Abnormality Classification of Diabetic Macular EDEMA in Retinal Images

-Diabetic Macular Edema disease leads to vision loss problem in Diabetic patients. Early detection of Macular Edema in diabetic patients pave a path for prevention from blindness. Diabetic Macular Edema (DME) occurs when blood vessels in the retina of patients with diabetes begin to leak into the macula region of eye. These leakages cause the macula to thicken and swell, progressively leads to vision loss. The automatic detection of Diabetic Macular Edema and classification of DME severity is done in this paper. The Hard Exudates (HE) presence in macula region is detected and the features are extracted. The extracted features are inputised to Adaptive Neuro Fuzzy Inference System (ANFIS) to classify the images as normal and the abnormal image severity levels as mild, moderate and severe. Index terms --Diabetic Macular Edema (DME), Neuro-Fuzzy, Hard Exudates, Severity level.