Articulated Statistical Shape Models of the Spine

The spine is a complex assembly of rigid vertebrae surrounded by various soft tissues (ligaments, spinal cord, intervertebral discs, etc.). Its motion for a given individual and its shape variations across a population are greatly influenced by this fact. We show in this chapter how statistical shape models can be constructed, used, and analyzed while taking into account the articulated nature of the spine. We begin by defining what articulated models are and how they can be extracted from existing 3D reconstructions or segmented models. As an example, we use data from scoliotic patients that have been reconstructed in 3D using bi-planar radiographs. Articulated models naturally belong to a manifold where conventional statistical tools are not applicable. In this context, a few key concepts allowing the computation of statistical models on Riemannian manifolds are presented. When properly visualized, the resulting statistical models can be quite useful to analyze and compare the shape variations in different groups of patients. Two different approaches to visualization are demonstrated graphically. Finally, another important use of statistical models in medical imaging is to constrain the solution of inverse problems. Articulated models can readily be used in this context, we illustrate this in the context of 3D model reconstruction using partial data. More precisely, we will show the benefits of integrating a simple regularization term based on articulated statistical models to well known algorithms.

[1]  P P Smyth,et al.  Vertebral shape: automatic measurement with active shape models. , 1999, Radiology.

[2]  Markus Fleute.  Shape reconstruction for computer assisted surgery based on non-rigid registration of statistical models with intra-operative point data and X-ray images , 2001 .

[3]  Nicholas Ayache,et al.  Articulated Spine Models for 3-D Reconstruction From Partial Radiographic Data , 2008, IEEE Transactions on Biomedical Engineering.

[4]  David G. Stork,et al.  Pattern Classification , 1973 .

[5]  P. Thomas Fletcher,et al.  Principal geodesic analysis for the study of nonlinear statistics of shape , 2004, IEEE Transactions on Medical Imaging.

[6]  Marleen de Bruijne,et al.  Quantitative vertebral morphometry using neighbor-conditional shape models , 2007, Medical Image Anal..

[7]  Guoyan Zheng,et al.  Automated Vertebra Identification from X-Ray Images , 2010, ICIAR.

[8]  Ya-Xiang Yuan,et al.  Optimization Theory and Methods: Nonlinear Programming , 2010 .

[9]  Gunnar Rätsch,et al.  Kernel PCA and De-Noising in Feature Spaces , 1998, NIPS.

[10]  Max Mignotte,et al.  3D/2D registration and segmentation of scoliotic vertebrae using statistical models. , 2003, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[11]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[12]  Cristian Lorenz,et al.  Spine Segmentation Using Articulated Shape Models , 2008, MICCAI.

[13]  Timothy F. Cootes,et al.  Segmentation of Lumbar Vertebrae Using Part-Based Graphs and Active Appearance Models , 2009, MICCAI.

[14]  Nicholas Ayache,et al.  Geometric Variability of the Scoliotic Spine Using Statistics on Articulated Shape Models , 2008, IEEE Transactions on Medical Imaging.

[15]  Xavier Pennec,et al.  Probabilities and statistics on Riemannian manifolds: Basic tools for geometric measurements , 1999, NSIP.

[16]  S. Delorme,et al.  Long-term three-dimensional changes of the spine after posterior spinal instrumentation and fusion in adolescent idiopathic scoliosis , 1999, European Spine Journal.

[17]  G. Zheng,et al.  Statistical shape modeling of pathological scoliotic vertebrae: A comparative analysis , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[18]  J. Dansereau,et al.  Morphometric evaluations of personalised 3D reconstructions and geometric models of the human spine , 1997, Medical and Biological Engineering and Computing.

[19]  Farida Cheriet,et al.  Personalized X-Ray 3-D Reconstruction of the Scoliotic Spine From Hybrid Statistical and Image-Based Models , 2009, IEEE Transactions on Medical Imaging.

