Researcher Bashir Dodo from Brunel University London’s Department of Computer Science
By Helen Carter
A new technique for identifying and diagnosing damage to the human retina automatically segments images of the retina into seven distinct layers.
It is hoped the method can improve the accuracy and speed of diagnosis, and help save the sight of patients by identifying damage in eye-related disease earlier.
Doctoral candidate Bashir Dodo from Brunel University London’s Department of Computer Science demonstrated the new algorithm for OCT (Optical Coherence Tomography) at the BIOIMAGING 2018 conference in Portugal, where it was awarded best student paper.
He used ideas of continuity and discontinuity to develop an algorithm to identify where one layer of the retina transitions to the next.
‘Layer segmentation is one of the early processes of OCT retina image analysis, and already plays an important role in clinics,’ Mr Dodo said in a press release. ‘For example, the thickness profile of the retinal nerve fibre layer – which can be calculated directly from the segment layer – is used in the diagnosis of glaucoma.
The algorithm automatically separates the retina into seven layers
‘Automatically segmenting the layers could provide critical information for abnormality detection by comparing them to the average population, and monitoring the progress of disease against previous scans.’
While optometrists and ophthalmologists currently identify the layers manually from OCT images, the new technique automatically segments images of the retina, allowing eye care professionals to detect abnormalities quicker and to better track medication progress.
‘It is evident that prior knowledge plays an important role in diagnosis,’ Mr Dodo said. ‘Therefore, using automated methods to look back through medical records or ophthalmology literature has great potential to influence how this field progresses.’
View the research paper: Graph-Cut Segmentation of Retinal Layers from OCT Images