hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images

SIMPLE SUMMARY: Breast cancer diagnosis and treatment can be improved by understanding the specific genetic makeup of a patient’s tumour. Currently, this genetic information is obtained through expensive and time-consuming molecular tests, which are not widely reimbursed by healthcare systems. To address this issue, we propose a new, computationally efficient deep learning based method called hist2RNA to predict the expression of genes using digital images of stained tissue samples. Our approach successfully predicts gene expression and identifies breast cancer subtypes, enabling personalized treatments, thereby improving patient survival and overall breast cancer management. ABSTRACT: Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12–3.06), p < 5 × 10(−3)), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30–2.68), p < 5 × 10(−3)). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing.