Format

Send to

Choose Destination
J Biomed Opt. 2017 Dec;22(12):1-9. doi: 10.1117/1.JBO.22.12.126005.

Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography.

Author information

1
University of Malaya, Faculty of Engineering, Department of Biomedical Engineering, Kuala Lumpur, Malaysia.
2
University of Malaya, Faculty of Medicine, Department of Biomedical Imaging, Kuala Lumpur, Malaysia.
3
University of Malaya, University Malaya Research Imaging Centre, Kuala Lumpur, Malaysia.
4
University of Adelaide, Faculty of Health and Medical Sciences, Adelaide Medical School, Australian, Australia.
5
University of Adelaide, Institute for Photonics and Advanced Sensing (IPAS), Adelaide, Australia.
6
University of Western Australia, School of Electrical, Electronic and Computer Engineering, Western, Australia.
7
University of Malaya, Faculty of Medicine, Department of Medicine, Kuala Lumpur, Malaysia.

Abstract

Intravascular optical coherence tomography (OCT) is an optical imaging modality commonly used in the assessment of coronary artery diseases during percutaneous coronary intervention. Manual segmentation to assess luminal stenosis from OCT pullback scans is challenging and time consuming. We propose a linear-regression convolutional neural network to automatically perform vessel lumen segmentation, parameterized in terms of radial distances from the catheter centroid in polar space. Benchmarked against gold-standard manual segmentation, our proposed algorithm achieves average locational accuracy of the vessel wall of 22 microns, and 0.985 and 0.970 in Dice coefficient and Jaccard similarity index, respectively. The average absolute error of luminal area estimation is 1.38%. The processing rate is 40.6 ms per image, suggesting the potential to be incorporated into a clinical workflow and to provide quantitative assessment of vessel lumen in an intraoperative time frame.

KEYWORDS:

coronary lumen; neural network; optical coherence tomography; optical diagnostics; pattern recognition; segmentation

PMID:
29274144
DOI:
10.1117/1.JBO.22.12.126005
[Indexed for MEDLINE]

Supplemental Content

Loading ...
Support Center