[20]  Purang Abolmaesumi,et al.  Lumbar Spine Segmentation Using a Statistical Multi-Vertebrae Anatomical Shape+Pose Model , 2013, IEEE Transactions on Medical Imaging.

[21]  A Plamondon,et al.  Application of a Stereoradiographic Method for the Study of Intervertebral Motion , 1988, Spine.

[22]  Guy Fabry,et al.  Factors determining the final outcome of treatment of idiopathic scoliosis with the Boston brace: a longitudinal study , 2004, Journal of pediatric orthopedics. Part B.

[23]  Jason J. Corso,et al.  Lumbar Disc Localization and Labeling with a Probabilistic Model on Both Pixel and Object Features , 2008, MICCAI.

[24]  Hans-Peter Meinzer,et al.  Statistical shape models for 3D medical image segmentation: A review , 2009, Medical Image Anal..

[25]  H Labelle,et al.  Pre-, intra-, and postoperative three-dimensional evaluation of adolescent idiopathic scoliosis. , 2000, Journal of spinal disorders.

[26]  Hubert Labelle,et al.  Fast 3D reconstruction of the spine from biplanar radiographs using a deformable articulated model. , 2011, Medical engineering & physics.

[27]  Simon Fuhrmann,et al.  Automatic Construction of Statistical Shape Models for Vertebrae , 2011, MICCAI.

[28]  Sebastian P. M. Dries,et al.  Spine Detection and Labeling Using a Parts-Based Graphical Model , 2007, IPMI.

[29]  Mohammed Benjelloun,et al.  Three-Dimensional Spine Model Reconstruction Using One-Class SVM Regularization , 2013, IEEE Transactions on Biomedical Engineering.

[30]  Xavier Pennec,et al.  A Framework for Uncertainty and Validation of 3-D Registration Methods Based on Points and Frames , 2004, International Journal of Computer Vision.

[31]  W. Skalli,et al.  Coupling 2D/3D registration method and statistical model to perform 3D reconstruction from partial x-rays images data , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  W Skalli,et al.  3D reconstruction of the spine from biplanar X-rays using parametric models based on transversal and longitudinal inferences. , 2009, Medical engineering & physics.

[33]  F. Pernus,et al.  Automated curved planar reformation of 3D spine images , 2005, Physics in medicine and biology.

[34]  W. Boothby.  An introduction to differentiable manifolds and Riemannian geometry , 1975 .

[35]  W. Skalli,et al.  Validation of the non-stereo corresponding points stereoradiographic 3D reconstruction technique , 2001, Medical and Biological Engineering and Computing.

[36]  Tim Cootes,et al.  Semi-automatic determination of detailed vertebral shape from lumbar radiographs using active appearance models , 2011, Osteoporosis International.

[37]  Gabor Fichtinger,et al.  Biomechanically constrained groupwise ultrasound to CT registration of the lumbar spine , 2012, Medical Image Anal..

[38]  David Mitton,et al.  Fast accurate stereoradiographic 3D-reconstruction of the spine using a combined geometric and statistic model. , 2004, Clinical biomechanics.

[39]  M. Fréchet.  Les éléments aléatoires de nature quelconque dans un espace distancié , 1948 .

[40]  H Labelle,et al.  A Three-Dimensional Radiographic Comparison of Cotrel–Dubousset and Colorado Instrumentations for the Correction of Idiopathic Scoliosis , 2000, Spine.

[41]  Jean Dansereau,et al.  Intraoperative Comparison of Two Instrumentation Techniques for the Correction of Adolescent Idiopathic Scoliosis: Rod Rotation and Translation , 1999, Spine.

[42]  Stefan Wesarg,et al.  3D Active Shape Model Segmentation with Nonlinear Shape Priors , 2011, MICCAI.

[43]  Purang Abolmaesumi,et al.  A statistical multi-vertebrae shape+pose model for segmentation of CT images , 2013, Medical Imaging.