14 July 2014 Accurate and reliable segmentation of the optic disc in digital fundus images
Author Affiliations +
Funded by: Leverhulme Trust
Abstract
We describe a complete pipeline for the detection and accurate automatic segmentation of the optic disc in digital fundus images. This procedure provides separation of vascular information and accurate inpainting of vessel-removed images, symmetry-based optic disc localization, and fitting of incrementally complex contour models at increasing resolutions using information related to inpainted images and vessel masks. Validation experiments, performed on a large dataset of images of healthy and pathological eyes, annotated by experts and partially graded with a quality label, demonstrate the good performances of the proposed approach. The method is able to detect the optic disc and trace its contours better than the other systems presented in the literature and tested on the same data. The average error in the obtained contour masks is reasonably close to the interoperator errors and suitable for practical applications. The optic disc segmentation pipeline is currently integrated in a complete software suite for the semiautomatic quantification of retinal vessel properties from fundus camera images (VAMPIRE).
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE) 0091-3286/2014/$25.00 © 2014 SPIE
Andrea Giachetti, Lucia Ballerini, and Emanuele Trucco "Accurate and reliable segmentation of the optic disc in digital fundus images," Journal of Medical Imaging 1(2), 024001 (14 July 2014). https://doi.org/10.1117/1.JMI.1.2.024001
Published: 14 July 2014
Lens.org Logo
CITATIONS
Cited by 58 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Biomedical optics

Image resolution

Pathology

Sensors

Image filtering

Image analysis

RELATED CONTENT

Study on pathological area of knee by infrared imaging
Proceedings of SPIE (November 08 2010)
An extended half-scan Feldkamp-type CT reconstruction
Proceedings of SPIE (March 03 2006)
Image segmentation by multiresolution histogram decomposition
Proceedings of SPIE (September 01 1995)
Recognition of object formations in SAR image sequences
Proceedings of SPIE (January 28 2002)
No-reference metrics for demosaicing
Proceedings of SPIE (January 18 2010)

Back to Top