Deformable registration of diffusion tensor MR images with explicit orientation optimization

Authors:
Hui Zhang;Paul A. Yushkevich;James C. Gee
Affiliations:
Department of Computer & Information Science, University of Pennsylvania;Department of Radiology, University of Pennsylvania;Department of Radiology, University of Pennsylvania
Venue:
MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2005

Citing 1
Cited 6

Deformations incorporating rigid structures

Computer Vision and Image Understanding

Automatic Deformable Diffusion Tensor Registration for Fiber Population Analysis

MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Diffusion Tensor Field Registration in the Presence of Uncertainty

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
Non-rigid Registration of High Angular Resolution Diffusion Images Represented by Gaussian Mixture Fields

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
Multivariate normalization with symmetric diffeomorphisms for multivariate studies

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Affine registration of diffusion tensor MR images

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
An embedding framework for myocardial velocity processing with MRI

Miar'06 Proceedings of the Third international conference on Medical Imaging and Augmented Reality

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a novel deformable registration algorithm for diffusion tensor (DT) MR images that enables explicit analytic optimization of tensor reorientation. The optimization seeks a piecewise affine transformation that divides the image domain into uniform regions and transforms each of them affinely. The objective function captures both the image similarity and the smoothness of the transformation across region boundaries. The image similarity enables explicit orientation optimization by incorporating tensor reorientation, which is necessary for warping DT images. The objective function is formulated in a way that allows explicit implementation of analytic derivatives to drive fast and accurate optimization using the conjugate gradient method. The optimal transformation is hierarchically refined in a subdivision framework. A comparison with affine registration for inter-subject normalization of 8 subjects shows that our algorithm improves the alignment of manually segmented white matter structures (corpus callosum and cortio-spinal tracts).