RT info:eu-repo/semantics/article
T1 Comparison of the performance of Convolutional Neural Networks and Vision Transformer-Based Systems for automated Glaucoma detection with eye fundus images
A1 Alayón Miranda, Silvia
A1 Hernández,  Jorge
A1 Fumero, Francisco J.
A1 Sigut, José F.
A1 Díaz Alemán, Tinguaro
K1 convolutional neural network; vision transformer-based system; glaucoma; fundus
imagin
AB Glaucoma, a disease that damages the optic nerve, is the leading cause of irreversibleblindness worldwide. The early detection of glaucoma is a challenge, which in recent years hasdriven the study and application of Deep Learning (DL) techniques in the automatic classificationof eye fundus images. Among these intelligent systems, Convolutional Neural Networks (CNNs)stand out, although alternatives have recently appeared, such as Vision Transformers (ViTs) or hybridsystems, which are also highly efficient in image processing. The question that arises in the faceof so many emerging methods is whether all these new techniques are really more efficient forthe problem of glaucoma diagnosis than the CNNs that have been used so far. In this article, wepresent a comprehensive comparative study of all these DL models in glaucoma detection, with theaim of elucidating which strategies are significantly better. Our main conclusion is that there areno significant differences between the efficiency of both DL strategies for the medical diagnosticproblem addressed.
YR 2023
FD 2023
LK http://riull.ull.es/xmlui/handle/915/35152
UL http://riull.ull.es/xmlui/handle/915/35152
LA en
DS Repositorio institucional de la Universidad de La Laguna
RD 16-may-2024