Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy

Abstract

The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin–eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning–predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63–0.77) on 354 TMA samples and 0.67 (95% CI, 0.62–0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology–based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15–0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.

Machine-Learning–Based Evaluation of Intratumoral Heterogeneity and Tumor-Stroma Interface for Clinical Guidance

“…ERBB2 amplificationeassociated morphology extracted from H&E images of breast cancer also correlated with the efficacy of adjuvant trastuzumab therapy and had a favorable effect on distant disease-free survival in CISH ERBB2-positive patients. 44 Another deep-learning model exceeded the performance of experienced gastrointestinal pathologists predicting microsatellite instability from H&Estained WSIs. 45 More importantly, these methods also allowed localization of the tumor areas responsible for this classification, which help in highlighting biologically and clinically relevant ITH aspects of the tumor morphology.…”

Weakly supervised annotation‐free cancer detection and prediction of genotype in routine histopathology

“…Recent studies have shown that a wide range of molecular features, including MSI/dMMR status and BRAF mutational status, can be predicted from digitized slides of CRC using deep learning, an artificial intelligence technology [9][10][11][12][13][14]. The application of such methods is not limited to CRC but has been demonstrated in bladder cancer [15], breast cancer [16,17], sarcoma [18], head and neck cancer [19], hepatocellular carcinoma [20], and several other types of solid tumor [8,12]. Therefore, in the future, deep learning could supplement current molecular testing strategies in solid tumors and could be used as a tool for translational research [21].…”

Comparative analysis of molecular representations in prediction of drug combination effects

“…Finally, we hope that in the future biomedical DL research will go beyond representation learning and will be used to derive novel biological knowledge by e.g. inferring synthetic and retrosynthetic chemical reactions, identifying novel diseaseassociated druggable proteins and clinically actionable biomarkers [129][130][131].…”