Exudate detection in color retinal images for mass screening of diabetic retinopathy

Abstract : The automatic detection of exudates in colour eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to auto-matically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also de-tect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.
Type de document :
Article dans une revue
Medical Image Analysis, Elsevier, 2014, 18 (7), pp.1026 - 1043. <10.1016/j.media.2014.05.004>
Liste complète des métadonnées


https://hal-mines-paristech.archives-ouvertes.fr/hal-01082809
Contributeur : Etienne Decencière <>
Soumis le : vendredi 14 novembre 2014 - 13:55:45
Dernière modification le : mardi 12 septembre 2017 - 11:41:38
Document(s) archivé(s) le : vendredi 14 avril 2017 - 15:51:45

Fichier

exudate_journal.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Xiwei Zhang, Guillaume Thibault, Etienne Decencière, Beatriz Marcotegui, Bruno Laÿ, et al.. Exudate detection in color retinal images for mass screening of diabetic retinopathy. Medical Image Analysis, Elsevier, 2014, 18 (7), pp.1026 - 1043. <10.1016/j.media.2014.05.004>. <hal-01082809>

Partager

Métriques

Consultations de
la notice

280

Téléchargements du document

252