Abird's eye view for improved diagnosis

June 25, 2018, Agency for Science, Technology and Research (A*STAR), Singapore
Abird’s eye view for improved diagnosis
An anterior segment optical coherence tomography (AS-OCT) image of the eye's anterior chambers. Credit: © 2018 A*STAR Institute for Infocomm Research

An effective method of screening patients for closed-angle glaucoma has been developed by A*STAR researchers.

In closed-angle , the optic nerve is damaged because the aqueous fluid in the eye does not drain properly. This is because the gap between the cornea and the iris, known as the anterior chamber angle, where fluid normally flows through the eye, has narrowed significantly or become blocked. The resulting build-up of pressure within the eye, which can happen rapidly, can cause irreversible blindness.

Current diagnosis of closed-angle glaucoma involves analyzing 'anterior segment optical coherence tomography' (AS-OCT) images, which are cross-sectional pictures of the eye's anterior chambers. However, manual comparison of AS-OCT images, particularly those taken using different systems, takes considerable time and expertise.

"We wanted to create a fully-automated, rapid method for screening AS-OCT images that could ascertain whether closed-angle glaucoma is present," explains Huazhu Fu at A*STAR's Institute for Infocomm Research, who led the project alongside Mani Baskaran at Singapore Eye Research Institute, with scientists from China and the UK. "Our algorithm compares each individual image with a library of exemplar images, before producing a set of clinical parameters from each image that clinicians can use to validate diagnosis."

Fu's team created a reference dataset of labelled images taken by different AS-OCT machines of several thousand individual eyes, both with and without clinically-diagnosed glaucoma. Their algorithm then uses the dataset to analyze newly-uploaded images.

"Although the eye structure shown in every AS-OCT image is different, local regions within each eye are similar. When our algorithm receives a new eye image, it searches the annotated dataset for 'best-fit' images that are the closest match in terms of eye structure and anterior chamber angle, before transferring the labels from these selected library images to the new image," Fu explains.

The algorithm then applies a smoothing technique to refine the structural labeling and ensure it is accurate for each unique eye shape. This allows very precise clinical measurements of the anterior chamber angle and other diagnostic features.

During tests, the algorithm was able to segment and measure one AS-OCT image in ten seconds, providing a potentially invaluable tool for clinicians.

"Our algorithm accurately interprets single or multiple AS-OCT scans, is fully automated and does not depend on specialist training," says Baskaran. "This will significantly improve screening for patients in clinics or community settings and provide support for clinicians."

The team are expanding their trials to larger datasets and aim to incorporate machine-learning techniques into the to further improve accuracy and performance.

Explore further: Anterior segment parameters tied to gonioscopic angle closure

More information: Huazhu Fu et al. Segmentation and Quantification for Angle-Closure Glaucoma Assessment in Anterior Segment OCT, IEEE Transactions on Medical Imaging (2017). DOI: 10.1109/TMI.2017.2703147

Related Stories

Anterior segment parameters tied to gonioscopic angle closure

February 10, 2017
(HealthDay)—Baseline anterior segment parameters are associated with development of incident gonioscopic angle closure after four years, according to a study published online Feb. 9 in JAMA Ophthalmology.

Automated method could prevent blindness by detecting glaucoma in its early stages

September 11, 2013
A team of researchers led by Jun Cheng of the A*STAR Institute for Infocomm Research, Singapore, has developed a novel automated technology that screens for glaucoma more accurately and quickly than existing methods.

NTU Singapore and SERI invent new scope to diagnose glaucoma

April 5, 2018
Scientists at Nanyang Technological University, Singapore (NTU Singapore), with clinicians from the Singapore Eye Research Institute (SERI), have invented a new 'pen camera' that makes it easier for doctors to diagnose patients ...

Recommended for you

Newly formed blood vessels may contribute to eye disease

September 14, 2018
Newly formed blood vessels may be cracks in the barrier between the bloodstream and the eye, according to a Northwestern Medicine study published in the Proceedings of the National Academy of Sciences.

Eye disease can cause blindness, and it's on the rise

August 29, 2018
A new study into recent cases of ocular syphilis warns increasing numbers of people are at risk of permanent damage to their vision.

INSiGHT identifies unique retinal regulatory genes

August 28, 2018
Vision begins in the retina, a light-sensing neural network in the eye that is critical for our ability observe the world around us. Researches at Baylor College of Medicine, Texas Children's Hospital and the Hospital for ...

Alzheimer's one day may be predicted during eye exam

August 23, 2018
It may be possible in the future to screen patients for Alzheimer's disease using an eye exam.

Researchers find potential new gene therapy for blinding disease

August 20, 2018
The last year has seen milestones in the gene therapy field, with FDA approvals to treat cancer and an inherited blinding disorder. New findings from a team led by University of Pennsylvania vision scientists, who have in ...

Sleep in your contacts, risk serious eye damage: CDC

August 16, 2018
(HealthDay)—A 59-year-old man was in the shower, wiping his eyes with a towel, when he heard a popping sound and felt pain shoot through his left eye.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.