Diagnosis of Major Depressive Disorder Based on Anomaly Detection with sMRI Gray Matter Slices

The current research focus on Major Depressive Disorder (MDD) is a reflection of its significant adverse impact on individuals and society. Structural magnetic resonance imaging (SMRI) is a valuable tool for clinicians in diagnosing and identifying MDD. sMRI employs a uniform imaging protocol, and images of gray matter slices in the same plane across different sMRIs demonstrate high similarity, revealing repetitive anatomical structures between patients. Given the consistency of anatomical structures, the same regional evidence in normal images presents similar physiological structural information. Lesions, meanwhile, cause structural changes that manifest as abnormal patterns. In this paper, we apply the SQUID model, which is capable of detecting abnormal structural information, to the MDD classification problem. The study employed gray matter slice data generated by SMRI from 1025 individuals with MDD and 1205 Healthy Controls(HC). The objective was to undertake an abnormality detection classification task in MDD and HC, and to further verify the pivotal role of the hippocampus in the diagnosis of MDD through masked experiment. The findings contribute novel methods and evidence for the clinical diagnosis of MDD.