Groupwise Registration of Brain Magnetic Resonance Images: A Review

doi:10.1007/s12204-014-1576-5

摘要/Abstract

摘要： A relatively new family of image registration methods, namely groupwise registration, has recently emerged and been widely investigated due to its fundamentally key role in analyzing image populations in terms of atlas-based analysis or clinical diagnostic systems. Compared with pairwise registration, groupwise registration is capable of handling a large-scale population of images simultaneously in an unbiased way. In this paper, a review of the latest research on groupwise registration is presented. First, the schemes of pairwise registration and groupwise registration are compared. Then, a classification of groupwise registration and several exemplar implementations of groupwise registration are illustrated, including their experimental results. Finally, typical applications of groupwise registration, e.g., infant atlas construction, and population-based anatomical variability evaluation, are discussed in this paper.

关键词: pairwise registration, groupwise registration, clinical diagnostic system, infant atlas construction

Abstract: A relatively new family of image registration methods, namely groupwise registration, has recently emerged and been widely investigated due to its fundamentally key role in analyzing image populations in terms of atlas-based analysis or clinical diagnostic systems. Compared with pairwise registration, groupwise registration is capable of handling a large-scale population of images simultaneously in an unbiased way. In this paper, a review of the latest research on groupwise registration is presented. First, the schemes of pairwise registration and groupwise registration are compared. Then, a classification of groupwise registration and several exemplar implementations of groupwise registration are illustrated, including their experimental results. Finally, typical applications of groupwise registration, e.g., infant atlas construction, and population-based anatomical variability evaluation, are discussed in this paper.

Key words: pairwise registration, groupwise registration, clinical diagnostic system, infant atlas construction

中图分类号:

TP 399

LIU Qin (刘钦), WANG Qian*(王乾). Groupwise Registration of Brain Magnetic Resonance Images: A Review[J]. 上海交通大学学报（英文版）, 2014, 19(6): 755-762.

LIU Qin (刘钦), WANG Qian*(王乾). Groupwise Registration of Brain Magnetic Resonance Images: A Review[J]. Journal of shanghai Jiaotong University (Science), 2014, 19(6): 755-762.

