RT info:eu-repo/semantics/article
T1 Ganglion cell layer analysis with deep learning in glaucoma diagnosis
A1 Sigut Saavedra, José Francisco
A1 Díaz Alemán, Valentín Tinguaro
A1 Fumero Batista, Francisco José
A1 Alayón Miranda, Silvia
A1 Ángel Pereira, Denisse
A1 Arteaga Hernández, Víctor Javier
A2 Ingeniería Informática y de Sistemas
A2 GAIM (Grupo de Análisis de Imágenes Médicas)
K1 Glaucoma
K1 Deep learning
K1 Tomography
K1 Ganglion cells
AB Objective: To determine and compare the diagnostic precision in glaucoma oftwo deep learning models using infrared images of the optic nerve, eye fundus, and the ganglion cell layer(GCL).Methods: We have selected a sample of normal and glaucoma patients. Three infrared imageswere registered with a spectral-domain optical coherence tomography (SD-OCT). The firstcorresponds to the confocal scan image of the fundus, the second is a cut-out of the firstcentered on the optic nerve, and the third was the SD-OCT image of the GCL. Our deeplearning models are developed on the MatLab platform with the ResNet50 and VGG19 pretrained neural networks.Results: 498 eyes of 298 patients were collected. Ofthe 498 eyes, 312 are glaucoma and 186 arenormal. In the test, the precision of the models was 96% (ResNet50) and 96% (VGG19) for theGCL images, 90% (ResNet50) and 90% (VGG19) for the optic nerve images and 82% (ResNet50)and 84% (VGG19) for the fundus images. The ROC area in the test was 0.96 (ResNet50) and0.97 (VGG19) for the GCL images, 0.87 (ResNet50) and 0.88 (VGG19) for the optic nerve images,and 0.79 (ResNet50) and 0.81 (VGG19) for the fundus images.Conclusions: Both deep learning models, applied to the GCL images, achieve high diagnosticprecision, sensitivity and specificity in the diagnosis of glaucoma
YR 2021
FD 2021
LK http://riull.ull.es/xmlui/handle/915/35141
UL http://riull.ull.es/xmlui/handle/915/35141
LA en
NO https://doi.org/10.1016/j.oftale.2020.09.015
DS Repositorio institucional de la Universidad de La Laguna
RD 13-nov-2025