Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography
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...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Published: |
International Society for Optical Engineering (SPIE)
2017
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/18897/ http://dx.doi.org/10.1117/1.JBO.22.12.126005 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.18897 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.188972018-06-28T06:46:10Z http://eprints.um.edu.my/18897/ Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography Yong, Y.L. Tan, L.K. McLaughlin, R.A. Chee, K.H. Liew, Y.M. R Medicine T Technology (General) 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. International Society for Optical Engineering (SPIE) 2017 Article PeerReviewed Yong, Y.L. and Tan, L.K. and McLaughlin, R.A. and Chee, K.H. and Liew, Y.M. (2017) Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography. Journal of Biomedical Optics (JBO), 22 (12). p. 1. http://dx.doi.org/10.1117/1.JBO.22.12.126005 doi:10.1117/1.JBO.22.12.126005 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
R Medicine T Technology (General) |
spellingShingle |
R Medicine T Technology (General) Yong, Y.L. Tan, L.K. McLaughlin, R.A. Chee, K.H. Liew, Y.M. Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
description |
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. |
format |
Article |
author |
Yong, Y.L. Tan, L.K. McLaughlin, R.A. Chee, K.H. Liew, Y.M. |
author_facet |
Yong, Y.L. Tan, L.K. McLaughlin, R.A. Chee, K.H. Liew, Y.M. |
author_sort |
Yong, Y.L. |
title |
Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
title_short |
Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
title_full |
Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
title_fullStr |
Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
title_full_unstemmed |
Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
title_sort |
linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography |
publisher |
International Society for Optical Engineering (SPIE) |
publishDate |
2017 |
url |
http://eprints.um.edu.my/18897/ http://dx.doi.org/10.1117/1.JBO.22.12.126005 |
_version_ |
1643690829021184000 |
score |
13.18916 |