参考文献

[1] Oliveira F P, Tavares J M R. Medical image registration:A review [J]. Computer Methods in Biomechanics and Biomedical Engineering, 2014, 17(2): 73-93.
[2] Zitova B, Flusser J. Image registration methods: A survey [J]. Image and Vision Computing, 2003, 21(11):977-1000.
[3] Thevenaz P, Unser M. Optimization of mutual information for multiresolution image registration [J].IEEE Transactions on Image Processing, 2000, 9(12):2083-2099.
[4] Reddy B S, Chatterji B N. An FFT-based technique for translation, rotation, and scale-invariant image registration [J]. IEEE Transactions on Image Processing,1996, 5(8): 1266-1271.
[5] Pluim J P W, Maintz J B A, Viergever M A. Image registration by maximization of combined mutual information and gradient information [C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2000. Berlin, Germany:Springer, 2000: 452-461.
[6] Penney G P, Weese J, Little J A, et al. A comparison of similarity measures for use in 2-D-3-D medical image registration [J]. IEEE Transactions on Medical Imaging, 1998, 17(4): 586-595.
[7] Modersitzer J. Numerical methods for image registration — Numerical mathematics and scientific computation[M]. New York, USA: Oxford University Press, 2004: 148-200.
[8] Maes F, Vandermeulen D, Suetens P. Comparative evaluation of multiresolution optimization strategies for multimodality image registration by maximization of mutual information [J]. Medical Image Analysis,1999, 3(4): 373-386.
[9] Maes F, Collignon A, Vandermeulen D, et al.Multimodality image registration by maximization of mutual information [J]. IEEE Transactions on Medical Imaging, 1997, 16(2): 187-198.
[10] Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision [C]// International Joint Conferences on Artifical Intelligence.Vancouver, Canada: Artificial Intelligence Society of Canada, 1981: 674-679.
[11] Li H, Manjunath B, Mitras S K. A contour-based approach to multisensor image registration [J]. IEEE Transactions on Image Processing, 1995, 4(3): 320-334.
[12] Irani M, Peleg S. Improving resolution by image registration [J]. Graphical Models and Image Processing,1991, 53(3): 231-239.
[13] Hill D L, Batchelor P G, Holden M, et al. Medical image registration [J]. Physics in Medicine and Biology,2001, 46(3): R1-R45.
[14] Kneoaurek K, Ivanoic M, Machac J, et al.Medical image registration [J]. Europhysics News, 2000, 31(4):5-8.
[15] Guizar-Sicairos M, Thurman S T, Fienup J R. Efficient subpixel image registration algorithms [J]. Optics Letters, 2008, 33(2): 156-158.
[16] Gill S, Mousavi P, Fichtinger G, et al. Group-wise registration of ultrasound to CT images of human vertebrae[J]. Proceeding of the SPIE Medical Imaging:Visualization, Image-Guided Procedures, and Modeling,2009, 7261: 72611O-1-72611O-9.
[17] Cox R W, Jesmanovicz A. Real-time 3D image registration for functional MRI [J]. Magnetic Resonance in Medicine, 1999, 42(6): 1014-1018.
[18] Christensen G E, Jhonson H J. Consistent image registration [J]. IEEE Transactions on Medical Imaging,2001, 20(7): 568-582.
[19] Brown L G. A survey of image registration techniques [J]. ACM Computing Surveys, 1992, 24(4): 325-376.
[20] Ashburner J, Neelin P, Collions D, et al. Incorporating prior knowledge into image registration [J].Neuroimage, 1997, 6(4): 344-352.
[21] Ashburner J. A fast diffeomorphic image registration algorithm [J]. Neuroimage, 2007, 38(1): 95-113.
[22] Resnik S M, Goldszal A F, Davatzikos C, et al.One-year age changes in MRI brain volumes in older adults [J]. Cerebral Cortex, 2000, 10(5): 464-472.
[23] Marsland S, Twining C J, Taylor C J. Groupwise non-rigid registration using polyharmonic clampedplate splines [C]//Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany:Springer, 2003: 771-779.
[24] Xue Z, Shen D, Davatzicos C, Determining correspondence in 3-D MR brain images using attribute vectors as morphological signatures of voxels [J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1276-1291.
[25] Rohr K, Stiehl H S, Sprengel R, et al. Landmarkbased elastic registration using approximating thinplate splines [J]. IEEE Transactions on Medical Imaging,2001, 20(6): 526-534.
[26] Joshi S C, Miller M I. Landmark matching via large deformation diffeomorphisms [J]. IEEE Transactions on Image Processing, 2000, 9(8): 1357-1370.
[27] Rohde G K, Aldroubi A, Dawant B M. The adaptive bases algorithm for intensity-based nonrigid image registration [J]. IEEE Transactions on Medical Imaging,2003, 22(11): 1470-1479.
[28] Klein S, Staring M, Murphy K, et al. Elastix: A toolbox for intensity-based medical image registration [J]. IEEE Transactions on Medical Imaging, 2010,29(1): 196-205.
