Automated detection of microaneurysms using robust blob descriptors

Kedir Adal 1 Sharib Ali 1 Désiré Sidibé 1 T.P. Karnowski 2 Edward Chaum 3 Fabrice Mériaudeau 1
1 Le2i - Laboratoire Electronique, Informatique et Image
2 ORNL - Oak Ridge National Laboratory [Oak Ridge]
3 The Neuroscience Institute
Abstract : Microaneurysms (MAs) are among the first signs of diabetic retinopathy (DR) that can be seen as round dark-red structures in digital color fundus photographs of retina. In recent years, automated computer-aided detection and diagnosis (CAD) of MAs has attracted many researchers due to its low-cost and versatile nature. In this paper, the MA detection problem is modeled as finding interest points from a given image and several interest point descriptors are introduced and integrated with machine learning techniques to detect MAs. The proposed approach starts by applying a novel fundus image contrast enhancement technique using Singular Value Decomposition (SVD) of fundus images. Then, Hessian-based candidate selection algorithm is applied to extract image regions which are more likely to be MAs. For each candidate region, robust low-level blob descriptors such as Speeded Up Robust Features (SURF) and Intensity Normalized Radon Transform are extracted to characterize candidate MA regions. The combined features are then classfi ed using SVM which has been trained using ten manually annotated training images. The performance of the overall system is evaluated on Retinopathy Online Challenge (ROC) competition database. Preliminary results show the competitiveness of the proposed candidate selection techniques against state-of-the art methods as well as the promising future for the proposed descriptors to be used in the localization of MAs from fundus images.
Keywords : Microaneurysm SURF SVD Hessian SVM
Type de document :
Communication dans un congrès
SPIE Medical Imaging - Computer-Aided Diagnosis, Feb 2013, Orlando - FL, United States. pp.8670-22, 2013
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-00784580
Contributeur : Désiré Sidibé <>
Soumis le : lundi 4 février 2013 - 16:23:59
Dernière modification le : mardi 5 février 2013 - 08:28:41
Document(s) archivé(s) le : dimanche 5 mai 2013 - 08:55:17

Fichier

articleSPIE-updated.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00784580, version 1

Collections

LE2I

Citation

Kedir Adal, Sharib Ali, Désiré Sidibé, T.P. Karnowski, Edward Chaum, et al.. Automated detection of microaneurysms using robust blob descriptors. SPIE Medical Imaging - Computer-Aided Diagnosis, Feb 2013, Orlando - FL, United States. pp.8670-22, 2013. <hal-00784580>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

215

Téléchargements du document

645

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD