Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Images
This work addresses the problem of weak supervision in prognostic prediction for medical imaging, specifically in oncology, though it appears incremental as it builds on existing techniques like contrastive and multiple instance learning.
The paper tackled the challenge of automated prognostic prediction from histopathological images by proposing a three-part deep learning framework, achieving AUCs of 0.721 and 0.678 for recurrence and treatment outcome prediction in bladder cancer.
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.