[29] Feldmar J, Malandain G, Declerck J, et al. Extension of the ICP algorithm to non-rigid intensitybased registration of 3D volumes [C]//Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. San Francisco, USA: IEEE, 1996:84-93.
[30] Peli E, Augliere R A, Timerlake G T. Featurebased registration of retinal images [J]. IEEE Transactions on Image Processing, 1987, 6(3): 272-278.
[31] Dare P, Downman I. An improved model for automatic feature-based registration of SAR and SPOT images [J]. Journal of Photogrammetry and Remote Sensing,2001, 56(1): 13-28.
[32] Dai X, Khorram S. A feature-based image registration algorithm using improved chain-code representation combined with invariant moments [J].IEEE Transactions on Geoscience and Remote Sensing,1999, 37(5): 2351-2362.
[33] Shen D, Davatzikos C. HAMMER: Hierarchical attribute matching mechanism for elastic registration [J].IEEE Transactions on Medical Imaging, 2002, 21(11):1421-1439.
[34] Shen D, Davatzikos C. Very high-resolution morphometry using mass-preserving deformations and HAMMER elastic registration [J]. NeuroImage, 2003,18(1): 28-41.
[35] Johnson H J, Christensan G E, Consistent landmark and intensity-based image registration [J]. IEEE Transactions on Medical Imaging, 2002, 21(5): 450-461.
[36] Wu G, Wang Q, Jia H, et al. Groupwise registration by hierarchical anatomical correspondence detection [C]// Medical Image Computing and Computer Assisted Intervention. Beijing, China: Springer, 2010:684-691.
[37] Wu G, Jia H, Wang Q, et al. Sharpmean: Groupwise registration guided by sharp mean image and treebased registration [J]. NeuroImage, 2011, 56(4): 1968-1981.
[38] Wang Q, Wu G, Yap P T, et al. Attribute vector guided groupwise registration [J]. NeuroImage, 2010, 50(4): 1485-1496.
[39] Wang Q, Chen L, Yap P T, et al. Groupwise registration based on hierarchical image clustering and atlas synthesis [J]. Human Brain Mapping, 2010, 31(8):1128-1140.
[40] Cootes T F, Marsland S, Twining C J, et al. Groupwise diffeomorphic non-rigid registration for automatic model building [C]//European Conference on Computer Vision. Berlin, Germany: Springer, 2004:316-327.
[41] Sidorov K A, Richmond S, Marshall D. Efficient groupwise non-rigid registration of textured surfaces [C]// IEEE Conference on Computer Vision and Pattern Recognition. Colorado, USA: IEEE, 2011: 2401-2408.
[42] Kim M, Wu G, Shen D. Groupwise registration of breast DCE-MR images for accurate tumor measurement [C]//IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Chicago, USA:IEEE, 2011: 598-601.
[43] Jiang D, Jiang T, Fan Y. Groupwise fMRI registration using multi-range functional connectivity patterns [C]// IEEE International Symposium on Biomedical Imaging. Barcelona, Spain: IEEE, 2012: 1763-1766.
[44] Jia H, Yap P T, Wu G, et al. Intermediate templates guided groupwise registration of diffusion tensor images [J]. NeuroImage, 2011, 54(2): 928-939.
[45] Jia H,Wu G,Wang Q, et al. ABSORB: Atlas building by self-organized registration and bundling [J].NeuroImage, 2010, 51(3): 1057-1070.
[46] Hamm J, Ye D H, Verma R, et al. GRAM: A framework for geodesic registration on anatomical manifolds[J]. Medical Image Analysis, 2010, 14(5): 633-642.
[47] Geng X, Christensen G E, Gu H, et al. Implicit reference-based group-wise image registration and its application to structural and functional MRI [J]. NeuroImage,2009, 47(4): 1341-1351.
[48] Cootes T F, Twining C J, Petrovic V S, et al. Groupwise construction of appearance models using piece-wise affine deformations [C]// British Machine Vision Conference. Oxford, UK: British Machine Vision Association, 2005: 879-888.
[49] Chappelow J, Bloch B. N, Rofsky N, et al. Elastic registration of multimodal prostate MRI and histology via multiattribute combined mutual information [J].Medical Physics, 2011, 38(4): 2005-2018.
[50] Bhatia K K, Hajnal J, Hammers A, et al. Similarity metrics for groupwise non-rigid registration [C]//Medical Image Computing and Computer-Assisted Intervention.Brisbane, Australia: Springer, 2007: 544-552.
[51] Bhatia K, Hajnal J, Edwards A, et al. Groupwise atlas construction for the identification of neuroanatomical changes associated with preterm birth [C]//Proceedings International Society for Magnetic Resonance in Medicine. Miami, USA: Springer. 2005:643.
[52] Barmpoutis A, Vemuri B C. Groupwise registration and atlas construction of 4th-order tensor fields using the R+ Riemannian metric [C]//Medical Image Computing and Computer-Assisted Intervention. London,UK: Springer, 2009: 640-647.
[53] Baloch S, Davatzikos C. Morphological appearance manifolds in computational anatomy: Groupwise registration and morphological analysis [J]. NeuroImage, 2009, 45(1): S73-S85.
