Biomedical Image Registration

Accurate affine registrations are crucial for many applications in medical image analysis. Within the Osteoarthritis Initiative (OAI) dataset we have observed a failure rate of approximately 4% for direct affine registrations of knee MRI without manual initialisation. Despite this, the problem of robust affine registration has not received much attention in recent years. With the increase in large medical image datasets, manual intervention is not a suitable solution to achieve successful affine registrations. We introduce a framework to improve the robustness of affine registrations without prior manual initialisations. We use 10,307 MR images from the large dataset available from the OAI to model the low dimensional manifold of the population of unregistered knee MRIs as a sparse k-nearest-neighbour graph. Affine registrations are computed in advance for nearest neighbours only. When a pairwise image registration is required the shortest path across the graph is extracted to find a geodesic path on the empirical manifold. The precomputed affine transformations on this path are composed to find an estimated transformation. Finally a refinement step is used to further improve registration accuracy. Failure rates of geodesic affine registrations reduce to 0.86% with the registration framework proposed.

[1]  Paul Suetens,et al.  Nonrigid Image Registration Using Conditional Mutual Information , 2007, IPMI.

[2]  George D. Stetten,et al.  Carotid Artery and Jugular Vein Tracking and Differentiation Using Spatiotemporal Analysis , 2006, MICCAI.

[3]  Graham M. Treece,et al.  Engineering a freehand 3D ultrasound system , 2003, Pattern Recognit. Lett..

[4]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Colin Studholme,et al.  Deformation-based mapping of volume change from serial brain MRI in the presence of local tissue contrast change , 2006, IEEE Transactions on Medical Imaging.

[6]  Guido Gerig,et al.  Spatiotemporal Atlas Estimation for Developmental Delay Detection in Longitudinal Datasets , 2009, MICCAI.

[7]  Theo van Walsum,et al.  A Semi-automatic Method for Segmentation of the Carotid Bifurcation and Bifurcation Angle Quantification on Black Blood MRA , 2010, MICCAI.

[8]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[9]  Anand Rangarajan,et al.  A new point matching algorithm for non-rigid registration , 2003, Comput. Vis. Image Underst..

[10]  Karl J. Friston,et al.  Spatial registration and normalization of images , 1995 .

[11]  D. Norman,et al.  Normal maturation of the neonatal and infant brain: MR imaging at 1.5 T. , 1988, Radiology.

[12]  H. Kinney,et al.  Myelination in the developing human brain: Biochemical correlates , 1994, Neurochemical Research.

[13]  Michael Unser,et al.  Optimization of mutual information for multiresolution image registration , 2000, IEEE Trans. Image Process..

[14]  François-Xavier Vialard,et al.  Geodesic Regression for Image Time-Series , 2011, MICCAI.

[15]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[16]  Max A. Viergever,et al.  Adaptive Stochastic Gradient Descent Optimisation for Image Registration , 2009, International Journal of Computer Vision.

[17]  Nicholas Ayache,et al.  Multimodal Elastic Matching of Brain Images , 2000, ECCV.

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

[19]  Mark W. Woolrich,et al.  Probabilistic inference of regularisation in non-rigid registration , 2012, NeuroImage.