期刊
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
卷 241, 期 -, 页码 -出版社
ELSEVIER IRELAND LTD
DOI: 10.1016/j.cmpb.2023.107733
关键词
Survival analysis; Multiple instance learning; Whole slide image; Deep learning interpretation
This paper proposes a highly interpretable neural network model called Surformer for predicting cancer survival from histopathology images. Surformer can quantify specific histological patterns through the use of learnable prototypes and enhance the features using multi-head self-attention mechanisms. Experimental results demonstrate that Surformer outperforms existing methods in terms of prediction accuracy and interpretability.
Background and Objective: High-resolution histopathology whole slide images (WSIs) contain abundant valuable information for cancer prognosis. However, most computational pathology methods for survival prediction have weak interpretability and cannot explain the decision-making processes reasonably. To address this issue, we propose a highly interpretable neural network termed pattern-perceptive survival transformer (Surformer) for cancer survival prediction from WSIs. Methods: Notably, Surformer can quantify specific histological patterns through bag-level labels without any patch/cell-level auxiliary information. Specifically, the proposed ratio-reserved cross-attention module (RRCA) generates global and local features with the learnable prototypes (������������������������������������������, ������������������������������������������) as detectors and quantifies the patches correlative to each ������������������������������������in the form of ratio factors (rfs). Afterward, multi-head self & cross-attention modules proceed with the computation for feature enhancement against noise. Eventually, the designed disentangling loss function guides multiple local features to focus on distinct patterns, thereby assisting ������������ ������from RRCA in achieving more explicit histological feature quantification. Results: Extensive experiments on five TCGA datasets illustrate that Surformer outperforms existing state-of-the-art methods. In addition, we highlight its interpretation by visualizing rfs distribution across high-risk and low-risk cohorts and retrieving and analyzing critical histological patterns contributing to the survival prediction. Conclusions: Surformer is expected to be exploited as a useful tool for performing histopathology image data -driven analysis and gaining new insights for interpreting the associations between such images and patient survival states.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据