Development of an efficient algorithm for the detection of macular edema from optical coherence tomography images

Detection of eye diseases and their treatment is a key to reduce blindness, which impacts human daily needs like driving, reading, writing, etc. Several methods based on image processing have been used to monitor the presence of macular diseases. Optical coherence tomography (OCT) imaging is the most efficient technique used to observe eye diseases. This paper proposes an efficient algorithm to automatically classify normal as well as disease-affected (macular edema) retinal OCT images by using segmentation of Inner Limiting Membrane and the Choroid Layer.

In the proposed method, preprocessing of the input image is done to improve the quality and reduce the speckle noise. The layer segmentation is done on the gradient image, and graph theory and dynamic programming algorithm is performed. The feature vectors from segmented image are in terms of thickness profile and cyst fluid parameter, and these features are applied to various classifiers.

The proposed method was tested with the standard dataset collected from the Department of Ophthalmology, Duke University, and achieved a high accuracy rate of 99.4975%, sensitivity of 100%, and specificity of 99% for the SVM classifier.

An efficient algorithm is proposed for macular edema detection from OCT images using segmentation based on graph theory and dynamic programming algorithm. The comparison with alternative methods yielded results that demonstrate the superiority of the proposed algorithm for macular edema detection.