Multi-modality liver image registration based on multilevel B-splines free-form deformation and L-BFGS optimal algorithm

Abstract

A new coarse-to-fine strategy was proposed for nonrigid registration of computed tomography (CT) and magnetic resonance (MR) images of a liver. This hierarchical framework consisted of an affine transformation and a B-splines free-form deformation (FFD). The affine transformation performed a rough registration targeting the mismatch between the CT and MR images. The B-splines FFD transformation performed a finer registration by correcting local motion deformation. In the registration algorithm, the normalized mutual information (NMI) was used as similarity measure, and the limited memory Broyden-Fletcher-Goldfarb-Shannon (L-BFGS) optimization method was applied for optimization process. The algorithm was applied to the fully automated registration of liver CT and MR images in three subjects. The results demonstrate that the proposed method not only significantly improves the registration accuracy but also reduces the running time, which is effective and efficient for nonrigid registration.

Keywords

multi-modal image registration / affine transformation / B-splines free-form deformation (FFD) / L-BFGS

References

[1] KaplanL M, NasrabadiN M. Block Wiener-based image registration for moving target indication [J]. Image and Vision Computing, 2009, 27(6): 694-703

[2] MarkeljP, TomaževičD, LikarB, PernušF. A review of 3D/2D registration methods for image-guided interventions [J]. Medical Image Analysis, 2012, 16(3): 642-661

[3] FayadH J, LamareF, le RestC C, BettinardiV, VisvikisD. Generation of 4-dimensional CT images based on 4-dimensional PET-derived motion fields [J]. Nuclear Medicine and Molecular Imaging, 2013, 54(4): 631-638

[4] VenotA, GolmardJ L, LebruchecJ F. Digital methods for change detection in medical images [C]. Information Processing in Medical Imaging, 1984, Netherlands, Springer: 1-16

[5] LeeS, WolbergG, ShinS Y. Scattered data interpolation with multilevel B-splines [J]. Visualization and Computer Graphics, IEEE Transactions on, 1997, 3(3): 228-244

[6] CarrilloA, DuerkJ L, LewinJ S, WilsonD L. Semiautomatic 3-D image registration as applied to interventional MRI liver cancer treatment [J]. Medical Imaging, IEEE Transactions on, 2000, 19(3): 175-185

[7] ArchipN, TatliS, MorrisonP, JoleszF, WarfieldS K, SilvermanS. Non-rigid registration of pre-procedural MR images with intra-procedural unenhanced CT images for improved targeting of tumors during liver radiofrequency ablations [M]. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2007, 2007969-977

[8] KwonD, YunI D, LeeK H, LeeS U. Efficient feature-based nonrigid registration of multiphase liver CT volumes [C]. British Machine Vision Conference, 2008, UK, Leads: 1-10

[9] LeeH, LeeJ, KimN, KimS J, ShinY G. Robust feature-based registration using a Gaussian-weighted distance map and brain feature points for brain PET/CT images [J]. Computers in Biology and Medicine, 2008, 38(9): 945-961

[10] NamW H, LeeD, JeongK Y, KimJ H, RaJ B. Non-rigid registration between 3D MR and CT images of the liver based on intensity and edge orientation information [C]. Nuclear Science Symposium Conference Record (NSS/MIC), 2010 IEEE, 2010, USA, Knoxville: 2998-3000

[11] HuangX, WangB, LiuR, WangX, WuZ. CT-MR image registration in liver treatment by maximization of mutual information [C]. IT in Medicine and Education, 2008. ITME 2008. Xiamen, China, 2008715-718

[12] TangS, WangY. Application of nonrigid registration in liver cancer treatment [J]. Optical Technique, 2006, 32(z1): 369-373

[13] StudholmeC, HillD L G, HawkesD J. An overlap invariant entropy measure of 3D medical image alignment [J]. Pattern Recognition, 1999, 32(1): 71-86

[14] LiB, OuS-x, TianL-fang. Thorax multimodal medical image registration based on adaptive free-form deformation and gradient descent [J]. Application Research of Computers, 2009, 26(10): 3978-3982

[15] De GrootM, VernooijM W, KleinS, IkramM A, VosF M, SmithS M, AnderssonJ L. Improving alignment in Tract-based spatial statistics: Evaluation and optimization of image registration [J]. NeuroImage, 2013, 76: 400-411