Deformable density matching for 3D non-rigid registration of shapes

Authors:
Arunabha S. Roy;Ajay Gopinath;Anand Rangarajan
Affiliations:
Imaging Technologies Laboratory, GE Global Research Center, Bangalore, India;Imaging Technologies Laboratory, GE Global Research Center, Bangalore, India;Department of CISE, University of Florida, Gainesville, FL
Venue:
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Year:
2007

Citing 4
Cited 3

A Robust Algorithm for Point Set Registration Using Mixture of Gaussians

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Diffeomorphic matching of distributions: a new approach for unlabelled point-sets and sub-manifolds matching

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
3-D diffeomorphic shape registration on hippocampal data sets

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Simultaneous nonrigid registration of multiple point sets and atlas construction

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III

Automatic Mutual Nonrigid Registration of Dense Surfaces by Graphical Model Based Inference

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Generalized L2-Divergence and Its Application to Shape Alignment

IPMI '09 Proceedings of the 21st International Conference on Information Processing in Medical Imaging
Closed-Form Jensen-Renyi Divergence for Mixture of Gaussians and Applications to Group-Wise Shape Registration

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

There exists a large body of literature on shape matching and registration in medical image analysis. However, most of the previous work is focused on matching particular sets of features--point-sets, lines, curves and surfaces. In this work, we forsake specific geometric shape representations and instead seek probabilistic representations-- specifically Gaussian mixture models--of shapes. We evaluate a closed-form distance between two probabilistic shape representations for the general case where the mixture models differ in variance and the number of components. We then cast non-rigid registration as a deformable density matching problem. In our approach, we take one mixture density onto another by deforming the component centroids via a thin-plate spline (TPS) and also minimizing the distance with respect to the variance parameters. We validate our approach on synthetic and 3D arterial tree data and evaluate it on 3D hippocampal shapes.