BIOMISA retinal image database for macular and ocular syndromes

Abstract

Retinopathy is a collective group of macular and ocular syndromes that damages the human retina due to increased fluid pressure or hyperglycemia. The major forms of retinopathy include macular edema (ME), exudative or non-exudative age related macular degeneration (AMD) and glaucoma. Various eye testing techniques are being used by ophthalmologists to grade retinopathy. Furthermore, different researchers are developing fully autonomous systems to mass screen eye patients across the globe. However, to validate the performance of these systems, they must be tested on publicly available standardized datasets. Therefore, this paper presents a retinal image database containing high quality 64 fundus and 2497 OCT brightness scans (B-scans). The proposed dataset is first of its kind in providing detailed annotations of retinal hemorrhages, hard exudates, intra-retinal and sub-retinal fluids, drusen, retinal pigment epithelium (RPE) atrophy and cup to disc (CDR) ratios from both retinal fundus and OCT imagery. The proposed dataset is also compared with the publicly available databases where it outmatched them by providing high quality fundus and OCT scans along with detailed markings through which different researchers can automatically diagnose different pathological conditions of human retina. Keywords: Optical coherence tomography (OCT), Fundus photography, Retinopathy