Abstract #3916

Classification of Schizophrenia with Structural MRI Using 3D-MIGR Transformer

Ye Tian¹, Junhao Zhang¹, Xuemin Zhu¹, Pin-Yu Lee¹, Vishwanatha Mitnala Rao¹, Zhuoyao Xin¹, Andrew F Laine², Scott A Small³, and Jia Guo⁴

¹Columbia University, New York, NY, United States, ²Biomedical Engineering, Columbia University, New York, NY, United States, ³Neurology, Columbia University, New York, NY, United States, ⁴Psychiatry, Columbia University, New York, NY, United States

Synopsis

To detect distinctive structural abnormalities of schizophrenia early in magnetic resonance imaging (MRI) data, we propose a 3D Medical Image Global-Regional (3D-MIGR) Transformer with a VGG11BN backbone followed by a global-regional transformer encoder, which outperforms state-of-the-art models. We trained and tested our model on 887 pre-processed structural whole-head (WH) T1W 3D images from 3 datasets with similar acquisition parameters. 3D-MIGR Transformer improves AUROC to 0.990 and demonstrates strong generality. We found that combining volume-level contextual information with patch-level features enhances performance and allows us to identify ventricle areas as the most informative regions in regional schizophrenia likelihood visualization.

This abstract and the presentation materials are available to members only; a login is required.

Join Here