Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Images

TL;DR

This paper introduces a novel deep learning framework combining tissue segmentation, contrastive feature learning, and multiple instance classification to improve prognostic predictions from histopathological images, validated on bladder cancer data.

Contribution

It presents a new three-part weakly supervised learning framework specifically designed for prognostic prediction using whole slide images, addressing weak labels and future event prediction challenges.

Findings

Achieved AUC of 0.721 for recurrence prediction

Achieved AUC of 0.678 for treatment outcome prediction

Validated on bladder cancer data with promising results

Abstract

We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique challenge as the ground truth labels are inherently weak, and the model must anticipate future events that are not directly observable in the image. To address this challenge, we propose a novel three-part framework comprising of a convolutional network based tissue segmentation algorithm for region of interest delineation, a contrastive learning module for feature extraction, and a nested multiple instance learning classification module. Our study explores the significance of various regions of interest within the histopathological slides and exploits diverse learning scenarios. The pipeline is initially validated on artificially generated data and a simpler diagnostic task. Transitioning to prognostic prediction, tasks become more challenging. Employing bladder cancer as use case, our best models yield an AUC of 0.721 and 0.678 for recurrence and treatment outcome prediction respectively.