Artery-venous classification in fluorescein angiograms based on region growing with sequential and structural features. (July 2020)

• Record Type: Journal Article
• Authors: Sun, Gang; Liu, Xiaoyan; Gong, Junhui; Gao, Ling
• Is Part Of: Computer methods and programs in biomedicine. Volume 190(2020)
• Publication Date: 2020-07
• Subjects: Fluorescein angiography -- Artery-venous classification -- Retinal circulation -- Region growing -- Image processing; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105340
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A method is proposed to classify arteries and veins in fluorescein angiograms. It has high accuracy and is advantageous in classifying thin vessels. It has potential to reduce the time costs in measurement of important parameters (such as arterio-venous passage time and arterio-venous width ratio) that are proven useful in assessing circulation disturbance and vessel abnormalities. Abstract: Background and objectives: Fluorescein angiography (FA) is widely used in ophthalmology for examining retinal hemodynamics and vascular morphology. Artery-venous classification is an important step in FA image processing for measurement of feature parameters, such as arterio-venous passage time (AVP) and arterio-venous width ratio (AVR) that are proven useful in clinical assessment of circulation disturbance and vessel abnormalities. However, manual artery-venous classification needs expertise and is rather time consuming, and little effort has been devoted to develop automatic classification methods. In order to solve this problem, we propose a novel artery-venous classification method using region growing strategy with sequential and structural features (RGSS). Methods: The main procedures of our proposed RGSS method include: (i) registration of FA image sequence by mutual-information method; (ii) extraction of sequential features of the dye perfusion process from the registrated FA images; (iii) extraction of vessel structural features from vascular centerline map; (iv) based on the obtained features, seeds of arteries and veins within initial growing region (here optic disk) are generated and then propagated in the entire vessel network using region growing strategy. The RGSS method was tested on our own dataset and public Duke dataset, and its performance was evaluated quantitatively. Results: Tests show that RGSS method is able to classify arteries and veins from the complicated vessel network in FA images, with high classification accuracy of 0.91 ± 0.04 on Duke dataset and 0.92 ± 0.03 on our dataset. The employed sequential and structural features are demonstrated to be effective in classifying thin arteries and veins at vessel crossings. Conclusions: Automatic artery-venous classification can be accomplished using our proposed RGSS method with high accuracy. The RGSS method not only emancipates ophthalmologists from hard work of manual marking of arteries and veins, but also helps in measuring important parameters (such as AVP and AVR) for clinical assessment of circulation disturbance and vessel abnormalities.