Deep Learning for Identifying Metastatic Breast Cancer

TL;DR

This paper presents a deep learning system that significantly improves the accuracy of detecting metastatic breast cancer in pathology images, outperforming human pathologists and reducing diagnostic errors.

Contribution

The authors developed a deep learning approach that achieved top performance in a grand challenge for breast cancer metastasis detection, surpassing previous methods and enhancing diagnostic accuracy.

Findings

Deep learning achieved AUC of 0.925 for classification

Combined system and pathologist reached AUC of 0.995

Deep learning reduced human error rate by approximately 85%

Abstract

The International Symposium on Biomedical Imaging (ISBI) held a grand challenge to evaluate computational systems for the automated detection of metastatic breast cancer in whole slide images of sentinel lymph node biopsies. Our team won both competitions in the grand challenge, obtaining an area under the receiver operating curve (AUC) of 0.925 for the task of whole slide image classification and a score of 0.7051 for the tumor localization task. A pathologist independently reviewed the same images, obtaining a whole slide image classification AUC of 0.966 and a tumor localization score of 0.733. Combining our deep learning system's predictions with the human pathologist's diagnoses increased the pathologist's AUC to 0.995, representing an approximately 85 percent reduction in human error rate. These results demonstrate the power of using deep learning to produce significant improvements in the accuracy of pathological diagnoses.