Jun 18, 2019
Today we’re joined by Judy Gichoya an interventional radiology fellow at the Dotter Institute at Oregon Health and Science University. In our conversation, we discuss:
• Judy's research in “Phronesis of AI in Radiology: Superhuman meets Natural Stupidy,” reviewing the claims of “superhuman” AI performance in radiology.
• We explore potential roles in which AI can have success in radiology, along with some of the different types of biases that can manifest themselves across multiple use cases.
• We look at the CheXNet paper, which details how human and AI performance can complement and improve each other's performance for detecting pneumonia in chest X-rays.
The complete show notes can be found at twimlai.com/talk/275.
Visit twimlcon.com to learn more about the TWIMLcon: AI Platforms conference!