[KEYNOTE] AI in Digital Pathology: Closing the Gap Between the Research Lab and the Clinic

One of the main advantages of adopting a digital workflow in pathology is the ability to use computers to analyze microscopy images, reducing the workoad of pathologists. Advances in Artificial Intelligence over the last 10 years have made it possible to count cells, detect tumors and classify disease with accuracy approaching, or even surpassing, that of pathologists. It is even possible for AI models to predict patient outcomes by assessing imaging features not discernable to the human eye. The first part of the talk will introduce the main AI methods and explore some of the exciting applications in digital pathology. Despite this rapid progress, the number of applications where pathologists are able to make use of AI in their routine workflow is relatively small and there are still many barriers to overcome before AI reaches its full potential. In the second half of this talk I will delve into the challenges faced when translating algorithms developed in the research lab- into clinical settings and explore potential solutions.

Learning Objectives

1. Be familiar with some of the applications of AI in digital pathology
2. Have an awareness of some of the different kinds of AI models used in DP
3. Be aware of some of the challenges in deploying AI in a clinical setting