Retinal blood vessel segmentation from high resolution fundus image using deep learning architecture - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Retinal blood vessel segmentation from high resolution fundus image using deep learning architecture

Résumé

The Retinal Vascular Tree (RVT) segmentation is required to diagnose various ocular pathologies. Recently, fundus images are acquired with higher resolution, which allows representing a large range of vessel thickness. However, standard Deep Learning (DL) architectures with static and small convolution size have failed to achieve higher segmentation performance. In this paper, we propose a novel DL architecture for RVT segmentation dedicated for high resolution fundus images. The idea consists at extending the U-net architecture by increasing (e.g. decreasing) convolution kernel size through convolution blocs, in correlation with downscale (e.g. upscale) of feature map dimensions. The proposed architecture is validated on HRF database, where average sensitivity is increased from 56% to 84%.
Fichier principal
Vignette du fichier
Henda_ESANN_ES2023-180.pdf (1.48 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04451189 , version 1 (11-02-2024)

Identifiants

Citer

Henda Boudegga, Yaroub Elloumi, Asma Ben Abdallah, Rostom Kachouri, Mouhamed Hédi Bedoui. Retinal blood vessel segmentation from high resolution fundus image using deep learning architecture. ESANN 2023 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Oct 2023, Bruges, Belgium. pp.471-476, ⟨10.14428/esann/2023.ES2023-180⟩. ⟨hal-04451189⟩
14 Consultations
9 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More