Multimodal Swin Transformer with Hyper-Feature and Attention-Gated Clinical Fusion for Skin Lesion Classification
Clinical photographs and patient metadata are complementary sources of information for automated skin lesion classification. In this study, a multimodal framework is proposed that combines Swin Transformer Tiny (Swin-T), Hyper-Feature Fusion (HFF), and Attention-Gated Clinical Metadata Fusion (AGCMF). HFF combines four...