A Robust and Rotation Invariant Automated Algorithm for Grading Diabetic Macular Edema in Retinal Images

Abstract

In this work, an algorithm for grading Diabetic Macular edema is projected for diagnosing the severity of disease. One of the major contributions is that, the algorithm is invariant to the rotation of retinal image. The projected research work includes the segmentation of Optic disk, localization of Macula, segmentation of exudates and Grading of Diabetic Macular Edema into Severe, moderate and No disease. Rotation Invariance and Less time complexity make the work more efficient. The projected method is highly precise with high precision, recall and F-Measure values. A set of NPDR (Non Proliferative Diabetic Retinopathy) database is used for the proposed algorithm.

Keywords: Diabetic Macular Edema, Exudates, Macula, Optic Disk, Rotation Invariant