LAUSR

Rendering cancer diagnoses from tissues is a highly complex process that requires many years of expert training. It involves challenging tasks for pathologists, such as identifying rare events in very large images (e.g., micrometastases in lymph nodes) or classifying subtle differences between normal vs tumor or among similar-looking tumors that have very different treatment plans. These tasks are typically more challenging for human cognition, and, consequently, over- and underdiagnoses are not uncommon, resulting in nonoptimal treatment selection. Deep learning, a type of machine intelligence, has been successfully applied to solve similar identification and classification problems for Gmail, Google Maps, Google Photos, Google Translate, etc., and may have the potential to solve these similar challenges in the practice of pathology and help improve patient9s diagnoses. This talk will begin by providing a brief background on deep learning and how it has been utilized at Google for health care and non-health care applications. The latter half of the talk will discuss the potential of deep learning to improve the accuracy and efficiency of the pathology workflow while highlighting recent advances towards that goal. Citation Format: Jason D. Hipp, Martin Stumpe. Advancing cancer diagnostics with artificial intelligence [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr PL02-01.