At present, the training pathway for artificial intelligence to interpret medical images is straightforward: show the AI medical images labeled with features of interest, like cancerous lesions, in large enough quantities for the system to identify patterns that allow it to “see” those features in unlabeled images.
Despite more than 14,000 academic papers having been published on AI and radiology in the last decade, the results are largely inaccurate.
“Neural networks easily overfit on spurious correlations,” says Mark Yatskar, assistant professor in computer and information science (CIS) in the School of Engineering and Applied Science, referring to the AI architecture that emulates biological neurons and powers tools as varied as ChatGPT and image-recognition software. “Instead of how a human makes the decisions, it will take shortcuts.”
In a new paper, Yatskar, together with Chris Callison-Burch, professor in CIS, and first author Yue Yang, a doctoral student advised by Callison-Burch and Yatskar, introduces a novel means of developing neural networks for medical image recognition by emulating the training pathway of human physicians. “Generally, with AI systems, the procedure is to throw a lot of data at the AI system, and it figures it out,” says Yatskar. “This is actually very unlike how humans learn—a physician has a multistep process for their education.”
The team’s new method effectively takes AI to medical school by providing a set body of medical knowledge culled from textbooks, from PubMed, the academic database of the National Library of Medicine, and from StatPearls, an online company that provides practice exam questions for medical practitioners. “Doctors spend years in medical school learning from textbooks and in classrooms before they begin their clinical training in earnest,” points out Yatskar. “We’re trying to mirror that process.”
Read more at Penn Engineering.
