TY - JOUR
T1 - Evaluation of six registration methods for the human abdomen on clinically acquired CT
AU - Xu, Zhoubing
AU - Lee, Christopher P.
AU - Heinrich, Mattias P.
AU - Modat, Marc
AU - Rueckert, Daniel
AU - Ourselin, Sebastien
AU - Abramson, Richard G.
AU - Landman, Bennett A.
PY - 2016/8/1
Y1 - 2016/8/1
N2 - Objective: This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans. Methods: Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively. Results: The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT. Conclusion: There is substantial room for improvement in image registration for abdominal CT. Significance: All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.
AB - Objective: This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans. Methods: Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively. Results: The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT. Conclusion: There is substantial room for improvement in image registration for abdominal CT. Significance: All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.
UR - http://www.scopus.com/inward/record.url?scp=84986331410&partnerID=8YFLogxK
U2 - 10.1109/TBME.2016.2574816
DO - 10.1109/TBME.2016.2574816
M3 - Journal articles
C2 - 27254856
AN - SCOPUS:84986331410
SN - 0018-9294
VL - 63
SP - 1563
EP - 1572
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 8
M1 - 7482649
ER -