Melbourne’s Monash University has contributed to an international project that successfully applied artificial intelligence (AI) technology to real-world retinal imagery, which may be able to detect diseases more accurately and on a larger scale.
The Comprehensive AI Retinal Expert (CARE) system was developed by an international group of researchers from Sun Yat-sen University, Beijing Eaglevision Technology (Airdoc), Monash University, University of Miami Miller School of Medicine, Beijing Tongren Eye Centre and Capital Medical University.
Following the results – published in The Lancet Digital Health – study authors expect the system could soon be adopted in medical settings across China and later in the Asia Pacific region.
Associate Professor Zongyuan Ge, from the Department of Electrical and Computer Systems Engineering at Monash University and the Monash Data Futures Institute, said the researchers trained a clinically applicable deep-learning system for fundus diseases using data derived from real world case studies, and then externally tested the model using fundus photographs collected from clinical settings in China.
The CARE system was developed to identify the 14 most common retinal abnormalities that included conditions such as referable diabetic retinopathy, retinal drusen, macular hole, and geographic atrophy. It was trained using 207,228 colour fundus photographs derived from 16 clinical settings across Asia, Africa, North America and Europe, with different disease distributions.
“CARE was internally validated using 21,867 photographs and externally tested using 18,136 photographs prospectively collected from 35 real-world settings across China, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres,” Ge said.
Further, CARE’s performance was compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types.
“We also found that the performance of the CARE system was similar to that of professional ophthalmologists and the system retained strong identification performance when tested using the non-Chinese datasets,” 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.”
Ms Amitha Domalpally, director of the University of Wisconsin-Madison Imaging Diagnostic Center, said the research was a step in the right direction for medical and artificial intelligence research.
“I hope that through this work we can continue to see technological advancements in this space,” she added.
The research will also build out a database of screening images from real-world environments that can be rolled out in clinical settings to better diagnose retinal diseases.
More reading