The researchers from Monash University, Sun Yat-sen University, Beijing Eaglevision Technology, Beijing Tongren Eye Centre, Capital Medical University, and University of Miami Miller School have developed the comprehensive AI retinal expert (CARE) system. The CARE system, according to the researchers, was developed using fundus photography in combination with a deep-learning system, which was trained using data from real-world case studies of retinal disease. It was then externally tested using fundus photographs collected from clinical settings the model would most likely be adopted.  Fundus photography is a process of taking photographs of the interior of the eye through the pupil to screen for retinal diseases. “The CARE system was trained to identify the 14 most common retinal abnormalities using 207,228 colour fundus photographs derived from 16 clinical settings across Asia, Africa, North America, and Europe, with different disease distributions,” Monash University department of electrical and computer systems engineer associate professor Zongyuan Ge said. “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.” The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. From these tests, Ge said 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. “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,” he said. The researchers hope to make CARE commercially available in China and later in the Asia Pacific region, and plan to build out a database of screening images from real-world environments that can be rolled out in clinical settings to better diagnose retinal diseases.  “I hope that through this work we can continue to see technological advancements in this space,” University of Wisconsin-Madison Imaging Diagnostic Center director Amitha Domalpally said.

Aussie researchers using biosensors to investigate ALS diagnosis and treatmentRMIT University researchers train AI to detect early-stage prostate cancerAustralian and New Zealand scientists use AI to predict heart disease risk