Common Shape Model and Inter-individual Variations of the Heart using Medial Representation

A lot of heart diseases result in or from morphologic variations; analysis of shape variability is therefore important for diagnostic classification and understanding of biological processes. The problem of analyzing shapes of complex objects like the heart is widely discussed in the image processing and analysis community, and different approaches have been published. The goal of the work presented here was to investigate the suitability of a medial based approach to fulfill the task of representing and analyzing individual heart shape and inter-individual variations. In a pilot study we analyzed 16 individual human hearts, their common shape, and their main inter-individual variations for a fixed time phase. Electrocardiogram triggered MRIs of 16 subjects were segmented semi-automatically to derive an object ensemble containing the seven major structures: the left and right ventricle, the left and right atria, the pericardium, the radix of the aorta and the pulmonary trunk for each individual heart. These objects were modeled using a medial based representation providing inter-individual shape correspondence via an object intrinsic coordinate system. Based on this concept of correspondence, a common shape model was generated for both the single object and the object ensemble. The inter-individual variations were analyzed using an extended PCA method showing that almost 80% of variations are covered within the first 5 modes. The results give promise that the method will have great value in quantifying inter-individual shape changes both for healthy and for clinically relevant populations, will allow education in anatomy to communicate variabilities, and furthermore may serve as a potential basis for 3 segmentation, classification, and diagnosis. This potential has to be validated with a statistically relevant population in the future.

[1]  Paul A. Yushkevich,et al.  Deformable M-Reps for 3D Medical Image Segmentation , 2003, International Journal of Computer Vision.

[2]  G. Christensen,et al.  Large Deformation Fluid Diffeomorphisms for Landmark and Image Matching , 1999 .

[3]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Thomas S. Huang,et al.  Modeling, Analysis, and Visualization of Left Ventricle Shape and Motion by Hierarchical Decomposition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Nicholas Ayache,et al.  A scheme for automatically building three-dimensional morphometric anatomical atlases: application to a skull atlas , 1998, Medical Image Anal..

[6]  Milan Sonka,et al.  3-D active appearance models: segmentation of cardiac MR and ultrasound images , 2002, IEEE Transactions on Medical Imaging.

[7]  U. Grenander,et al.  Hippocampal morphometry in schizophrenia by high dimensional brain mapping. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Juha Koikkalainen,et al.  Four-Chamber 3-D Statistical Shape Model from Cardiac Short-Axis and Long-Axis MR Images , 2003, MICCAI.

[9]  Christopher J. Taylor,et al.  Construction of 3D Shape Models of Femoral Articular Cartilage Using Harmonic Maps , 2000, MICCAI.

[10]  Milan Sonka,et al.  Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images , 2001, IEEE Transactions on Medical Imaging.

[11]  Paul A. Yushkevich,et al.  Multiscale deformable model segmentation and statistical shape analysis using medial descriptions , 2002, IEEE Transactions on Medical Imaging.

[12]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Paul A. Yushkevich,et al.  Segmentation, registration, and measurement of shape variation via image object shape , 1999, IEEE Transactions on Medical Imaging.

[14]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[15]  Andrew Thall,et al.  Fast C 2 Interpolating Subdivision Surfaces using Iterative Inversion of Stationary Subdivision Rules , 2003 .

[16]  Paramate Horkaew,et al.  Optimal Deformable Surface Models for 3D Medical Image Analysis , 2003, IPMI.

[17]  P. Thomas Fletcher,et al.  Gaussian Distributions on Lie Groups and Their Application to Statistical Shape Analysis , 2003, IPMI.

[18]  Christopher J. Taylor,et al.  A Method of Automated Landmark Generation for Automated 3D PDM Construction , 1998, BMVC.

[19]  H Bunke,et al.  Left ventricular boundary detection from spatio-temporal volumetric computed tomography images. , 1995, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[20]  P. Thomas Fletcher,et al.  Statistics of shape via principal geodesic analysis on Lie groups , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[21]  Hervé Delingette,et al.  Deformable biomechanical models: Application to 4D cardiac image analysis , 2003, Medical Image Anal..

[22]  Andrew Thall,et al.  A method and software for segmentation of anatomic object ensembles by deformable m-reps. , 2005, Medical physics.

[23]  James N. Damon,et al.  Determining the Geometry of Boundaries of Objects from Medial Data , 2005, International Journal of Computer Vision.

[24]  Douglas W. Jones,et al.  Shape analysis of brain ventricles using SPHARM , 2001, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001).

[25]  Laurent D. Cohen,et al.  Tracking and motion analysis of the left ventricle with deformable superquadrics , 1996, Medical Image Anal..

[26]  Demetri Terzopoulos,et al.  Symmetry-seeking models and 3D object reconstruction , 1988, International Journal of Computer Vision.

[27]  Lawrence H. Staib,et al.  Physical model-based non-rigid registration incorporating statistical shape information , 2000, Medical Image Anal..

[28]  Demetri Terzopoulos,et al.  A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis. , 1995, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[29]  D. Louis Collins,et al.  Model-based segmentation of individual brain structures from MRI data , 1992, Other Conferences.

[30]  Alejandro F. Frangi,et al.  Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling , 2002, IEEE Transactions on Medical Imaging.

[31]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 2004, International Journal of Computer Vision.

[32]  Dimitris N. Metaxas,et al.  Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Milan Sonka,et al.  Automatic segmentation of echocardiographic sequences by active appearance motion models , 2002, IEEE Transactions on Medical Imaging.

[35]  Alejandro F. Frangi,et al.  Three-dimensional modeling for functional analysis of cardiac images, a review , 2001, IEEE Transactions on Medical Imaging.

[36]  Shigeo Abe DrEng Pattern Classification , 2001, Springer London.

[37]  Richard Szeliski,et al.  Matching 3D anatomical surfaces with nonrigid deformations using octree splines , 1993, Optics & Photonics.

[38]  Timothy F. Cootes,et al.  The Use of Active Shape Models for Locating Structures in Medical Images , 1993, IPMI.

[39]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..