-supervised pretraining, involving the reconstruction of masked values from the input, significantly enhances classification performance without the need for additional or separate training data. Through stratified cross-validation, we evaluate the proposed framework and show that it surpasses state-of-the-art performance on the ABIDE I dataset, with an average accuracy of 83.7% and an AUC-score of 0.832. The code for our framework is available at https://github.com/Lugges991/METAFormer