Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains
| Autor: | Michael F. Press, Ali Madani, Nitish Shirish Keskar, David B. Agus, Daniel Ruderman, Nikhil Naik, Richard Socher, Andre Esteva |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Oncology Receptors Steroid medicine.medical_specialty Receptor Status Science H&E stain General Physics and Astronomy Breast Neoplasms Article General Biochemistry Genetics and Molecular Biology 03 medical and health sciences Breast cancer Deep Learning 0302 clinical medicine Internal medicine Machine learning Humans Medicine Receptor lcsh:Science Estrogen Receptor Status Neoplasm Grading Multidisciplinary Staining and Labeling business.industry General Chemistry medicine.disease 030104 developmental biology Hormone receptor Area Under Curve 030220 oncology & carcinogenesis Immunohistochemistry Female lcsh:Q business |
| Zdroj: | Nature Communications, Vol 11, Iss 1, Pp 1-8 (2020) Nature Communications |
| ISSN: | 2041-1723 |
| Popis: | 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. Determination of estrogen receptor status (ERS) in breast cancer tissue requires immunohistochemistry, which is sensitive to the vagaries of sample processing and the subjectivity of pathologists. Here the authors present a deep learning model that determines ERS from H&E stained tissue, which could improve oncology decisions in under-resourced settings. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|