Title: Automatic vessel lumen segmentation in optical coherence tomography images

Authors: Kamel K. Mohammed; Noha M. Elfiky; Ashraf Darwish; Aboul Ella Hassanien

Addresses: Center for Virus Research and Studies, Al-Azhar University, Cairo, Egypt ' Department of Business Analytics, School of Economics and Business, Saint Mary's College of California, CA, USA ' Faculty of Science, Helwan University, Helwan, Egypt ' Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt

Abstract: Automatic vessel lumen segmentation is a very challenging vision task, yet it is extremely important. Automatic vessel lumen segmentation helps in better diagnostics and therapy of coronary artery disease. In this paper, we propose an automatic vessel lumen segmentation framework that relies on a fully convolutional network (FCN), motivated by the fact that FCNs have been widely used recently in various biomedical image segmentation applications showing very promising results. In addition, the proposed framework has been evaluated using standard evaluation metrics. The proposed framework has been compared with state-of-the-art methods for vessel lumen segmentation and we obtained more accurate results using the same publicly available optical coherence tomography (OCT) images dataset. The experimental results show that the proposed architecture achieves high evaluation scores; with absolute mean difference (AMD) of 1.62%, Sensitivity of 99.43%, Specificity of 99.25%, Hausdorff distance of 12.42, and F1 score of 99.34%.

Keywords: optical coherence tomography; OCT; vessel segmentation; lumen detection; medical imaging; deep learning; image processing; biomedical engineering; cardiovascular imaging; machine learning; medical image analysis.

DOI: 10.1504/IJRIS.2023.136386

International Journal of Reasoning-based Intelligent Systems, 2023 Vol.15 No.3/4, pp.173 - 182

Received: 05 Aug 2021
Accepted: 13 Apr 2022
Published online: 31 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article