Abstract
We present an improved MR brain image registration algorithm, called TPS-HAMMER, which is based on the concepts of attribute vectors and hierarchical landmark selection scheme proposed in the highly successful HAMMER registration algorithm. We demonstrate that TPS-HAMMER algorithm yields better registration accuracy, robustness, and speed over HAMMER owing to (1) the employment of soft correspondence matching and (2) the utilization of thin-plate splines (TPS) for sparse-to-dense deformation field generation. These two aspects can be integrated into a unified framework to refine the registration iteratively by alternating between soft correspondence matching and dense deformation field estimation. Compared with HAMMER, TPS-HAMMER affords several advantages: (1) unlike the Gaussian propagation mechanism employed in HAMMER, which can be slow and often leaves unreached blotches in the deformation field, the deformation interpolation in the non-landmark points can be obtained immediately with TPS in our algorithm; (2) the smoothness of deformation field is preserved due to the nice properties of TPS; (3) possible misalignments can be alleviated by allowing the matching of the landmarks with a number of possible candidate points and enforcing more exact matches in the final stages of the registration. Extensive experiments have been conducted, using the original HAMMER as a comparison baseline, to validate the merits of TPS-HAMMER. The results show that TPS-HAMMER yields significant improvement in both accuracy and speed, indicating high applicability for the clinical scenario.
| Original language | English |
|---|---|
| Pages (from-to) | 2225-2233 |
| Number of pages | 9 |
| Journal | NeuroImage |
| Volume | 49 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2010 Feb 1 |
| Externally published | Yes |
Fingerprint
Keywords
- Deformable registration
- HAMMER
- Soft correspondence
- Thin-plate splines
ASJC Scopus subject areas
- Cognitive Neuroscience
- Neurology
Cite this
TPS-HAMMER : Improving HAMMER registration algorithm by soft correspondence matching and thin-plate splines based deformation interpolation. / Wu, Guorong; Yap, Pew Thian; Kim, Minjeong; Shen, Dinggang.
In: NeuroImage, Vol. 49, No. 3, 01.02.2010, p. 2225-2233.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - TPS-HAMMER
T2 - Improving HAMMER registration algorithm by soft correspondence matching and thin-plate splines based deformation interpolation
AU - Wu, Guorong
AU - Yap, Pew Thian
AU - Kim, Minjeong
AU - Shen, Dinggang
PY - 2010/2/1
Y1 - 2010/2/1
N2 - We present an improved MR brain image registration algorithm, called TPS-HAMMER, which is based on the concepts of attribute vectors and hierarchical landmark selection scheme proposed in the highly successful HAMMER registration algorithm. We demonstrate that TPS-HAMMER algorithm yields better registration accuracy, robustness, and speed over HAMMER owing to (1) the employment of soft correspondence matching and (2) the utilization of thin-plate splines (TPS) for sparse-to-dense deformation field generation. These two aspects can be integrated into a unified framework to refine the registration iteratively by alternating between soft correspondence matching and dense deformation field estimation. Compared with HAMMER, TPS-HAMMER affords several advantages: (1) unlike the Gaussian propagation mechanism employed in HAMMER, which can be slow and often leaves unreached blotches in the deformation field, the deformation interpolation in the non-landmark points can be obtained immediately with TPS in our algorithm; (2) the smoothness of deformation field is preserved due to the nice properties of TPS; (3) possible misalignments can be alleviated by allowing the matching of the landmarks with a number of possible candidate points and enforcing more exact matches in the final stages of the registration. Extensive experiments have been conducted, using the original HAMMER as a comparison baseline, to validate the merits of TPS-HAMMER. The results show that TPS-HAMMER yields significant improvement in both accuracy and speed, indicating high applicability for the clinical scenario.
AB - We present an improved MR brain image registration algorithm, called TPS-HAMMER, which is based on the concepts of attribute vectors and hierarchical landmark selection scheme proposed in the highly successful HAMMER registration algorithm. We demonstrate that TPS-HAMMER algorithm yields better registration accuracy, robustness, and speed over HAMMER owing to (1) the employment of soft correspondence matching and (2) the utilization of thin-plate splines (TPS) for sparse-to-dense deformation field generation. These two aspects can be integrated into a unified framework to refine the registration iteratively by alternating between soft correspondence matching and dense deformation field estimation. Compared with HAMMER, TPS-HAMMER affords several advantages: (1) unlike the Gaussian propagation mechanism employed in HAMMER, which can be slow and often leaves unreached blotches in the deformation field, the deformation interpolation in the non-landmark points can be obtained immediately with TPS in our algorithm; (2) the smoothness of deformation field is preserved due to the nice properties of TPS; (3) possible misalignments can be alleviated by allowing the matching of the landmarks with a number of possible candidate points and enforcing more exact matches in the final stages of the registration. Extensive experiments have been conducted, using the original HAMMER as a comparison baseline, to validate the merits of TPS-HAMMER. The results show that TPS-HAMMER yields significant improvement in both accuracy and speed, indicating high applicability for the clinical scenario.
KW - Deformable registration
KW - HAMMER
KW - Soft correspondence
KW - Thin-plate splines
UR - http://www.scopus.com/inward/record.url?scp=71849096928&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=71849096928&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2009.10.065
DO - 10.1016/j.neuroimage.2009.10.065
M3 - Article
VL - 49
SP - 2225
EP - 2233
JO - NeuroImage
JF - NeuroImage
SN - 1053-8119
IS - 3
ER -