Communications of the ACM
Researchers Develop AI System to Improve Eye Disease Detection
Monash University's Zongyuan Ge said, "These findings indicate that the system is accurate when compared to the outcomes of a professional and could allow for more testing to be carried out on a larger scale."
Credit: ZDNet
The comprehensive artificial intelligence retinal expert (CARE) system developed by Australian, Chinese, and U.S. researchers can detect and monitor eye diseases, according to its developers.
Zongyuan Ge at Australia's Monash University said, "The CARE system was trained to identify the 14 most common retinal abnormalities using 207,228 color fundus photographs derived from 16 clinical settings across Asia, Africa, North America, and Europe, with different disease distributions."
The researchers externally tested the system using fundus photos from clinical environments in China; Ge said its performance was comparable to that of professional ophthalmologists, and remained strong when tested on datasets with non-Chinese ethnicities and previously unused camera types.
Ge said the results indicated the CARE system "could allow for more testing to be carried out on a larger scale."
From ZDNet
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found