We obtained sMRI data from unmedicated adolescents and young adults with MDD, StD and well-matched healthy control subjects, and identified radiomics features from gray and white matter, and establish classification models. The accuracies and AUC were 86.75%, 0.93 for distinguishing MDD from HC, 70.51%, 0.69 for discriminating StD from HC, and 59.15%, 0.66 for differentiating MDD from StD, respectively. These findings provide preliminary evidence that radiomics features of brain structure are valid for discriminating MDD and StD from HCs. The MRI-based radiomics approach, with further improvement and validation, is a potential facilitating method to clinical diagnosis of mental illness.
This abstract and the presentation materials are available to members only; a login is required.