A template free approach to volumetric spatial normalization of brain anatomy

Abstract Approaches to brain image spatial normalization conventionally make use of a target image to which each subject image is separately matched. In many cases the use of a single brain template, or a statistical one derived from multiple subjects of another population, does not adequately capture the structure present in a population of anatomies under investigation. In this paper, we therefore explore an approach which seeks to drive subjects in the group of anatomies of interest into registration with each other, rather than with an unrepresentative template. We examine the extension of registration concepts from multi-modality image alignment, specifically those deriving criteria from the joint probability distribution of image values, to the general case of describing the alignment of a population of images. Geometric constraints forcing the convergence of the set of transformations to an average geometric shape are discussed and results presented on synthetic images. Experiments show the ability to recover average shape from a population of objects having varying material contrasts and sub-groups with additional tissue structure simulating lesions. Initial results are also presented showing the application of the technique to a group of 32 magnetic resonance images of the brain.

[1]  Gary E. Christensen,et al.  Consistent image registration , 2001, IEEE Transactions on Medical Imaging.

[2]  G. Marchal,et al.  Multi-modal volume registration by maximization of mutual information , 1997 .

[3]  Norbert Schuff,et al.  Detecting Spatially Consistent Structural Differences in Alzheimer's and Fronto Temporal Dementia Using Deformation Morphometry , 2001, MICCAI.

[4]  R. Woods,et al.  Mathematical/computational challenges in creating deformable and probabilistic atlases of the human brain , 2000, Human brain mapping.

[5]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6]  Fazlollah M. Reza,et al.  Introduction to Information Theory , 2004, Lecture Notes in Electrical Engineering.

[7]  Nicholas Ayache,et al.  A scheme for automatically building three-dimensional morphometric anatomical atlases: application to a skull atlas , 1998, Medical Image Anal..

[8]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[9]  Christos Davatzikos,et al.  Spatial Transformation and Registration of Brain Images Using Elastically Deformable Models , 1997, Comput. Vis. Image Underst..

[10]  Sung Yong Shin,et al.  Scattered Data Interpolation with Multilevel B-Splines , 1997, IEEE Trans. Vis. Comput. Graph..

[11]  Jean-Philippe Thirion,et al.  Image matching as a diffusion process: an analogy with Maxwell's demons , 1998, Medical Image Anal..

[12]  J C Mazziotta,et al.  Automated image registration: II. Intersubject validation of linear and nonlinear models. , 1998, Journal of computer assisted tomography.

[13]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[14]  Ruzena Bajcsy,et al.  The Institute For Research In Cognitive Science Elastically Deforming a Three-Dimensional Atlas to Match Anatomical Brain Images , 1993 .

[15]  Erik Gundersen Miller,et al.  Learning from one example in machine vision by sharing probability densities , 2002 .

[16]  U. Grenander,et al.  Computational anatomy: an emerging discipline , 1998 .

[17]  Paul A. Viola.  Alignment by maximisation of mutual information , 1993 .

[18]  A Collignon,et al.  Automated multimodality image registration using information theory , 1995 .

[19]  Simon R. Arridge,et al.  Non-linear Registration with the Variable Viscosity Fluid Algorithm , 1999, IPMI.

[20]  Michael I. Miller,et al.  Deformable templates using large deformation kinematics , 1996, IEEE Trans. Image Process..

[21]  Colin Studholme,et al.  Voxel similarity measures for automated image registration , 1994, Other Conferences.