Quantification of retinopathy of prematurity via vessel segmentation

Abstract

Retinopathy of prematurity is a disease that affects the eyes of many babies who are prematurely born. If the retinopathy is not detected in the days following birth blindness may occur. Studies have demonstrated that by observing the blood vessels within the retina, the disease can be quantified in an early stage and early treatment can save the baby's eyes. We have developed a new tool to assess retinopathy of prematurity. Our technique captures images of the retina to extract and quantify both tortuosity and dilation of blood vessels. Our approach demonstrates a 80% sensitivity and 92% specificity in the prediction of retinopathy compared to experts and shows a significant reduced diagnosis time and clinical integration via speech recognition and glare detection.