RT info:eu-repo/semantics/article
T1 RIM-ONE DL: A Unified Retinal Image Database for Assessing Glaucoma Using Deep Learning
A1 Sigut Saavedra, José Francisco
A1 Fumero Batista, Francisco José
A1 Díaz Alemán, Tinguaro
A1 Alayón, Silvia
A1 Arnay, Rafael
A1 Angel-Pereira, Denisse
K1 Convolutional Neural Networks
K1 Deep Learning
K1 Glaucoma Assessment
K1 RIM-ONE
AB The first version of the Retinal IMage database for Optic Nerve Evaluation (RIM-ONE) was published in2011. This was followed by two more, turning it into one of the most cited public retinography databases forevaluating glaucoma. Although it was initially intended to be a database with reference images for segmentingthe optic disc, in recent years we have observed that its use has been more oriented toward training andtesting deep learning models. The recent REFUGE challenge laid out some criteria that a set of images ofthese characteristics must satisfy to be used as a standard reference for validating deep learning methods thatrely on the use of these data. This, combined with the certain confusion and even improper use observedin some cases of the three versions published, led us to consider revising and combining them into a new,publicly available version called RIM-ONE DL (RIM-ONE for Deep Learning). This paper describes this setof images, consisting of 313 retinographies from normal subjects and 172 retinographies from patients withglaucoma. All of these images have been assessed by two experts and include a manual segmentation of thedisc and cup. It also describes an evaluation benchmark with different models of well-known convolutionalneural networks.
SN 1854-5165
YR 2020
FD 2020
LK http://riull.ull.es/xmlui/handle/915/35104
UL http://riull.ull.es/xmlui/handle/915/35104
LA en
DS Repositorio institucional de la Universidad de La Laguna
RD 27-may-2024