CERA researchers awarded NHMRC grants for artificial intelligence in eye healthAugust 30, 2019
Professor Mingguang He and Dr Stuart Keel have been awarded National Health and Medical Research Council (NHMRC) Investigator Grants to further their work improving eye health services.
These grants will provide funding for five years, supporting innovative research to improve screening for major eye diseases in Australia, particularly through artificial intelligence (AI).
“Stuart and Ming are undertaking research at the leading edge of artificial intelligence and its real-world application to improve eye health care delivery,” says Professor Keith Martin, CERA Managing Director.
“NHMRC Investigator Grant support will enable our researchers to continue to advance this important area of research.”
Artificial intelligence for eye screening
Professor He says artificial intelligence has the potential to increase access to eye screening, leading to earlier diagnosis and treatment.
“Vision impairment and blindness are major public health problems in Australia, with up to 50% of major eye diseases remaining undiagnosed,” says Professor He.
“Artificial intelligence has the potential to close the gap in eye care services, considerably increase early diagnosis of the four most common blinding eye diseases and reduce the burden of vision loss in the Australian communities that need it the most.”
Professor He has led a team of researchers to develop and pilot test an automated AI screening tool, designed to give GPs and endocrinologists a quick and simple way to detect signs of diabetic retinopathy, glaucoma, age-related macular degeneration (AMD) and cataracts.
The tool is currently being tested in real-world settings, including endocrinology and primary care clinics in metropolitan, regional and Aboriginal health services in Australia.
Predicting eye disease progression
Next, with the support of the NHMRC Investigator Grant, Professor He intends to develop an advanced AI system that could help predict the likely progression of eye disease.
“The full potential of an AI application such as this is yet to be fully realised,” says Professor He.
“In the next 5 years, I aim to further evolve this deep learning technology to develop and validate a clinical decision system that is able to predict disease outcomes and prognosis.
“This system will help clinicians decide the best treatment option, based on real-world multi-modality clinical data.”
The current system can make a binary classification of specific eye diseases – for example, it might give a classification of no glaucoma, probable glaucoma or certain glaucoma. However, severity is based on a single image modality, fundus photography.
Professor He is striving to create a tool that could provide a more detailed classification – for example, showing what type of glaucoma is present, and how likely it is to progress.
“This would require access to data from additional imaging modalities such as visual field, ocular coherence tomography (OCT), as well as real-world clinical data in text format, and to use this data to train a new AI algorithm to build a clinical decision system.
“This system will use one particular disease domain, for example glaucoma, and will further expand to other diseases using the same framework and strategies when validation is proven.”
Dr Keel is the proud recipient of an Emerging Leader Fellowship from the NHMRC. The award follows his success in co-leading the National Eye Health Survey and his achievements in studying the application of artificial intelligence in clinical settings.
In recognition of his rising trajectory, Dr Keel was recently appointed as a Principal Investigator at CERA and was the recipient of research grant funding from the Juvenile Diabetes Research Foundation and the Melbourne Academic Centres for Health.
With the support of this NHMRC Fellowship, Dr Keel will continue his focus on diabetic eye disease, with the goal of improving the uptake of regular eye screening by Australians with diabetes.
A key component will include evaluating the effectiveness of KeepSight, a new national eye screening program and applying these findings into evidence-based program improvements.
He will also continue his research into the clinical adoption of AI systems for diabetic retinopathy screening, including in regional and remote locations.
Dr Keel has recently taken up a prestigious role with the World Health Organisation in Geneva, working on the World Report on Vision and designing and testing eye health initiatives. He plans to take up his fellowship on his return to CERA.
Congratulations to Professor He and Dr Keel on their success!