Function-Structural Interaction With Progressive and Multi-Level Feature Fusion for ADHD Classification.

Current neuroscience indicates that multiple brain regions in individuals with Attention Deficit Hyperactivity Disorder (ADHD) are structurally and functionally interconnected. The patient exhibited abnormal alterations in both respective modal brain regions and co-occurrent brain regions with multi-level relationships encompassing hierarchical interactions between function-structural alterations as well as hierarchical progression from local regions to broader brain networks. However, most existing multi-modal ADHD classification approaches independently embed functional and structural data into separate spaces for information integration, often predominately focusing on uni-modal features. Those approaches lead to a significant loss of features related to function-structural interaction. This study proposes a function-structural interaction multi-modal network with progressive and multi-level feature fusion (FSIPM) for ADHD classification. The main contributions are threefold: 1) An innovative function-structural interaction method is proposed to facilitate the mutual regulation of information across modalities, thereby relieving modal feature bias caused by integrated fusion. 2) A progressive multi-level refinement framework is designed to promote the identification of both individual and co-occurrent abnormal brain regions, modeling the function-structural alterations of abnormal brain regions and the hierarchical relationships from local to brain networks. 3) Multi-level feature fusion aims to minimize the loss of details caused by consecutive sampling operations during the progressive process of the network. Experimental results on the ADHD-200 and ABIDE I datasets demonstrate that FSIPM achieves competitive performance in ADHD classification while revealing altered brain regions that are consistent with clinical findings.