Share Email Print

Journal of Medical Imaging

Tracking and diameter estimation of retinal vessels using Gaussian process and Radon transform
Author(s): Masoud E. Asl; Navid A. Koohbanani; Alejandro F. Frangi; Ali Gooya
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Extraction of blood vessels in retinal images is an important step for computer-aided diagnosis of ophthalmic pathologies. We propose an approach for blood vessel tracking and diameter estimation. We hypothesize that the curvature and the diameter of blood vessels are Gaussian processes (GPs). Local Radon transform, which is robust against noise, is subsequently used to compute the features and train the GPs. By learning the kernelized covariance matrix from training data, vessel direction and its diameter are estimated. In order to detect bifurcations, multiple GPs are used and the difference between their corresponding predicted directions is quantified. The combination of Radon features and GP results in a good performance in the presence of noise. The proposed method successfully deals with typically difficult cases such as bifurcations and central arterial reflex, and also tracks thin vessels with high accuracy. Experiments are conducted on the publicly available DRIVE, STARE, CHASEDB1, and high-resolution fundus databases evaluating sensitivity, specificity, and Matthew’s correlation coefficient (MCC). Experimental results on these datasets show that the proposed method reaches an average sensitivity of 75.67%, specificity of 97.46%, and MCC of 72.18% which is comparable to the state-of-the-art.

Paper Details

Date Published: 12 September 2017
PDF: 14 pages
J. Med. Imag. 4(3) 034006 doi: 10.1117/1.JMI.4.3.034006
Published in: Journal of Medical Imaging Volume 4, Issue 3
Show Author Affiliations
Masoud E. Asl, Tarbiat Modares Univ. (Iran)
Navid A. Koohbanani, Tarbiat Modares Univ. (Iran)
Alejandro F. Frangi, The Univ. of Sheffield (United Kingdom)
Ali Gooya, The Univ. of Sheffield (United Kingdom)

© SPIE. Terms of Use
Back to Top