IPMI 2013 - LNCS 7917

Edge- and Detail-Preserving Sparse Image Representations for Deformable Registration of Chest MRI and CT Volumes

Mattias P. Heinrich^{1, 2}, Mark Jenkinson², Bartlomiej W. Papie¹, Fergus V. Glesson³, Sir Michael Brady⁴, and Julia A. Schnabel¹

¹Institute of Biomedical Engineering, University of Oxford, UK
mattias.heinrich@eng.ox.ac.uk
http://users.ox.ac.uk/~shil3388

²Oxford University, Centre for Functional MRI of the Brain, UK

³Department of Radiology, Churchill Hospital, Oxford, UK

⁴Department of Oncology, University of Oxford, UK

Abstract. Deformable medical image registration requires the optimisation of a function with a large number of degrees of freedom. Commonly-used approaches to reduce the computational complexity, such as uniform B-splines and Gaussian image pyramids, introduce translation-invariant homogeneous smoothing, and may lead to less accurate registration in particular for motion fields with discontinuities. This paper introduces the concept of sparse image representation based on supervoxels, which are edge-preserving and therefore enable accurate modelling of sliding organ motions frequently seen in respiratory and cardiac scans. Previous shortcomings of using supervoxels in motion estimation, in particular inconsistent clustering in ambiguous regions, are overcome by employing multiple layers of supervoxels. Furthermore, we propose a new similarity criterion based on a binary shape representation of supervoxels, which improves the accuracy of single-modal registration and enables multi-modal registration. We validate our findings based on the registration of two challenging clinical applications of volumetric deformable registration: motion estimation between inhale and exhale phase of CT scans for radiotherapy planning, and deformable multi-modal registration of diagnostic MRI and CT chest scans. The experiments demonstrate state-of-the-art registration accuracy, and require no additional anatomical knowledge with greatly reduced computational complexity.

Keywords: supervoxels, sliding motion, multi-modal fusion, pulmonary

LNCS 7917, p. 463 ff.

Full article in PDF | BibTeX