https://academictorrents.com/details/eb9dd9216a1c9a622250ad70a400204e7531196d

Abstract:

A de-identified dataset of retinal fundus images for glaucoma analysis (RIGA) was derived from three sources. The optic cup and disc boundaries of these images were marked and annotated manually by six experienced ophthalmologists individually using a tablet and a precise pen. Six parameters were extracted and assessed among the ophthalmologists. The inter-observer annotations were compared by calculating the standard deviation (SD) for every image between the six ophthalmologists in order to determine if there are any outliers among the six annotations to be eliminated i.e. filtering the images.

The dataset includes 3 different files: 1) MESSIDOR dataset file contains 460 original images and 460 images for every single ophthalmologist manual marking in total of 3220 images for the entire file. 2) Bin Rushed Ophthalmic center file and contains 195 original images and 195 images for every sin... [more]

Ahmed Almazroa, Sami Alodhayb, Essameldin Osman, Eslam Ramadan, Mohammed Hummadi, Mohammed Dlaim, Muhannad Alkatee, Kaamran Raahemifar, Vasudevan Lakshminarayanan, "Retinal fundus images for glaucoma analysis: the RIGA dataset", Proc. SPIE 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 105790B (6 March 2018); doi: 10.1117/12.2293584; https://doi.org/10.1117/12.2293584

URL: https://deepblue.lib.umich.edu/data/concern/data_sets/3b591905z?locale=en
License: http://creativecommons.org/licenses/by-nc/4.0/