Abstract
The relationship between changes in retinal vessel morphology and the onset and progression of diseases such as diabetes, hypertension and retinopathy of prematurity (ROP) has been the subject of several large scale clinical studies. However, the difficulty of quantifying changes in retinal vessels in a sufficiently fast, accurate and repeatable manner has restricted the application of the insights gleaned from these studies to clinical practice. This paper presents a novel algorithm for the efficient detection and measurement of retinal vessels, which is general enough that it can be applied to both low and high resolution fundus photographs and fluorescein angiograms upon the adjustment of only a few intuitive parameters. Firstly, we describe the simple vessel segmentation strategy, formulated in the language of wavelets, that is used for fast vessel detection. When validated using a publicly available database of retinal images, this segmentation achieves a true positive rate of 70.27%, false positive rate of 2.83%, and accuracy score of 0.9371. Vessel edges are then more precisely localised using image profiles computed perpendicularly across a spline fit of each detected vessel centreline, so that both local and global changes in vessel diameter can be readily quantified. Using a second image database, we show that the diameters output by our algorithm display good agreement with the manual measurements made by three independent observers. We conclude that the improved speed and generality offered by our algorithm are achieved without sacrificing accuracy. The algorithm is implemented in MATLAB along with a graphical user interface, and we have made the source code freely available.
Highlights
Variations in blood vessel diameters occur as part of the autonomous control of blood flow in healthy subjects and at different stages in the pulse cycle [1], while sustained changes may indicate the presence of some pathologies [2]
Despite its simplicity we found it to be well-suited to the task of vessel detection
Accurate segmentation is only a means to an end in the algorithm described here, and does not constitute the final output, in order to establish the suitability of the Isotropic Undecimated Wavelet Transform (IUWT) for efficient vessel detection we have compared it with more specialised published algorithms
Summary
Variations in blood vessel diameters occur as part of the autonomous control of blood flow in healthy subjects and at different stages in the pulse cycle [1], while sustained changes may indicate the presence of some pathologies [2]. Measurements of vessel calibre are of interest both to physiologists looking to better understand the regulation of blood flow [3,4] and to clinicians interested in the prediction, diagnosis or progression of disease [5,6,7]. Accurate quantification of changes in vessel calibre is difficult to automate fully because of large variations in image type, size and quality. Retinal vessel segmentation Fully automating the analysis of vessel calibre in still images relies firstly upon accurately locating the blood vessels. Published retinal segmentation algorithms can be broadly categorised as those that require training images and those that do not. In order to better enhance vessels of different widths, the width of the filter may be varied in addition to its orientation, resulting in a multiscale matched filter method [18,19]. The effectiveness of morphological, rather than linear, filters for vessel detection has been explored [22]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
