Conference proceeding
Optimal filter approach for the detection of vessel bifurcations in color fundus images
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.8669, pp.866920-866920-7
03/13/2013
DOI: 10.1117/12.2007088
Abstract
Bifurcations of retinal vessels in fundus images are important structures clinically and their detection is also an important component in image processing algorithms such as registration, segmentation and change detection. In this paper, we develop a method for direct bifurcation detection based on the optimal filter framework. This approach first generates a set of filters to represent all cases of bifurcations, and then uses them to generate a feature space for a classifier to distinguish bifurcations and non-bifurcations. This approach is different from previous methods as it uses a minimal number of assumptions, essentially only requiring training images and expert annotations of bifurcations. The method is trained on 60 fundus images and tested on 20 fundus images, resulting in an AUC of 0.883, which compares well to a human expert.
Details
- Title: Subtitle
- Optimal filter approach for the detection of vessel bifurcations in color fundus images
- Creators
- Qiao HuMona K GarvinMark A ChristopherXiayu XuT. E ScheetzMichael D Abramoff
- Resource Type
- Conference proceeding
- Publication Details
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.8669, pp.866920-866920-7
- Publisher
- SPIE
- DOI
- 10.1117/12.2007088
- ISSN
- 1605-7422
- Language
- English
- Date published
- 03/13/2013
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Ophthalmology and Visual Sciences; Electrical and Computer Engineering
- Record Identifier
- 9983806282102771
Metrics
12 Record Views