Assessing the risk of recurrence in early-stage breast cancer through H&E stained whole slide images

2024-06-10

AI Summary

This study addresses the challenge of non-invasive, cost-effective stratification of early breast cancer recurrence risk using routine hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) alone. We propose an end-to-end deep learning framework that approximates molecular-level risk assessment without requiring genomic testing. Methodologically, we innovatively integrate multi-center WSI data and validate consistency with clinical-pathological indicators—particularly histologic grade—via Pearson correlation analysis. To enhance interpretability, we incorporate class activation mapping (CAM) to localize prognostically salient features, including glandular architecture and mitotic activity. Our model achieves 0.857 sensitivity and 0.972 specificity in three-class recurrence risk prediction, with a correlation coefficient of 0.61 against histologic grade. These results significantly extend the applicability of digital pathology in precision prognostication, demonstrating robust generalizability across institutions and clinical relevance without ancillary molecular assays.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Accurate prediction of the likelihood of recurrence is important in the selection of postoperative treatment for patients with early-stage breast cancer. In this study, we investigated whether deep learning algorithms can predict patients' risk of recurrence by analyzing the pathology images of their cancer histology.We analyzed 125 hematoxylin and eosin-stained whole slide images (WSIs) from 125 patients across two institutions (National Cancer Center and Korea University Medical Center Guro Hospital) to predict breast cancer recurrence risk using deep learning. Sensitivity reached 0.857, 0.746, and 0.529 for low, intermediate, and high-risk categories, respectively, with specificity of 0.816, 0.803, and 0.972, and a Pearson correlation of 0.61 with histological grade. Class activation maps highlighted features like tubule formation and mitotic rate, suggesting a cost-effective approach to risk stratification, pending broader validation. These findings suggest that deep learning models trained exclusively on hematoxylin and eosin stained whole slide images can approximate genomic assay results, offering a cost-effective and scalable tool for breast cancer recurrence risk assessment. However, further validation using larger and more balanced datasets is needed to confirm the clinical applicability of our approach.

Problem

• Predict breast cancer recurrence risk using H&E slide images
• Evaluate deep learning for risk stratification accuracy
• Compare model performance with genomic assay results

Innovation

• Deep learning predicts breast cancer recurrence risk
• Analyzes H&E stained whole slide images
• Offers cost-effective alternative to genomic assays