Bulletin No. 1, 2013

Eyeing Cerebral Hazards and Stroke 39  A g r e a t e r h u r d l e , however, laid in the detection of new blood v e s s e l s i n t he e y e, whose growth is a sure sign of problems to come. As new vessels are short, irregular and squiggly, the determination of their existence and s t a t e o f g r ow t h e l ud e s a l l e x i s t en t automatized technology. Applying pattern recognition skills, the team was able to devise an algorithm which reads, pixel by pixel, retinal images and analyse them to get measurements on exudates, haemorrhages, new vessels, before finally achieving an overall evaluation of retinopathy. Standard retinal images can be transmitted through the Internet to a server installed with the algorithm and the results will be out within a short period of time. This new, non-invasive method substantially reduces cost, time required, as well as bias due to human perception. Initial tests have confirmed its dependability and high accuracy rates. Professor Zee intends to expand application to both diabetic and non-diabetic patients for early detection of stroke. an ophthalmologis t and a PhD student of Professor Zee’s who set out to identify vascular diseases before the occurrence of stroke. U p t o 8 0% o f a l l diabetics of over 10 years will develop diabetic retinopathy (DR)— damage to the retina caused by diabetes mellitus, with a concomitant higher chance of suffering stroke at a later stage. DR screening has become a standard procedure in diabetic care but its effectiveness is hampered by a shortage of specialists administering the screening, human variability in diagnosis, long waiting time for results, and high cost. To address these issues, the team tried to find a methodology that would turn the analogue images of the retina into quantifiable and analysable data. Professor Zee recounted that the first difficulty encountered in the process was the location of the optic disc, the spot where light- sensitive ganglion cell axons leave the eye to form the optic nerve to the brain, also known as the physiological blind spot. Though methods for its location already existed, his team developed a new one that better fit their purpose. taking retina image Normal retina Diabetic retinopathy Diabetic retinopathy screening process screening producing analysis report