Current histopathological diagnosis involves human expert interpretation of stained images for diagnosis. This process is prone to inter-observer variability, often leading to low concordance rates amongst pathologists across many types of tissues. Further, since structural features are mostly just defined for epithelial alterations during tumor progression, the use of associated stromal changes is limited. Here we sought to examine whether digital analysis of commonly used hematoxylin and eosin-stained images could provide precise and quantitative metrics of disease from both epithelial and stromal cells. We developed a convolutional neural network approach to identify epithelial breast cells from their microenvironment. Second, we analyzed the microenvironment to further observe different constituent cells using unsupervised clustering. Finally, we categorized breast cancer by the combined effects of stromal and epithelial inertia. Together, the work provides insight and evidence of cancer association for interpretable features from deep learning methods that provide new opportunities for comprehensive analysis of standard pathology images.
Keywords: breast cancer; deep learning; ductal carcinoma in-situ; hyperplasia and clustering; microenvironment.
Copyright © 2019 Mittal, Stoean, Kajdacsy-Balla and Bhargava.