End-to-end Learning for Image-based Detection of Molecular Alterations in Digital Pathology

TL;DR

This paper introduces an end-to-end deep learning method for classifying whole slide images in digital pathology that predicts molecular alterations without needing auxiliary labels, achieving high accuracy across multiple cancer types.

Contribution

The authors present a novel end-to-end training pipeline for WSI classification that eliminates the need for auxiliary annotations, simplifying the process and maintaining competitive performance.

Findings

Achieved up to 94% AUC in molecular alteration prediction.

Performed well across colorectal, lung, and breast cancer datasets.

Outperformed traditional two-stage methods in some cases.

Abstract

Current approaches for classification of whole slide images (WSI) in digital pathology predominantly utilize a two-stage learning pipeline. The first stage identifies areas of interest (e.g. tumor tissue), while the second stage processes cropped tiles from these areas in a supervised fashion. During inference, a large number of tiles are combined into a unified prediction for the entire slide. A major drawback of such approaches is the requirement for task-specific auxiliary labels which are not acquired in clinical routine. We propose a novel learning pipeline for WSI classification that is trainable end-to-end and does not require any auxiliary annotations. We apply our approach to predict molecular alterations for a number of different use-cases, including detection of microsatellite instability in colorectal tumors and prediction of specific mutations for colon, lung, and breast cancer cases from The Cancer Genome Atlas. Results reach AUC scores of up to 94% and are shown to be competitive with state of the art two-stage pipelines. We believe our approach can facilitate future research in digital pathology and contribute to solve a large range of problems around the prediction of cancer phenotypes, hopefully enabling personalized therapies for more patients in future.