Breast Cancer Recurrence Risk Prediction Based on Multiple Instance Learning

TL;DR

This study develops and compares multiple deep learning frameworks based on Multiple Instance Learning to predict breast cancer recurrence risk from routine histology slides, achieving promising accuracy and AUC scores.

Contribution

Introduces and evaluates three MIL-based deep learning models for breast cancer risk prediction using WSIs, demonstrating feasibility and superior performance of the modified CLAM-SB model.

Findings

Modified CLAM-SB achieved AUC of 0.836

Model accuracy reached 76.2%

Deep learning can effectively stratify risk from standard histology slides

Abstract

Predicting breast cancer recurrence risk is a critical clinical challenge. This study investigates the potential of computational pathology to stratify patients using deep learning on routine Hematoxylin and Eosin (H&E) stained whole-slide images (WSIs). We developed and compared three Multiple Instance Learning (MIL) frameworks -- CLAM-SB, ABMIL, and ConvNeXt-MIL-XGBoost -- on an in-house dataset of 210 patient cases. The models were trained to predict 5-year recurrence risk, categorized into three tiers (low, medium, high), with ground truth labels established by the 21-gene Recurrence Score. Features were extracted using the UNI and CONCH pre-trained models. In a 5-fold cross-validation, the modified CLAM-SB model demonstrated the strongest performance, achieving a mean Area Under the Curve (AUC) of 0.836 and a classification accuracy of 76.2%. Our findings demonstrate the feasibility of using deep learning on standard histology slides for automated, genomics-correlated risk stratification, highlighting a promising pathway toward rapid and cost-effective clinical decision support.