AIMI Research Group Meeting: Medical Sieve: The Radiology Grand Challenge, Tanveer Syeda-Mahmood, PhD

This event is for the Stanford community.

Medical Sieve: The Radiology Grand Challenge

With advances in machine learning and artificial intelligence, a new role is emerging for machines as intelligent assistants to radiologists in their clinical workflows. After the success of Watson Jeopardy challenge, IBM Researchers have been engaged in a new radiology grand challenge to build machines with offer provably good capabilities for being eligible to serve as cognitive assistants. The resulting work has advanced research in many fronts including new multimodal deep learning networks, clinical knowledge, clinical reasoning/inference, text analytics, crowd-sourced annotation platforms, evaluation methodologies and clinical studies. It has also spurred new look at federated AI in building robust algorithms, and the development of AI commons with co-learning for auto labeling. In this talk I will give an overview of the progress made in this area in my research lab with a focus on the chest X-ray challenge. I will also outline some of the new research ideas I would like to explore during my sabbatical here at Stanford and invite suggestions for new work in the areas of clinical decision support and understanding disease mechanisms across imaging scales.