Enhanced Detection of Glaucoma on Ensemble Convolutional Neural Network for Clinical Informatics

Irretrievable loss of vision is the predominant result Glaucoma in retina. Recently, multiple approaches have paid attention to automatic detection glaucoma on fundus images. Due interlace blood vessels and herculean task involved detection, exactly affected site optic disc whether small or big size cup, deemed challenging. Spatially Based Ellipse Fitting Curve Model (SBEFCM) classification suggested based Ensemble for a reliable diagnosis Optic Cup (OC) Disc (OD) boundary correspondingly. This research deploys Convolutional Neural Network (CNN) classifying Diabetes Retinopathy (DR). The between OC OD performed by SBEFCM, which latest weighted ellipse fitting model. SBEFCM that enhances widens multi-ellipse technique proposed here. There pre-processing input image besides segmentation avoid interlacing surrounding tissues vessels. ascertaining boundary, characterized many output factors has been developed CNN classification, includes detecting sensitivity, specificity, precision, Area Under receiver operating characteristic (AUC) values accurately an innovative SBEFCM. In terms contrast, significantly outperformed current methods.