Share Email Print

Proceedings Paper

Method for retinal vessel detection and diameter measurement
Author(s): Xiaokun Li; Tong Fang; Jenn-Kwei Tyan; Ming Fang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Since retinal vessel detection and measurement plays an important role in diagnosing cardiovascular diseases, a lot of efforts have been made in recent years. In this paper, we propose an efficient method for vessel detection and diameter measurement which incorporates with edge detection, path searching, and matched filtering. Firstly, Gaussian- Laplacian filter and zero crossing detection are applied to retinal image to get an initial edge-map. Then, for any vessel of interest, its centerline and diameter can be accurately obtained by using region growing, thinning, path searching, and matched filter. The robustness and efficiency of the proposed method have been demonstrated by our extensive experiments. Another advantage is that it can process retinal image in real-time speed. The detection and measurement results lead us to determine more parameters for further study of vascular diseases.

Paper Details

Date Published: 12 May 2004
PDF: 9 pages
Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); doi: 10.1117/12.534539
Show Author Affiliations
Xiaokun Li, Univ. of Cincinnati (United States)
Tong Fang, Siemens Corporate Research, Inc. (United States)
Jenn-Kwei Tyan, Siemens Corporate Research, Inc. (United States)
Ming Fang, Siemens Corporate Research, Inc. (United States)

Published in SPIE Proceedings Vol. 5370:
Medical Imaging 2004: Image Processing
J. Michael Fitzpatrick; Milan Sonka, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?