Abstract
Abdominal image non-rigid registration is a particularly challenging task due to the presence of multiple organs, many of which move independently, contributing to independent deformations. Local-affine registration methods can handle multiple independent movements by assigning prior definition of each affine component and its spatial extent which is less suitable for multiple soft-tissue structures as in the abdomen. Instead, we propose to use the local-affine assumption as a prior constraint within the dense deformation field computation. Our method use the dense correspondences field computed using the optical-flow equations to estimate the local-affine transformations that best represent the deformation associated with each voxel with Gaussian regularization to ensure the smoothness of the deformation field. Experimental results from both synthetic and 400 controlled experiments on abdominal CT images and Diffusion Weighted MRI images demonstrate that our method yields a smoother deformation field with superior registration accuracy compared to the demons and diffeomorphic demons algorithms.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Akselrod-Ballin, A., Bock, D., Reid, R., Warfield, S.: Improved registration for large electron microscopy images. In: IEEE Int. Sym. Biomedical Imaging: From Nano to Macro, ISBI 2009, pp. 434–437 (2009)
Arsigny, V., Commowick, O., Ayache, N., Pennec, X.: A fast and log-euclidean polyaffine framework for locally linear registration. Journal of Mathematical Imaging and Vision 33(2), 222–238 (2009)
Arun, K., Huang, T., Blostein, S.: Least-Squares Fitting of Two 3-D Point Sets. IEEE Trans. Patt. Anal. Mach. Intell. 9(5), 698–700 (1987)
Ma, B., Meyer, C.R., Pickles, M.D., Chenevert, T.L., Bland, P.H., Galbán, C.J., Rehemtulla, A., Turnbull, L.W., Ross, B.D.: Voxel-by-Voxel Functional Diffusion Mapping for Early Evaluation of Breast Cancer Treatment. In: Prince, J.L., Pham, D.L., Myers, K.J. (eds.) IPMI 2009. LNCS, vol. 5636, pp. 276–287. Springer, Heidelberg (2009)
Buerger, C., Schaeffter, T., King, A.: Hierarchical adaptive local affine registration for respiratory motion estimation from 3-D MRI. In: IEEE Int. Sym. Biomedical Imaging: From Nano to Macro, ISBI 2010, pp. 1237–1240 (2010)
Cachier, P., Bardinet, E., Dormont, D., Pennec, X., Ayache, N.: Iconic feature based nonrigid registration: the PASHA algorithm. Comp. Vis. Image Und. 89(2–3), 272–298 (2003); nonrigid Image Registration
Cahill, N., Noble, J., Hawkes, D.: A Demons Algorithm for Image Registration with Locally Adaptive Regularization. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part I. LNCS, vol. 5761, pp. 574–581. Springer, Heidelberg (2009)
Commowick, O., Arsigny, V., Isambert, A., Costa, J., Dhermain, F., Bidault, F., Bondiau, P.Y., Ayache, N., Malandain, G.: An efficient locally affine framework for the smooth registration of anatomical structures. Medical Image Analysis 12(4), 427–441 (2008)
Freiman, M., Voss, S., Warfield, S.: Demons registration with local affine adaptive regularization: application to registration of abdominal structures. In: Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011, pp. 1219–1222 (2011)
Koh, D., Thoeny, H. (eds.): Diffusion-Weighted MR imaging: applications in the body. Springer, Heidelberg (2010)
Moffat, B., Chenevert, T., Meyer, C., McKeever, P., Hall, D., Hoff, B., Johnson, T., Rehemtulla, A., Ross, B.: The functional diffusion map: an imaging biomarker for the early prediction of cancer treatment outcome. Neoplasia 8(4), 259–267 (2006)
Risholm, P., Samset, E., Talos, I., Wells, W.: A Non-Rigid Registration Framework that Accommodates Resection and Retraction. In: Prince, J.L., Pham, D.L., Myers, K.J. (eds.) IPMI 2009. LNCS, vol. 5636, pp. 447–458. Springer, Heidelberg (2009)
Rueckert, D., Sonoda, L., Hayes, C., Hill, D., Leach, M., Hawkes, D.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)
Talos, I., Jakab, M., Kikinis, R.: Spl abdominal atlas (2008), http://www.spl.harvard.edu/publications/item/view/1266
Tang, L., Hamarneh, G., Abugharbieh, R.: Reliability-Driven, Spatially-Adaptive Regularization for Deformable Registration. In: Fischer, B., Dawant, B.M., Lorenz, C. (eds.) WBIR 2010. LNCS, vol. 6204, pp. 173–185. Springer, Heidelberg (2010)
Thirion, J.: Image matching as a diffusion process: an analogy with maxwell’s demons. Med. Image Anal. 2(3), 243–260 (1998)
Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Diffeomorphic demons: Efficient non-parametric image registration. NeuroImage 45(1, supplement 1), S61–S72 (2009)
Xiahai, Z., Rhode, K., Razavi, R., Hawkes, D., Ourselin, S.: A Registration-Based Propagation Framework for Automatic Whole Heart Segmentation of Cardiac MRI. IEEE Trans. Med Imaging 29(9), 1612–1625 (2010)
Yeo, B., Sabuncu, M., Desikan, R., Fischl, B., Golland, P.: Effects of registration regularization and atlas sharpness on segmentation accuracy. Med. Image Anal. 12(5), 603–615 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Freiman, M., Voss, S.D., Warfield, S.K. (2012). Abdominal Images Non-rigid Registration Using Local-Affine Diffeomorphic Demons. In: Yoshida, H., Sakas, G., Linguraru, M.G. (eds) Abdominal Imaging. Computational and Clinical Applications. ABD-MICCAI 2011. Lecture Notes in Computer Science, vol 7029. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28557-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-28557-8_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28556-1
Online ISBN: 978-3-642-28557-8
eBook Packages: Computer ScienceComputer Science (R0)