Cerebral Cortical Abnormalities and Classification for Schizophrenia Via High-Resolution Magnetic Resonance Imaging

Background: Evidence from neuroimaging has implicated abnormal cerebral cortical patterns in schizophrenia. Application of machine learning techniques is required for identifying a structural signature at the individual level reflecting neurobiological substrates of schizophrenia. Methods: 52 Patients and 66 healthy controls were recruited within the same period. Multivariate computation was used to examine the abnormalities of cortical features in schizophrenia. Features were selected by least absolute shrinkage and the selection operator (LASSO) method. The diagnostic capacity of multi-dimensional cortical neuroanatomical pattern-based classification was evaluated based on diagnostic tests. Findings: The features of mean curvature (left insula and left inferior frontal gyrus), cortical thickness (left fusiform gyrus), and metric distortion (left cuneus and right superior temporal gyrus) revealed both group differences and diagnostic capacity. Area under the receiver operating characteristic curve was 0.88, and the sensitivity, specificity, and accuracy were 94%, 82%, and 88% respectively. There was a positive association between the index score derived from multi-dimensional patterns and symptom severity (r = 0.40, P< 0.01) for patients. Our findings demonstrated a view of cortical differences with the capacity to discriminate patients with schizophrenia. Structural neuroimaging-based signatures hold potential promise of paving the road for clinical utility in schizophrenia. Interpretation: Our findings demonstrate a view of cortical differences with capacity to discriminate patients with schizophrenia. Structural neuroimaging-based signatures hold potential promise of paving the road for clinical utility in schizophrenia. Funding Statement:This study was supported by the National Basic Research Program of China under Grant Nos. 2014CB543203 and 2015CB856403, the National Natural Science Foundation of China under Grant Nos. 81471811, 81471738 and 61401346, the Fundamental Research Funds for the Central Universities (Dr Qin) and grants 81571651 from the National Natural Science Foundation of China and 2017ZDXM-SF-048 from the Key Research and Development Program of Shaanxi Province (Dr Yin). Declaration of Interest: No disclosure was reported. Ethics Approval Statement: This study was approved by the local Research Ethics Committee (Xijing Hospital, Fourth Military Medical University). All participants gave written informed consent after a complete description of this study