An Explainable Coarse-to-Fine Survival Analysis Method on Multi-Center Whole Slide Images

Survival models based on whole slide images (WSIs) arewidely used in precision medicine to treat cancer patients better. Most previous studies attempted to address the challenge ofWSIs' gigapixel resolutions to survival models, but they failed in terms of computational efficiency and interpretability ofmodels. This study proposes a coarse-to-fine survival model called WSISur based on graph neural networks, which not only solves the above two problems but also achieves the best survival prediction performance. To solve the issue of computational efficiency, coarse WSI graphs are first constructed on low-resolution images in WSIs, and then fine WSI graphs are built with high-resolution images on the basis of coarse WSI graphs. Subsequent survival analysis is performed on the constructed WSI graphs. To solve the issue of interpretability of the model,WSIs' regions most relevant to patients' lifetimes are identified by gradient-weighted class activation mapping. Nevertheless, due to the imbalance of data labels, there is a problem of probability failure in end-to-end mini-batch training. To this end, a survival event sampling strategy is proposed to balance data labels. In addition, a series of experiments are carried out on multicenter datasets to evaluate the proposed model.Experimental results show that WSISur achieves the state-of-the-art result compared with other existing related methods, and has stronger domain invariance. Results also demonstrate the interpretability of WSISur. Impact Statement-Survival models based on WSI play an important role in precision medicine. Existing WSI based survival models have lowcomputational efficiency and lack of interpretability. A novel survival model we propose in this study overcomes these limitations. The proposed survival model is not only computationally efficient but also interpretable. Moreover, the proposed survival model also shows a performance improvement of nearly 23%~29% over existing methods on multi-center datasets.