Back To Schedule
Saturday, October 20 • 4:30pm - 5:00pm
Real-time Application of Deep Learning in Colonoscopy

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Until recently, AI has not impacted time-sensitive procedures such as colonoscopy, during which potentially precancerous lesions can be missed in the blink of an eye. We will present our development and validation of multiple real-time AIs during colonoscopy to improve procedure quality and eliminate colorectal cancer. We envision a future where doctors can be doctors, and focus on the patient while letting AI take care of the rest. To that effect, we are developing AI differently, with a focus on assisting with the simplest and most important tasks.

Algorithm development is the first step, but making it function smoothly in a physician's already busy workflow is the biggest challenge. Toward that end, we've designed a new system architecture that enables several AIs to run simultaneously in real-time with no lag or framedrop, and have designed the AI to integrate seamlessly into workflow to reduce redundacy of documentation and can be turned on with a single button press.

avatar for William Karnes

William Karnes

Chief Medical Officer/ Clinical Professor, UC Irvine
I am a gastroenterologist with a primary interest in colorectal cancer prevention. After several years as Director of Research in the Colorectal Neoplasia Clinic at the Mayo Clinic, I was recruited to UCI in 2012 to spearhead efforts to reduce colorectal cancer burden in Orange County... Read More →

Saturday October 20, 2018 4:30pm - 5:00pm PDT
Ballroom # 403A + Conference Registration + Open talk