Clinical utility of receptor status prediction in breast cancer and misdiagnosis identification using deep learning on hematoxylin and eosin-stained slides
Open Access
- 20 December 2024
- journal article
- research article
- Published by Springer Nature in Communications Medicine
- Vol. 4 (1) , 1-16
Abstract
Background Molecular profiling of estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (also known as Her2) is essential for breast cancer diagnosis and treatment planning. Nevertheless, current methods rely on the qualitative interpretation of immunohistochemistry and fluorescence in situ hybridization (FISH), which can be costly, time-consuming, and inconsistent. Here we explore the clinical utility of predicting receptor status from digitized hematoxylin and eosin-stained (H&E) slides using machine learning trained and evaluated on a multi-institutional dataset. Methods We developed a deep learning system to predict ER, PR, and ERBB2 statuses from digitized H&E slides and evaluated its utility in three clinical applications: identifying hormone receptor-positive patients, serving as a second-read tool for quality assurance, and addressing intratumor heterogeneity. For development and validation, we collected 19,845 slides from 7,950 patients across six independent cohorts representative of diverse clinical settings. Results Here we show that the system identifies 30.5% of patients as hormone receptor-positive, achieving a specificity of 0.9982 and a positive predictive value of 0.9992, demonstrating its ability to determine eligibility for hormone therapy without immunohistochemistry. By restaining and reassessing samples flagged as potential false negatives, we discover 31 cases of misdiagnosed ER, PR, and ERBB2 statuses. Conclusions These findings demonstrate the utility of the system in diverse clinical settings and its potential to improve breast cancer diagnosis. Given the substantial focus of current guidelines on reducing false negative diagnoses, this study supports the integration of H&E-based machine learning tools into workflows for quality assurance.Keywords
This publication has 34 references indexed in Scilit:
- The spectrum of HER2 expression in breast cancer: linking immunohistochemistry quantification with in situ hybridization assayVirchows Archiv, 2022
- Outcome of breast cancer patients with low hormone receptor positivity: analysis of a 15-year population-based cohortAnnals of Oncology, 2021
- An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment studyThe Lancet Digital Health, 2020
- ESR1 mutations in breast cancerCancer, 2019
- Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast CancerJAMA Network Open, 2019
- Update on tumor-infiltrating lymphocytes (TILs) in breast cancer, including recommendations to assess TILs in residual disease after neoadjuvant therapy and in carcinoma in situ: A report of the International Immuno-Oncology Biomarker Working Group on Breast CancerSeminars in Cancer Biology, 2018
- Identity Mappings in Deep Residual Networks2016
- Lobular breast cancer: Clinical, molecular and morphological characteristicsPathology - Research and Practice, 2016
- A meta-analysis on concordance between immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH) to detect HER2 gene overexpression in breast cancerBreast Cancer, 2014
- A retrospective review with long term follow up of 11,400 cases of pure mucinous breast carcinomaBreast Cancer Research and Treatment, 2007