Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Algorithm able to diagnose AMD as well as human specialists

An artificial intelligence (AI) machine-learning algorithm can detect age-related macular degeneration (AMD) as accurately as human specialists, Johns Hopkins University researchers have said.

Scientists from the university’s Applied Physics Laboratory (APL) collaborated with the School of Medicine created a deep learning-based machine grading method to automatically assess AMD from fundus images.

“We’ve been able to show the feasibility of automated fine-grained classification of AMD severity that only highly trained ophthalmologists can achieve,” co-principal investigator Dr Philippe Burlina said.

“These techniques have the potential to provide individuals with automated grading of images to identify AMD, or monitor those individuals with earlier stages of AMD for the onset of the more advanced stages when prompt treatment may be indicated to reduce the risk of blindness.”

"We were able to show that machines can do as well as humans for diagnosing AMD."
Philippe Burlina, Co-principal investigator at Johns Hopkins University

The team has also expanded its inquiry to characterise retinal layers in optical coherence tomography (OCT) to diagnose other retinal diseases such as diabetic retinopathy. These techniques have the potential to diagnose vascular and neurodegenerative disorders.

“We were able to show that machines can do as well as humans for diagnosing AMD,” Burlina said.

“We have started looking at other retinal diseases, and how to combine images with other sources of information – demographics, lifestyle factors such as smoking, and sunlight exposure – to automatically perform prognosis and predict the probability for five-year risk of developing the advanced form of the disease.

“The end goal is to help clinicians and guide treatment.”

The team has expanded its collaboration to include scientists from the Singapore National Eye Centre, which tested algorithms on several different Asian ethnic groups, including Malaysian, Indian and Chinese. Further research in France, Brazil, and Thailand will extend the study to help determine how the machine-learning model can be applied to other ethnicities and conditions.

Face A Face

BOQ Specialist Bank
Editor's Suggestion
Hot Stories

AFT Pharmaceuticals


Subscribe for Insight in your Inbox

Get Insight with the latest in industry news, trends, new products, services and equipment!