AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images
This work addresses the problem of patient prognosis estimation in computational pathology by enabling more flexible and robust survival analysis on whole-slide images, though it appears incremental as it builds upon existing MIL-based methods.
The paper tackles the limitations of existing weakly-supervised deep learning models for survival analysis on whole-slide images, which are restricted by classical survival analysis rules and fully-supervised learning requirements, by proposing AdvMIL, an adversarial multiple instance learning framework that improves survival distribution estimation and enables semi-supervised learning, with experiments showing performance improvements for mainstream methods and enhanced robustness against patch occlusion and image noises.
The survival analysis on histological whole-slide images (WSIs) is one of the most important means to estimate patient prognosis. Although many weakly-supervised deep learning models have been developed for gigapixel WSIs, their potential is generally restricted by classical survival analysis rules and fully-supervised learning requirements. As a result, these models provide patients only with a completely-certain point estimation of time-to-event, and they could only learn from the labeled WSI data currently at a small scale. To tackle these problems, we propose a novel adversarial multiple instance learning (AdvMIL) framework. This framework is based on adversarial time-to-event modeling, and integrates the multiple instance learning (MIL) that is much necessary for WSI representation learning. It is a plug-and-play one, so that most existing MIL-based end-to-end methods can be easily upgraded by applying this framework, gaining the improved abilities of survival distribution estimation and semi-supervised learning. Our extensive experiments show that AdvMIL not only could often bring performance improvement to mainstream WSI survival analysis methods at a relatively low computational cost, but also enables these methods to effectively utilize unlabeled data via semi-supervised learning. Moreover, it is observed that AdvMIL could help improving the robustness of models against patch occlusion and two representative image noises. The proposed AdvMIL framework could promote the research of survival analysis in computational pathology with its novel adversarial MIL paradigm.