SG-Fusion: A swin-transformer and graph convolution-based multi-modal deep neural network for glioma prognosis

Minghan Fu, Ming Fang, Rayyan Azam Khan, Bo Liao, Zhanli Hu, Fang-Xiang Wu

Abstract: Highlights•Developed a multi-modal, multi-task framework for glioma diagnosis.•Integrated Swin-Transformer v2 with contrastive learning to enhance image features.•Implemented a novel gene selection method to reduce data redundancy.•Enhanced feature quality with cross-modal attention and divergence regularization.