LAUSR

Survival analysis is a branch of statistics to analyze the time duration that is expected until some events of interest happen, like the death in the organisms of biology. Currently, survival analysis based on pathological images has turned out to be a truly energetic area in the research of healthcare for making primary decisions on therapy and improving patients’ quality of treatment. In this regard, the interest to design convolutional neural networks for survival analysis with pathological images is increasing greatly at present. Furthermore, to consider the important spatial hierarchies between features and improve the robustness to affine transformation, capsule network (referred to as CapsNet) has been put forward in recent years. A novel capsule network named CapSurv is introduced in this paper, with a new loss function named survival loss to make survival analysis with whole slide pathological images. In addition, to train CapSurv preferably, semantic-level features extracted by VGG16, are used to distinguish discriminative patches from whole slide pathological images. Our method is applied to the predictions of the survival of glioblastoma and lung squamous cell carcinoma with a public cancer dataset. The results illustrate the proposed CapSurv model has the ability to improve the performance of the prediction by comparing with state-of-the-art survival models.