Localization of Optic Disc Using Blood Vessel Characteristics in Fundus Imagery

DOI

10.2991/978-94-6463-754-0_65How to use a DOI?

Keywords

Optic Disc (OD); Blood Vessel; Fundus Image; Vessel Distribution and Directional Characteristics

Abstract

Blood vessels and the optic disc serve as critical reference points in fundus images, playing an essential role in identifying and diagnosing retinal abnormalities. Since these structures may resemble bright or dark lesions, failing to isolate them beforehand can lead to false positives in automated screening processes. Therefore, accurately segmenting blood vessels and detecting the optic disc is a vital preliminary step. Our proposed method for optic disc detection utilizes vessel characteristics, identifying the optic disc as the convergence point of the vascular network. Blood vessel segmentation is performed using thresholding, region growing, and Gabor filtering techniques on retinal images from the Diarectdb0, Diarectdb1, DRIVE, and STARE datasets. The segmentation algorithm iteratively extracts major vessel structures by applying a threshold of 0.8 along with region-growing techniques. A novel stopping criterion enhances accuracy, achieving a segmentation success rate of 97.4% with an average AUC of 0.975. The unique vascular distribution and orientation facilitate optic disc localization, as its distinct pattern differentiates it from other retinal regions. Our method, which prioritizes major vessels over finer vascular structures, achieves an optic disc detection accuracy of 96.9% on Diarectdb0, 97.7% on Diarectdb1, 100% on DRIVE, and 95.1% on STARE, resulting in an overall accuracy of 97.1%. This refined vessel segmentation approach significantly improves optic disc detection, contributing to more effective automated retinal disease screening.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Borugula Ramamurthi
AU  - P. Vasuki
AU  - J. Kanimozhi
PY  - 2025
DA  - 2025/06/30
TI  - Localization of Optic Disc Using Blood Vessel Characteristics in Fundus Imagery
BT  - Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)
PB  - Atlantis Press
SP  - 744
EP  - 755
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-754-0_65
DO  - 10.2991/978-94-6463-754-0_65
ID  - Ramamurthi2025
ER  -