Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     
News

George & Matilda partners with IBM to fight glaucoma

07/11/2018By Myles Hume
Share
George & Matilda Eyecare (G&M) will combine with IBM Research Australia to develop artificial intelligence (AI) algorithms trained to spot glaucoma.

The new research project will develop algorithms that analyse retinal fundus photos and optical coherence tomography (OCT) images. The technology could then inform and guide practitioners in the detection of glaucoma.

It follows previous work by IBM scientists, who developed AI technology that scanned images and detected diabetic retinopathy (DR) levels with 86% accuracy.

Now, leveraging G&M’s anonymous clinical data set, IBM scientists and G&M optometrists will “train and validate” AI algorithms – such as deep learning neural networks – and use image analytics models to examine the relationship between characteristics of the optic nerve in diagnosing glaucoma.

Teams will assess glaucoma severity correlated with higher intraocular pressure, higher cup to disc ratios, and the thinning and thickness of the retinal nerve fibre layer and ganglion cell layer.

In a recent paper, IBM detailed “a first step” it had made in this field involving a deep learning framework that detected glaucoma from raw OCT imaging. It achieved 94% accuracy without additional segmentation or data scrubbing, which is usually time-consuming.

IBM Research Australia scientist Dr Simon Wail, said developing the technology for glaucoma posed a different challenge to DR because of the added complexity of 3D images in OCT.


“We think this research will allow us the ability to improve best practice for the patients that entrust their eyesight to our care.”
Chris Beer, George & Matilda

“Currently, glaucoma is detected using a number of different tests and most importantly, by tracking changes in retinal structure and visual function over time. The proposed work will combine various imaging modalities and test results to track patients carefully over time, and to detect the disease as early as possible,” he said.

IBM is working closely with G&M’s Dr Margaret Lam, and her optometry colleagues, along with clinical glaucoma researchers at the Langone Eye Centre, New York University. 

“This work is currently in the research stage and needs to be validated clinically and this is where G&M are helping us with their data and expertise,” Wail said.

“Ultimately, for this technology to be used with patients it would require the appropriate regulatory approval. As we progress this research there may be the potential for patents which would be jointly developed by IBM and G&M.”

largeleaderboard_1217
advertisement

G&M CEO Mr Chris Beer said the project was exciting as it looked at new ways of embracing technology that would improve the level of care offered to patients.

“We think this research will allow us the ability to improve best practice for the patients that entrust their eyesight to our care,” Beer said.

“We are also excited about what this collaboration with IBM Research Australia will bring in new learnings for the patients that see us in the future, and how it will help all Australians, and even those across the world, to reduce preventable blindness in the future.”

Visualisation of network-detected regions in a glaucomatous (top row) and healthy (bottom row) eye. Image Courtesy: IBM Research
Visualisation of network-detected regions in a glaucomatous (top row) and healthy (bottom row) eye. Image Courtesy: IBM Research

leaderboard
advertisement





skyscraper_article
advertisement
Editor's Suggestion
Hot Stories

OR
 

Subscribe for Insight in your Inbox

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