Exploring Genetic-histologic Relationships in Breast Cancer

TL;DR

This study employs deep learning on breast cancer histopathology images to predict genomic biomarkers and understand their morphological manifestations, enhancing diagnostic and prognostic capabilities.

Contribution

It introduces a novel deep learning approach that outperforms previous methods in predicting genomic biomarkers from histopathology images and provides insights into underlying morphological features.

Findings

Achieved up to 0.13 AUROC score improvement over existing methods

Identified morphological features like lymphocytes and karyorrhexis linked to biomarkers

Developed a fully automated workflow adaptable to other cancer types

Abstract

The advent of digital pathology presents opportunities for computer vision for fast, accurate, and objective solutions for histopathological images and aid in knowledge discovery. This work uses deep learning to predict genomic biomarkers - TP53 mutation, PIK3CA mutation, ER status, PR status, HER2 status, and intrinsic subtypes, from breast cancer histopathology images. Furthermore, we attempt to understand the underlying morphology as to how these genomic biomarkers manifest in images. Since gene sequencing is expensive, not always available, or even feasible, predicting these biomarkers from images would help in diagnosis, prognosis, and effective treatment planning. We outperform the existing works with a minimum improvement of 0.02 and a maximum of 0.13 AUROC scores across all tasks. We also gain insights that can serve as hypotheses for further experimentations, including the presence of lymphocytes and karyorrhexis. Moreover, our fully automated workflow can be extended to other tasks across other cancer subtypes.