Unsupervised multiscale retinal blood vessel segmentation using fundus images. Issue 11 (14th August 2020)

• Record Type: Journal Article
• Authors: Upadhyay, Kamini; Agrawal, Monika; Vashist, Praveen
• Is Part Of: IET image processing. Volume 14:Issue 11(2020)
• Page Start: 2616
• Page End: 2625
• Publication Date: 2020-08-14
• Subjects: blood vessels -- curvelet transforms -- medical image processing -- eye -- image segmentation -- image enhancement -- wavelet transforms -- biomedical optical imaging -- diseases; unsupervised multiscale retinal blood vessel segmentation -- retinal disease -- structural changes -- rule‐based retinal blood vessel segmentation algorithm -- directional‐wavelet transform -- vessel enhancement -- retinal image analysis -- morphological thickness‐correction -- curvelet transform; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0969
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Blood vessel segmentation is a vital step in automated diagnosis of retinal diseases. Some retinal diseases progress with structural changes in the vessels whereas in others, vessels may remain unaffected. Segmentation of vessels is inevitable in both the cases. The extracted vessel map can be studied for these structural changes or can be removed to highlight other abnormalities of the retina. This study presents a rule‐based retinal blood vessel segmentation algorithm. It implements two multi‐scale approaches, local directional‐wavelet transform and global curvelet transform, together in a novel manner for vessel enhancement and thereby segmentation. The authors have proposed a generic field‐of‐view mask for extraction of region‐of‐interest. Further, a morphological thickness‐correction step, to recover vessel‐boundary pixels, is also proposed. The significant contribution of this work is, segmentation of fine vessels while preserving the thickness of major vessels. Moreover, the algorithm is robust, as it performs consistently well, on four public databases, DRIVE, STARE, CHASE_DB‐1 and HRF. Performance of the proposed algorithm is evaluated in terms of eight measures : accuracy, sensitivity, specificity, precision, F‐1 score, G‐mean, MCC and AUC, where it has outperformed many other existing methods. Zero data dependency gives the suggested algorithm, an edge over other state‐of‐the‐art supervised methods.