TY - JOUR
T1 - Right ventricle segmentation from cardiac MRI
T2 - A collation study
AU - Petitjean, Caroline
AU - Zuluaga, Maria A.
AU - Bai, Wenjia
AU - Dacher, Jean Nicolas
AU - Grosgeorge, Damien
AU - Caudron, JérÔme
AU - Ruan, Su
AU - Ayed, Ismail Ben
AU - Cardoso, M. Jorge
AU - Chen, Hsiang Chou
AU - Jimenez-Carretero, Daniel
AU - Ledesma-Carbayo, Maria J.
AU - Davatzikos, Christos
AU - Doshi, Jimit
AU - Erus, Guray
AU - Maier, Oskar M.O.
AU - Nambakhsh, Cyrus M.S.
AU - Ou, Yangming
AU - Ourselin, Sébastien
AU - Peng, Chun Wei
AU - Peters, Nicholas S.
AU - Peters, Terry M.
AU - Rajchl, Martin
AU - Rueckert, Daniel
AU - Santos, Andres
AU - Shi, Wenzhe
AU - Wang, Ching Wei
AU - Wang, Haiyan
AU - Yuan, Jing
N1 - Publisher Copyright:
© 2014 Elsevier B.V.
PY - 2015/1/1
Y1 - 2015/1/1
N2 - Magnetic Resonance Imaging (MRI), a reference examination for cardiac morphology and function in humans, allows to image the cardiac right ventricle (RV) with high spatial resolution. The segmentation of the RV is a difficult task due to the variable shape of the RV and its ill-defined borders in these images. The aim of this paper is to evaluate several RV segmentation algorithms on common data. More precisely, we report here the results of the Right Ventricle Segmentation Challenge (RVSC), concretized during the MICCAI'12 Conference with an on-site competition. Seven automated and semi-automated methods have been considered, along them three atlas-based methods, two prior based methods, and two prior-free, image-driven methods that make use of cardiac motion. The obtained contours were compared against a manual tracing by an expert cardiac radiologist, taken as a reference, using Dice metric and Hausdorff distance. We herein describe the cardiac data composed of 48 patients, the evaluation protocol and the results. Best results show that an average 80% Dice accuracy and a 1. cm Hausdorff distance can be expected from semi-automated algorithms for this challenging task on the datasets, and that an automated algorithm can reach similar performance, at the expense of a high computational burden. Data are now publicly available and the website remains open for new submissions (http://www.litislab.eu/rvsc/).
AB - Magnetic Resonance Imaging (MRI), a reference examination for cardiac morphology and function in humans, allows to image the cardiac right ventricle (RV) with high spatial resolution. The segmentation of the RV is a difficult task due to the variable shape of the RV and its ill-defined borders in these images. The aim of this paper is to evaluate several RV segmentation algorithms on common data. More precisely, we report here the results of the Right Ventricle Segmentation Challenge (RVSC), concretized during the MICCAI'12 Conference with an on-site competition. Seven automated and semi-automated methods have been considered, along them three atlas-based methods, two prior based methods, and two prior-free, image-driven methods that make use of cardiac motion. The obtained contours were compared against a manual tracing by an expert cardiac radiologist, taken as a reference, using Dice metric and Hausdorff distance. We herein describe the cardiac data composed of 48 patients, the evaluation protocol and the results. Best results show that an average 80% Dice accuracy and a 1. cm Hausdorff distance can be expected from semi-automated algorithms for this challenging task on the datasets, and that an automated algorithm can reach similar performance, at the expense of a high computational burden. Data are now publicly available and the website remains open for new submissions (http://www.litislab.eu/rvsc/).
KW - Cardiac MRI
KW - Collation study
KW - Right ventricle segmentation
KW - Segmentation challenge
KW - Segmentation method evaluation
UR - http://www.scopus.com/inward/record.url?scp=84919361099&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919361099&partnerID=8YFLogxK
U2 - 10.1016/j.media.2014.10.004
DO - 10.1016/j.media.2014.10.004
M3 - Article
C2 - 25461337
AN - SCOPUS:84919361099
SN - 1361-8415
VL - 19
SP - 187
EP - 202
JO - Medical image analysis
JF - Medical image analysis
IS - 1
ER -