Abstract P5-03-08: Development of a histology-based digital pathology image analysis algorithm for assessment of tumor infiltrating lymphocytes in HER2+ breast cancer

Introduction: Anthracycline-based chemotherapy regimens have been shown to increase risk of cardiac toxicity and other side effects especially in combination with HER2-targeting agents such as trastuzumab. Identification of biomarkers that can predict similar patient benefit in the context of targeted therapy between anthracycline and non-anthracycline-based regimens is attractive for personalized care. Histology-based assessment of tumor infiltrating lymphocytes (TILs) as a surrogate of the host immune response has been shown to be prognostic and potentially chemopredictive in triple-negative and HER2-positive breast cancers; however, the inter-play of TILs, tumor cells, other microenvironment mediators, their spatial relationships, quantity, and other image-based features have yet to be determined exhaustively and systemically. In anticipation of analyzing these aspects in the context of chemo and targeted therapy response in patient sample cohorts, we developed a digital pathology image analysis algorithm to identify tumor, stromal, and lymphocyte cells and acquire respective histology-based image features from hematoxylin and eosin (HE 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P5-03-08.