Fusing multi-scale fMRI features using a brain-inspired multi-channel graph neural network for major depressive disorder diagnosis

Depression stands as one of the most pernicious mental disorders in contemporary society, characterized by a highly intricate pathological mechanism. Specifically, individuals suffering from Major Depressive Disorder (MDD) exhibit heightened vulnerability to suicidal tendencies. Currently, healthcare practitioners often encounter challenges related to the misdiagnosis and underdiagnosis of depression during clinical assessments. Consequently, it is of paramount importance to develop highly accurate auxiliary diagnostic tools for depression. Unfortunately, traditional machine learning and deep learning methodologies frequently neglect the integration of multi-source data and disregard the intricate topological structure and high-order attributes of brain networks. In this study, a multi-scale feature fusion classification framework is proposed to distinguish between MDD patients and healthy controls. Within the proposed model, a novel method, the Cross-Level High-Order Interaction (CLHOI), is introduced and implemented on a low-order functional connectivity (LOFC) matrix to derive two distinct high-order functional connectivity (HOFC) matrices. Subsequently, a Multi-Channel Fusion Graph Convolutional Network (MFGCN) is trained by integrating high-order and low-order brain graph features along with phenotypic information. The results of 10-fold cross-validation experiments conducted on the publicly available REST-meta-MDD dataset indicate that the fusion of multi-scale features improves the average accuracy by approximately 3%, resulting in an accuracy rate of 77.6%. Simultaneously, the hypothesis asserting the existence of intricate information interactions at various levels within brain connectivity networks is validated. Moreover, our model exhibits strong explanatory capabilities, effectively identifying brain regions closely associated with MDD, including the Precentral gyrus, Superior frontal gyrus, Cuneus, Lingual gyrus, and Fusiform gyrus. In comparison to numerous advanced studies within the same domain, our approach has produced competitive results. Furthermore, our proposed method can be readily extended to facilitate the diagnosis of various neurological diseases.