Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-Based Tool.

Abstract

Accurate recurrence risk stratification is crucial for optimizing treatment plans for breast cancer patients. Current prognostic tools like Oncotype DX offer valuable genomic insights into hormone receptor-positive and human epidermal growth factor receptor-negative patients but are limited by cost and accessibility, particularly in underserved populations. In this study, we present Deep-Breast-Cancer-Recurrence (BCR)-Auto, a deep learning-based computational pathology approach that predicts breast cancer recurrence risk from routine hematoxylin and eosin-stained whole slide images. Our methodology was validated on 2 independent cohorts: The Cancer Genome Atlas Program breast cancer data set and an in-house data set from The Ohio State University. Deep-BCR-Auto demonstrated robust performance in stratifying patients into low- and high-recurrence risk categories. On The Cancer Genome Atlas Program breast cancer data set, the model achieved an area under the receiver operating characteristic curve of 0.827, significantly outperforming the existing weakly supervised models (P = .041). In the independent The Ohio State University data set, Deep-BCR-Auto maintained strong generalizability, achieving an area under the receiver operating characteristic curve of 0.832, along with 82.0% accuracy, 85.0% specificity, and 67.7% sensitivity. These findings highlight the potential of computational pathology as a cost-effective alternative for recurrence risk assessment, broadening access to personalized treatment strategies. This study underscores the clinical utility of integrating deep learning-based computational pathology into routine pathological assessment for breast cancer prognosis across diverse clinical settings.