Deep domain generalization method via low-rank category constraint for multi-site ASD identification

With the development of deep learning in diagnosing autism spectrum disorder (ASD), multi-site resting-state functional magnetic resonance imaging (rs-fMRI) images have made excellent progress. However, there is a heterogeneous problem between the multi-site data caused by inconsistent data distribution. Existing domain adaptation methods cannot deal with the issue that the target domain data is unavailable during the training stage. To address this problem, we propose a deep domain generalization method via low-rank category constraint (DDGLCC) for multi-site ASD identification. The main idea is capturing the category discriminative information through the domain-specific networks and gaining the consistently shared information through the domain-invariant network. A novel category-based low-rank constraint strategy is used to align two types of networks. In the test stage, the well-Trained domain-invariant network is applied to the unseen target domain data. Whether the results on different deep structure experiments or different lowrank constraints experiments, the proposed DDGLCC method achieves the best performance.