The differential diagnosis of proliferative breast lesions, benign usual ductal hyperplasia (UDH) versus malignant ductal carcinoma in situ (DCIS) is challenging. This involves a pathologist examining histopathologic sections of a biopsy using a light microscope, evaluating tissue structures for their architecture or size, and assessing individual cell nuclei for their morphology. Imposing diagnostic boundaries on features that otherwise exist on a continuum going from benign to atypia to malignant is a challenge. Current computational pathology methods have focused primarily on nuclear atypia in drawing these boundaries. In this paper, we improve on these approaches by encoding for both cellular morphology and spatial architectural patterns. Using a publicly available breast lesion database consisting of UDH and three different grades of DCIS, we improve the classification accuracy by 10% over the state-of-the-art method for discriminating UDH and DCIS. For the four way classification of UDH and the three grades of DCIS, our method improves the results by 6% in accuracy, 8% in micro-AUC, and 19% in macro-AUC.
Keywords: Architectural Patterns; Breast Cancer; Classification; Computational Pathology; DCIS.