Explainable survival analysis with uncertainty using convolution-involved vision transformer

Zhihao Tang, Li Liu, Yifan Shen, Zongyi Chen, Guixiang Ma, Jiyan Dong, Xujie Sun, Xi Zhang, Chaozhuo Li, Qingfeng Zheng, Lin Yang

Abstract: Highlights•Without patching WSIs, a novel ViT-based model is proposed for survival predictions.•We first introduce aleatoric uncertainty into the survival loss function.•We explain survival prediction using a post-hoc explainable method.•Our method outperforms baselines in accuracy, explainability, and reliability.