BibTex format

author = {Zhuang, X and Li, L and Payer, C and Stern, D and Urschler, M and Heinrich, M and Oster, J and Wang, C and Smedby, O and Bian, C and Yang, X and Heng, P-A and Mortazi, A and Bagci, U and Yang, G and Sun, C and Galisot, G and Ramel, J-Y and Brouard, T and Tong, Q and Si, W and Liao, X and Zeng, G and Shi, Z and Zheng, G and Wang, C and MacGillivray, T and Newby, D and Rhode, K and Ourselin, S and Mohiaddin, R and Keegan, J and Firmin, D and Yang, G},
doi = {10.1016/},
journal = {Medical Image Analysis},
title = {Evaluation of algorithms for multi-modality whole heart segmentation: An open-access grand challenge},
url = {},
volume = {58},
year = {2019}

RIS format (EndNote, RefMan)

AB - Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS),which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functionsof the heart. However, automating this segmentation can be challenging due to the large variation of the heart shape,and different image qualities of the clinical data. To achieve this goal, an initial set of training data is generally neededfor constructing priors or for training. Furthermore, it is difficult to perform comparisons between different methods,largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologiesand evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provided 120 three-dimensionalcardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environmentswith manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelvegroups, have been evaluated. The results showed that the performance of CT WHS was generally better than thatof MRI WHS. The segmentation of the substructures for different categories of patients could present different levelsof challenge due to the difference in imaging and variations of heart shapes. The deep learning (DL)-based methodsdemonstrated great potential, though several of them reported poor results in the blinded evaluation. Their performance could vary greatly across different network structures and training strategies. The conventional algorithms,mainly based on multi-atlas segmentation, demonstrated good performance, though the accuracy and computationalefficiency could be limited. The challenge, including provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, conti
AU - Zhuang,X
AU - Li,L
AU - Payer,C
AU - Stern,D
AU - Urschler,M
AU - Heinrich,M
AU - Oster,J
AU - Wang,C
AU - Smedby,O
AU - Bian,C
AU - Yang,X
AU - Heng,P-A
AU - Mortazi,A
AU - Bagci,U
AU - Yang,G
AU - Sun,C
AU - Galisot,G
AU - Ramel,J-Y
AU - Brouard,T
AU - Tong,Q
AU - Si,W
AU - Liao,X
AU - Zeng,G
AU - Shi,Z
AU - Zheng,G
AU - Wang,C
AU - MacGillivray,T
AU - Newby,D
AU - Rhode,K
AU - Ourselin,S
AU - Mohiaddin,R
AU - Keegan,J
AU - Firmin,D
AU - Yang,G
DO - 10.1016/
PY - 2019///
SN - 1361-8415
TI - Evaluation of algorithms for multi-modality whole heart segmentation: An open-access grand challenge
T2 - Medical Image Analysis
UR -
UR -
VL - 58
ER -