Researchers from Australia, China and the United States have developed one artificial intelligence (AI) system that can detect and monitor diseases of the retina on a larger scale.
Researchers from Monash University, Sun Yat-sen University, Beijing Eaglevision Technology, Beijing Tongren Eye Center, Capital Medical University and the University of Miami Miller School developed a new integrated AI system (CARE) for retinal diseases.
The CARE system, according to the researchers, was developed using fundus photography in combination with a deep-learning system, who was trained using data from real case studies with retinal diseases.
The Fundus photography is a procedure of taking pictures of the inside of the eye through the pupil of the eye, for the examination of retinal diseases.
"The CARE AI system is trained to detect the 14 most common diseases of the retina using 207.228 fundus photographs from 16 clinics in Asia, Africa, North America and Europe", Said the associate professor Zongyuan Ge.
CARE has been tested using thousands of photographs collected from 35 medical facilities across China, including hospitals and physical examination centers.
CARE performance was compared with that of 16 ophthalmologists and tested using datasets of non-Chinese ethnicities. From these tests, Ge said the performance of the CARE system was similar to that of professional ophthalmologists.
"These findings show that the AI system is accurate compared to the results of a professional and could allow conduct more tests on a larger scale", he said.
Researchers hope to do CARE commercially available in China and later in the Asia-Pacific region and plan to create a database of screening images from real environments that can be made available to hospitals for better diagnosis of retinal diseases.
"I hope that through this work we will be able to continue to see technological developments in this area.Said the director of the University of Wisconsin-Madison Imaging Diagnostic Center, Amitha Domalpally.