Computer Assisted Methods for Retinal Image Classification

Abstract

Diabetes maculopathy has become one of the rapidly increasing health threats worldwide. The complication of diabetes associated to retina of the eye is diabetic retinopathy. A patient with the disease has to undergo periodic screening of eye. The ophthalmologists use colour retinal images of a patient acquired from digital fundus camera for disease diagnosis. Limited number of ophthalmology specialists in most of the countries motivates the need for computer based analysis of retinal images using image processing techniques. The results of this process may be used in applications such as, to classify the retinal images into normal and diseased. This could reduce the workload of ophthalmologists, also aid in diagnosis, to make measurements and to look for a change in progression of disease. Some computer based retinal image analysis methods used for the application are briefed in this chapter.

Diabetes Diagnosis Using Deep Learning

“…These new blood vessels are fragile and prone to bleeding, resulting in a vision-threatening hemorrhage. They'll also convert to connective tissue, which will constrict over time, causing the retina to detach and result in blindness [6]. Figure (1) From fundus photos, instances of DR are based on the severity of the illness [7].…”