Algorithm automatically analyses OCT images

The technique uses an algorithm developed by doctoral candidate Mr Bashir Dodo from Brunel University, London and won the “Best Student Paper” award at the prestigious BioImaging 2018 conference in Portugal.While eyecare professionals can already manually identify the layers in OCT images, Dodo’s algorithm does so automatically and then separates th into seven different segments.“Layer segmentation is one of the early processes of OCT retina image analysis, and already plays an important role in clinics,” Bashir said.“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. Automatically segmenting the layers could provide critical information for abnormality detection by comparing th to the average population, and monitoring the progress of disease against previous scans.“It is evident that prior knowledge plays an important role in diagnosis. Therefore, using automated methods to look back through medical records or ophthalmology literature has great potential to influence how this field progresses,” he added.Bashir’s paper, ‘Graph-cut segmentation of retinal layers from OCT images’, was published recently in the Proceedings of the 11th International Joint Conference on Biomedical Engineering Systs and Technologies.