Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images
In this paper, we develop and validate an open source, fully automatic algorithm to localize the left ventricular (LV) blood pool centroid in short axis cardiac cine MR images, enabling follow-on automated LV segmentation algorithms. The algorithm comprises four steps: (i) quantify motion to determi...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Published: |
Springer Verlag
2018
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/20535/ https://doi.org/10.1007/s11517-017-1750-7 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.20535 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.205352019-02-28T05:12:26Z http://eprints.um.edu.my/20535/ Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images Tan, Li Kuo Liew, Yih Miin Lim, Einly Abdul Aziz, Yang Faridah Chee, Kok Han McLaughlin, Robert A. R Medicine In this paper, we develop and validate an open source, fully automatic algorithm to localize the left ventricular (LV) blood pool centroid in short axis cardiac cine MR images, enabling follow-on automated LV segmentation algorithms. The algorithm comprises four steps: (i) quantify motion to determine an initial region of interest surrounding the heart, (ii) identify potential 2D objects of interest using an intensity-based segmentation, (iii) assess contraction/expansion, circularity, and proximity to lung tissue to score all objects of interest in terms of their likelihood of constituting part of the LV, and (iv) aggregate the objects into connected groups and construct the final LV blood pool volume and centroid. This algorithm was tested against 1140 datasets from the Kaggle Second Annual Data Science Bowl, as well as 45 datasets from the STACOM 2009 Cardiac MR Left Ventricle Segmentation Challenge. Correct LV localization was confirmed in 97.3% of the datasets. The mean absolute error between the gold standard and localization centroids was 2.8 to 4.7 mm, or 12 to 22% of the average endocardial radius. Springer Verlag 2018 Article PeerReviewed Tan, Li Kuo and Liew, Yih Miin and Lim, Einly and Abdul Aziz, Yang Faridah and Chee, Kok Han and McLaughlin, Robert A. (2018) Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images. Medical & Biological Engineering & Computing, 56 (6). pp. 1053-1062. ISSN 0140-0118 https://doi.org/10.1007/s11517-017-1750-7 doi:10.1007/s11517-017-1750-7 |
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 |
spellingShingle |
R Medicine Tan, Li Kuo Liew, Yih Miin Lim, Einly Abdul Aziz, Yang Faridah Chee, Kok Han McLaughlin, Robert A. Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
description |
In this paper, we develop and validate an open source, fully automatic algorithm to localize the left ventricular (LV) blood pool centroid in short axis cardiac cine MR images, enabling follow-on automated LV segmentation algorithms. The algorithm comprises four steps: (i) quantify motion to determine an initial region of interest surrounding the heart, (ii) identify potential 2D objects of interest using an intensity-based segmentation, (iii) assess contraction/expansion, circularity, and proximity to lung tissue to score all objects of interest in terms of their likelihood of constituting part of the LV, and (iv) aggregate the objects into connected groups and construct the final LV blood pool volume and centroid. This algorithm was tested against 1140 datasets from the Kaggle Second Annual Data Science Bowl, as well as 45 datasets from the STACOM 2009 Cardiac MR Left Ventricle Segmentation Challenge. Correct LV localization was confirmed in 97.3% of the datasets. The mean absolute error between the gold standard and localization centroids was 2.8 to 4.7 mm, or 12 to 22% of the average endocardial radius. |
format |
Article |
author |
Tan, Li Kuo Liew, Yih Miin Lim, Einly Abdul Aziz, Yang Faridah Chee, Kok Han McLaughlin, Robert A. |
author_facet |
Tan, Li Kuo Liew, Yih Miin Lim, Einly Abdul Aziz, Yang Faridah Chee, Kok Han McLaughlin, Robert A. |
author_sort |
Tan, Li Kuo |
title |
Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
title_short |
Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
title_full |
Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
title_fullStr |
Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
title_full_unstemmed |
Automatic localization of the left ventricular blood pool centroid in short axis cardiac cine MR images |
title_sort |
automatic localization of the left ventricular blood pool centroid in short axis cardiac cine mr images |
publisher |
Springer Verlag |
publishDate |
2018 |
url |
http://eprints.um.edu.my/20535/ https://doi.org/10.1007/s11517-017-1750-7 |
_version_ |
1643691308431179776 |
score |
13.188404 |