Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains

TLDR

Estrogen receptor status is a critical prognostic marker in breast cancer, but its current determination via immunohistochemistry is costly, time‑consuming, and variable, whereas hematoxylin‑and‑eosin staining offers a faster, cheaper alternative. The study demonstrates that machine learning can infer hormone receptor status directly from cellular morphology in H&E‑stained breast cancer tissue. A multiple‑instance learning deep neural network was trained on whole‑slide images to predict ER status. On a multi‑country cohort of 3,474 patients, the model achieved an AUC of 0.92, indicating high accuracy and potential clinical utility.

Abstract

Abstract For newly diagnosed breast cancer, estrogen receptor status (ERS) is a key molecular marker used for prognosis and treatment decisions. During clinical management, ERS is determined by pathologists from immunohistochemistry (IHC) staining of biopsied tissue for the targeted receptor, which highlights the presence of cellular surface antigens. This is an expensive, time-consuming process which introduces discordance in results due to variability in IHC preparation and pathologist subjectivity. In contrast, hematoxylin and eosin (H&E) staining—which highlights cellular morphology—is quick, less expensive, and less variable in preparation. Here we show that machine learning can determine molecular marker status, as assessed by hormone receptors, directly from cellular morphology. We develop a multiple instance learning-based deep neural network that determines ERS from H&E-stained whole slide images (WSI). Our algorithm—trained strictly with WSI-level annotations—is accurate on a varied, multi-country dataset of 3,474 patients, achieving an area under the curve (AUC) of 0.92 for sensitivity and specificity. Our approach has the potential to augment clinicians’ capabilities in cancer prognosis and theragnosis by harnessing biological signals imperceptible to the human eye.