Phase and structure based input enhancement for retinal vessel segmentation
Journal of Electrical Engineering · 01.04.2026 · 77 (2) · 113-122
DOI: 10.2478/jee-2026-0012 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Electrical Engineering, online erschienen am 18.04.2026. Verfasst von Ondrej Straka und 4 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This paper presents a study of retinal vessel segmentation that combines traditional image processing methods with deep learning. Two edge detection techniques, Phase Stretch Transform (PST) and B-COSFIRE filters. Both were applied as preprocessing steps to enhance vessel structures before segmentation using a U-net. PST parameters were optimized via a parallel genetic algorithm, and the resulting vessel maps replaced one channel in the RGB color space of the original fundus images. The method was evaluated on five public datasets (DRIVE, CHASE DB1, HRF, TREND, and FIVES) using standard segmentation metrics. Results show improved performance on DRIVE, CHASE and HRF datasets, and comparable or slightly improved performance on other datasets, indicating that spectral and structural enhancement can be complementary to deep learning methods without increasing computational complexity.
Zitieren
APA
Straka, O., Zubek, F., Kovac, M., Pavlovicova, J., & Kurilova, V. (2026). Phase and structure based input enhancement for retinal vessel segmentation. Journal of Electrical Engineering, 77(2), 113-122. https://doi.org/10.2478/jee-2026-0012
Vancouver
Straka O, Zubek F, Kovac M, Pavlovicova J, Kurilova V. Phase and structure based input enhancement for retinal vessel segmentation. Journal of Electrical Engineering. 2026;77(2):113-122. doi:10.2478/jee-2026-0012
BibTeX
@article{Straka2026,
author = {Straka, Ondrej and Zubek, Filip and Kovac, Michal and Pavlovicova, Jarmila and Kurilova, Veronika},
title = {Phase and structure based input enhancement for retinal vessel segmentation},
journal = {Journal of Electrical Engineering},
year = {2026},
volume = {77},
number = {2},
pages = {113--122},
doi = {10.2478/jee-2026-0012}
}
EUVIMED