[54] Balci S K, Golland P, Shenton M, et al. Freeform B-spline deformation model for groupwise registration[C]//Medical Image Computing and Computer-Assisted Intervention. Brisbane, Australia: Springer,2007: 23-30.
[55] Argenda C I, Sorzano C O, Marabini R, et al.Consistent and elastic registration of histological sections using vector-spline regularization [C]// Computer Vision Approaches to Medical Image Analysis.Graz, Austria: Springer, 2006: 85-95.
[56] Adeshina S A, Cootes T F. Constructing part-based models for groupwise registration [C]// IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Rotterdam, Netherlands: IEEE, 2010: 1073-1076.
[57] Wolz R, Aljabar P, Hajnal J V, et al. LEAP:Learning embeddings for atlas propagation [J]. NeuroImage,2010, 49(2): 1316-1325.
[58] Bhatia K K, Hajnal J V, Puri B K, et al. Consistent groupwise non-rigid registration for atlas construction [C]// IEEE International Symposium on Biomedical Imaging: Nano to Macro. Arlington, USA:IEEE, 2004: 908-911.
[59] Seghers D, Dagostino E, Maes F, et al. Construction of a brain template from MR images using state-of-the-art registration and segmentation techniques[C]//Medical Image Computing and Computer-Assisted Intervention. Saint-Malo, France: Springer,2004: 696-703.
[60] Wu G, Jia H, Wang Q, et al. Groupwise registration with sharp mean [C]// Medical Image Computing and Computer-Assisted Intervention. Beijing, China:Springer, 2010: 570-577.
[61] Scheet P, Stephens M. A fast and flexible statistical model for large-scale population genotype data: Applications to inferring missing genotypes and haplotypic phase [J]. The American Journal of Human Genetics,2006, 78(4): 629-644.
[62] Liang H, Bronzino J, Peterzon D. Biosignal processing:Principles and practices [M]. Boca Raton,USA: Taylor & Francis, 2012: 5-6.
[63] Wu G, Yap P T, Wang Q, et al. Groupwise registration from exemplar to group mean: Extending HAMMER to groupwise registration [C]//IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Rotterdam, Netherlands: IEEE, 2010:396-399.
[64] Tenenbaum S A, Carson C C, Lager P J, et al.Identifying mRNA subsets in messenger ribonucleoprotein complexes by using cDNA arrays [J]. Proceedings of the National Academy of Sciences, 2000, 97(26):14085-14090.
[65] Vercauteren T, Pennec X, Perchant A, et al.Diffeomorphic demons: Efficient non-parametric image registration [J]. NeuroImage, 2009, 45(1): S61-S72.
[66] Dueck D, Frey B J. Non-metric affinity propagation for unsupervised image categorization [C]//International Conference on Computer Vision.Rio de Janeiro, Brazil: IEEE, 2007: 1-8.
[67] Ying S, Wu G, Wang Q, et al. Hierarchical unbiased graph shrinkage (hugs): A novel groupwise registration for large data set [J]. NeuroImage, 2014, 84(1): 626-638.
[68] Wu G, Wang Q, Jia H, et al. Feature-based groupwise registration by hierarchical anatomical correspondence detection [J]. Human Brain Mapping, 2012,33(2): 253-271.
[69] Starring M, Heide U A, Klein S, et al. Registration of cervical MRI using multifeature mutual information [J]. IEEE Transactions on Medical Imaging,2009, 28(9): 1412-1421.
[70] Toga A W, Thompson P M. The role of image registration in brain mapping [J]. Image and Vision Computing,2001, 19(1-2): 3-24.
[71] Knickmeyer R C, Gouttard S, Kang C, et al.A structural MRI study of human brain development from birth to 2 years [J]. The Journal of Neuroscience,2008, 28(47): 12176-12182.
[72] Geng X, Christensen G E, Gu H, et al. Implicit reference-based group-wise image registration and its application to structural and functional MRI [J]. Neuroimage,2009, 47(4): 1341-1351.
[73] Zhang H, Avants B B, Yushkevch P A, et al. Highdimensional spatial normalization of diffusion tensor images improves the detection of white matter differences:An example study using amyotrophic lateral sclerosis [J]. IEEE Transactions on Medical Imaging,2007, 26(11): 1585-1597.
[74] Cootes T F, Marsland S, Twining C J, et al. Groupwise diffeomorphic non-rigid registration for automatic model building [C]//European Conference on Computer Vision. Berlin, Germany: Springer, 2004:316-327.
[75] Cootes T F, Twining C J, Petrovic V S, et al.Groupwise construction of appearance models using piece-wise affine deformations [C]//British Machine Vision Conference. Oxford, UK: British Machine Vision Association, 2005: 879-888.
[76] Yigitsoy M, Wachinger C, Navab N. Temporal groupwise registration for motionmodeling [C]//Information Processing in Medical Imaging.Berlin, Germany: Springer, 2011: 648-659.
[77] Pieperhoff P, Homke L, Schneider F, et al. Deformation field morphometry revealsage-related structural differences between the brains of adults up to 51 years [J]. The Journal of Neuroscience, 2008, 28(4):828-842.