Automatic detection and grading of severity level in exudative maculopathy

Diabetic maculopathy is one of the complications of diabetes mellitus that is considered as one of the major cause of vision loss among people around the world. Compulsory screening of eye will help to identify the maculopathy at early stage and reduce the risk of severe vision loss. A new automated method for the detection and grading of diabetic maculopathy severity level without any manual intervention is presented. Based on the location of exudates in marked macular region the severity level is classified into mild, moderate and severe. Digital color retinal images at different levels of maculopathy were used to evaluate the method. An overall sensitivity of 95.6% and specificity of 96.15% were achieved by the method.