An algorithm developed by a 29-year-old computer scientist could improve the detection and management of retinal disease.
The new technique that has been developed by Brunel University London doctoral candidate, Bashir Dodo, allows clinicians to automatically segment ocular coherence tomography (OCT) scans of the retina into distinct layers.
While clinicians are able to manually identify layers of the retina from OCT scans at present, the new algorithm would speed up this process.
“Automatically segmenting the layers could provide critical information for abnormality detection by comparing them to the average population and monitoring the progress of the disease against previous scans,” Mr Dodo explained.
His work was recognised with the Best Student Paper award at the Bioimaging 2018 conference in Portugal.
Mr Dodo told OT that further data sets were required to assess the suitability of the method for a clinical environment.
“The sole aim of our research is to ease the diagnostic process,” he shared.