Bashir Dodo, a student at the Brunel University, London, has developed a new technique for identifying and diagnosing damage to the human retina.
The technique described by the Press Office of the university is an algorithm for Optical Coherence Tomography equipment, which could automatically segment images of the retina into seven distinct layers.
Bashir Dodo, currently a doctoral student at the institution’s Department of Computer Science, demonstrated the new algorithm at the BIOIMAGING 2018 Conference recently held in Portugal and was rewarded with the ‘Best Student Paper’ Award at the event.
Dodo’s work seemed to have been inspired by the psychological concept of similarity, used the ideas of continuity and discontinuity to develop the algorithm.
The university expressed the hope that apart from improving the accuracy and speed of diagnosis, the technique would help to save the sight of patients by identifying damage earlier.
According to Bashir Dodo:
“Layer segmentation is one of the early processes of OCT retina image analysis, and already plays an important role in clinics.
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, which is one of the most common causes of sight loss worldwide.
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 doctors are able to identify the layers manually from OCT images, Dodo’s new technique would automatically segment images of the retina, thereby allowing specialists to spot abnormalities quicker and better track the progress of medication.