TY - JOUR
T1 - Multi-modal image set registration and atlas formation
AU - Lorenzen, Peter
AU - Prastawa, Marcel
AU - Davis, Brad
AU - Gerig, Guido
AU - Bullitt, Elizabeth
AU - Joshi, Sarang
N1 - Funding Information:
The authors would like to thank Matthieu Jomier for producing the class posterior mass functions used in the atlas formation and Dr. Mark Foskey for insightful discussions. This work was supported by NIBIB-NIH grant R01 EB000219, NIH-HLB grant R01 HL69808, DOD Prostate Cancer Research Program DAMD17-03-1-0134, NIMH grant MH064580 Longitudinal MRI Study of Brain Development in Fragile X, and the NDRC.
PY - 2006/6
Y1 - 2006/6
N2 - In this paper, we present a Bayesian framework for both generating inter-subject large deformation transformations between two multi-modal image sets of the brain and for forming multi-class brain atlases. In this framework, the estimated transformations are generated using maximal information about the underlying neuroanatomy present in each of the different modalities. This modality independent registration framework is achieved by jointly estimating the posterior probabilities associated with the multi-modal image sets and the high-dimensional registration transformations mapping these posteriors. To maximally use the information present in all the modalities for registration, Kullback-Leibler divergence between the estimated posteriors is minimized. Registration results for image sets composed of multi-modal MR images of healthy adult human brains are presented. Atlas formation results are presented for a population of five infant human brains.
AB - In this paper, we present a Bayesian framework for both generating inter-subject large deformation transformations between two multi-modal image sets of the brain and for forming multi-class brain atlases. In this framework, the estimated transformations are generated using maximal information about the underlying neuroanatomy present in each of the different modalities. This modality independent registration framework is achieved by jointly estimating the posterior probabilities associated with the multi-modal image sets and the high-dimensional registration transformations mapping these posteriors. To maximally use the information present in all the modalities for registration, Kullback-Leibler divergence between the estimated posteriors is minimized. Registration results for image sets composed of multi-modal MR images of healthy adult human brains are presented. Atlas formation results are presented for a population of five infant human brains.
KW - Atlas formation
KW - Computational anatomy
KW - Information theory
KW - Inverse consistent registration
KW - Medical image analysis
KW - Multi-modal image set registration
UR - http://www.scopus.com/inward/record.url?scp=33645881665&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33645881665&partnerID=8YFLogxK
U2 - 10.1016/j.media.2005.03.002
DO - 10.1016/j.media.2005.03.002
M3 - Article
C2 - 15919231
AN - SCOPUS:33645881665
VL - 10
SP - 440
EP - 451
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
IS - 3 SPEC. ISS.
ER -