Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation
- PDF / 3,193,943 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 80 Downloads / 169 Views
ORIGINAL ARTICLE
Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation Beatriz Remeseiro1,2
· Ana Maria Mendonça1,3 · Aurélio Campilho1,3
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Several systemic diseases affect the retinal blood vessels, and thus, their assessment allows an accurate clinical diagnosis. This assessment entails the estimation of the arteriolar-to-venular ratio (AVR), a predictive biomarker of cerebral atrophy and cardiovascular events in adults. In this context, different automatic and semiautomatic image-based approaches for artery/vein (A/V) classification and AVR estimation have been proposed in the literature, to the point of having become a hot research topic in the last decades. Most of these approaches use a wide variety of image properties, often redundant and/or irrelevant, requiring a training process that limits their generalization ability when applied to other datasets. This paper presents a new automatic method for A/V classification that just uses the local contrast between blood vessels and their surrounding background, computes a graph that represents the vascular structure, and applies a multilevel thresholding to obtain a preliminary classification. Next, a novel graph propagation approach was developed to obtain the final A/V classification and to compute the AVR. Our approach has been tested on two public datasets (INSPIRE and DRIVE), obtaining high classification accuracy rates, especially in the main vessels, and AVR ratios very similar to those provided by human experts. Therefore, our fully automatic method provides the reliable results without any training step, which makes it suitable for use with different retinal image datasets and as part of any clinical routine. Keywords Retinal images · Artery/vein classification · Arteriolar-to-venular ratio · Multilevel thresholding · Graph propagation
1 Introduction Human blood circulation can be observed in vivo in the eye, allowing to diagnose several systemic diseases that affect the retinal vessels in such a way that they become thicker or narrower [1,2]. Some of these diseases include diabetes,
B
Beatriz Remeseiro [email protected] Ana Maria Mendonça [email protected] Aurélio Campilho [email protected]
1
INESC TEC - INESC Technology and Science, Campus da FEUP, Rua Dr. Roberto Frias, 4200–465 Porto, Portugal
2
Present Address: Department of Computer Science, Universidad de Oviedo, Campus de Gijón s/n, 33203 Gijón, Spain
3
Faculdade de Engenharia, Universidade do Porto, Campus da FEUP, Rua Dr. Roberto Frias, 4200–465 Porto, Portugal
with a 8.5% of global prevalence among adults according to the WHO1 ; raised blood pressure, which is estimated to cause about the 12.8% of the total of all deaths worldwide as reported by WHO; and different vascular disorders. More specifically, diabetic retinopathy frequently causes vessel diameter alterations [3], while dilatation and elongation of main arteries and veins are often associated with hype
Data Loading...
