An Uncertainty-Guided Evidential Deep Learning Framework for Reliability-Aware Multimodal Fusion in Cancer Prognosis
REM-Fuse is introduced, an evidential deep learning framework in which per-source Dirichlet uncertainty adaptively weights each source through dual-channel weighting, asymmetric cross-scale enhancement, and Dempster–Shafer-inspired evidence accumulation that provides a compact reliability-aware fusion strategy for cancer prognosis.