Saving sight: using AI to diagnose diabetic eye disease

Saving sight: using AI to diagnose diabetic eye disease

Researchers have used artificial intelligence (AI) to support the instant diagnosis of one of the top causes of blindness – diabetes-related eye disease – in its earliest stages.

Diabetic retinopathy is the leading cause of vision loss in adults and its impact is growing worldwide, with 191 million people set to be affected by 2030.

There are no early-stage symptoms and the disease may already be advanced by the time people start losing their sight. Early diagnosis and treatment can make a dramatic difference to how much vision a patient retains.

Now a team of Australian-Brazilian researchers led by RMIT University have developed an image-processing algorithm that can automatically detect one of the key signs of the disease, fluid on the retina, with an accuracy rate of 98 per cent.

Lead investigator from RMIT University Professor Dinesh Kant Kumar said the method was instantaneous and cost-effective.

“We know that only half of those with diabetes have regular eye exams and one-third have never been checked,” Kumar said. 

“But the gold standard methods of diagnosing diabetic retinopathy are invasive or expensive, and often unavailable in remote or developing parts of the world.

“Our AI-driven approach delivers results that are just as accurate as clinical scans but relies on retinal images that can be generated with ordinary optometry equipment.

“Making it quicker and cheaper to detect this incurable disease could be life changing for the millions of people who are currently undiagnosed and risk losing their sight.”

Fluorescein angiography and optical coherence tomography scans are currently the most accurate clinical methods for diagnosing diabetic retinopathy.

An alternative and cheaper method is analysing images of the retina that can be taken with relatively inexpensive equipment called fundus cameras, but the process is manual, time-consuming and less reliable.

A fundus image of a retina, with damaged areas highlighted by the image-processing algorithm. A fundus image of a retina, with damaged areas highlighted by the image-processing algorithm.

To automate the analysis of fundus images, researchers in the Biosignals Laboratory in RMIT’s School of Engineering, together with collaborators in Brazil, used deep learning and artificial intelligence techniques.

The algorithm they developed can accurately and reliably spot the presence of fluid from damaged blood vessels, or exudate, inside the retina.

The researchers hope their method could eventually be used for widespread screening of at-risk populations.

“Undiagnosed diabetes is a massive health problem here and around the globe,” Kumar said.

“For every single person in Australia who knows they have diabetes, another is living with diabetes but isn’t diagnosed. In developing countries, the ratio is one diagnosed to four undiagnosed.

“This results in millions of people developing preventable and treatable complications from diabetes-related diseases.

“With further development, our technology has the potential to reduce that burden.”

The researchers are in discussions with manufacturers of fundus cameras about potential collaborations to advance the technology.

The research – with lead author Parham Khojasteh and collaborators from Federal University of Sao Carlos, Federal Institute of Sao Paolo, University of Campinas and Sao Paolo State University – is published in Computers in Biology and Medicine (January 2019, Volume 104, DOI:10.1016/j.compbiomed.2018.10.031.

Story: Gosia Kaszubska

  • Engineering
  • Research
25 February 2019

Share

Engage

Related news

news-thumbnail-agentic-ai-the-next-frontier-of-artificial-intelligence.jpg

Agentic AI: Bước tiến mới của trí tuệ nhân tạo giúp doanh nghiệp chuyển mình
Icon / Small / Calendar Created with Sketch. 27 Mar 2025

Trong vòng một thập kỷ tới, Agentic AI có thể đảm nhiệm tới 70% công việc văn phòng, định hình lại các ngành nghề bằng những hệ thống thông minh và linh hoạt, có khả năng học hỏi, tiến hóa cũng như giải quyết các vấn đề thực tế phức tạp.

news-thumbnail-quantum-computing-friend-or-foe.jpg

Máy tính lượng tử: Bạn hay thù?
Icon / Small / Calendar Created with Sketch. 19 Mar 2025

Máy tính lượng tử từ lâu đã được xem là công nghệ tương lai nhưng những đột phá gần đây của Google và Microsoft cho thấy tương lai đó có thể đến nhanh hơn ta tưởng.

news-thumbnail-vietnams-ai-ambitions-balancing-innovation-with-responsibility.jpg

Tham vọng AI của Việt Nam: Cần cân bằng giữa đổi mới và trách nhiệm
Icon / Small / Calendar Created with Sketch. 18 Mar 2025

Khi trí tuệ nhân tạo (AI) tạo sinh phát triển mạnh mẽ, tiềm năng thúc đẩy đổi mới là không thể phủ nhận nhưng đi kèm với đó là những rủi ro. Từ bê bối deepfake đến thông tin sai lệch do AI tạo ra, công nghệ này đặt ra những thách thức đạo đức nghiêm trọng.

news-thumbnail-deep-seek-ai-new-challenger-disrupting-big-tech.jpg

DeepSeek: Gương mặt mới khiến sân chơi AI xáo động
Icon / Small / Calendar Created with Sketch. 13 Mar 2025

Sự trỗi dậy của DeepSeek, mô hình trí tuệ nhân tạo (AI) mã nguồn mở, đang khuấy đảo ngành công nghệ, thách thức sự thống trị của các tập đoàn lớn và mở ra cơ hội mới cho các doanh nghiệp nhỏ.

Load more +