Simultaneous Population Based Image Alignment for Template Free Spatial Normalisation of Brain Anatomy
Current approaches to spatial normalisation of brain images have made use of a target image to which each subject image is matched. However, 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 such cases this paper proposes that a better approach may be to seek a method of driving subjects in the group into registration with each other, rather than with an unrepresentative template. This paper explores the approach of extending registration concepts from multi-modality registration, 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 simultaneously. Geometric constraints forcing the convergence to an average geometric shape are discussed and results presented on synthetic images and clinical brain image data.
KeywordsMutual Information White Matter Lesion Spatial Normalisation Fronto Temporal Dementia Joint Probability Distribution
Unable to display preview. Download preview PDF.
- 1.Christensen, G.E., Johnson, H.J.: Consistent image registration. Transactions on Medical Imaging, 568–582 (2001)Google Scholar
- 3.Collignon, A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.: Automated multimodality image registration using information theory. In: Bizais, Y., Barillot, C., Di Paola, R. (eds.) Proceedings of Information Processing in Medical Imaging, Brest, France, pp. 263–274. Kluwer Academic Publishers, Dordrecht (1995)Google Scholar
- 4.Collins, D.L., Evans, A.C., Holmes, C., Peters, T.M.: Automatic 3D segmentation of neuro-anatomical structures from MRI. In: Bizais, Y., Barillot, C., Di Paola, R. (eds.) Proceedings of Information Processing in Medical Imaging, Brest, France, pp. 139–152. Kluwer Academic Publishers, Dordrecht (1995)Google Scholar
- 8.Hill, D.L.G., Studholme, C., Hawkes, D.J.: Voxel similarity measures for automated image registration. In: Proceedings of Visualisation in Biomedical Computing, Rochester Mn.,U.S.A., vol. SPIE 2359, pp. 205–216. SPIE Press, Bellingham (1994)Google Scholar
- 10.Lester, H., Arridge, S., Jansons, K., Lemieux, L., Hajnal, J., Oatridge, A.: Nonlinear registration with variable viscosity fluid algorithm. In: Proc. Image Processing in Medical Imaging, pp. 238–251. Springer, Heidelberg (1999)Google Scholar
- 11.Miller, E.: Learning from One Example in Machine Vision by Sharing Probability Densities. PhD thesis, Massachusetts Institute of Technology (2002)Google Scholar
- 13.Studholme, C., Cardenas, V., Schuff, N., Rosen, H., Miller, B., Weiner, M.: Detecting spatially consistent structural differences in alzheimer’s and fronto temporal dementia using deformation morphometry. In: Proceedings of 4th International Conference on Medical Image Computing and Computer Assisted Interventions, pp. 41–48 (2001)Google Scholar
- 18.Viola, P.A., Wells, W.M.: Alignment by maximisation of mutual information. In: Proceedings of the 5th International Conference on Computer Vision, pp. 15–23 (1995)Google Scholar