Incorporating shape variability in implicit template deformation

In this chapter, we propose a method to learn and use prior knowledge on shape variability in the implicit template deformation framework. This shape prior is learnt via an original and dedicated process in which both an optimal template and principal modes of variations are estimated from a collection of shapes. This learning strategy does not require one-to-one correspondences between shape sample points and is not biased by a pre-alignment of the training shapes. We then generalize the implicit template deformation formulation to automatically select the most plausible deformation as a shape prior. This novel framework maintains the two main properties of implicit template deformation: topology preservation and computational efficiency. Our approach can be applied to any organ with a possibly complex shape but fixed topology. We validate our method on myocardium segmentation from cardiac magnetic resonance short-axis images and demonstrate segmentation improvement over standard template deformation. Raphael Prevost, Remi Cuingnet, Benoit Mory, Roberto Ardon Philips Research Medisys, Suresnes, France. e-mail: {raphael.prevost,benoit.mory,remi.cuingnet,roberto.ardon}@philips.com Laurent D. Cohen CEREMADE UMR CNRS 7534, Paris Dauphine University, PSL, Paris, France. e-mail: cohen@ceremade.dauphine.fr

[1]  Stefano Soatto,et al.  A Pseudo-distance for Shape Priors in Level Set Segmentation , 2003 .

[2]  Laurent D. Cohen,et al.  Tagged Template Deformation , 2014, MICCAI.

[3]  Laurent D. Cohen,et al.  A Parametric Deformable Model to Fit Unstructured 3D Data , 1998, Comput. Vis. Image Underst..

[4]  H. Karcher.  Riemannian center of mass and mollifier smoothing , 1977 .

[5]  Oudom Somphone,et al.  Real-Time 3D Image Segmentation by User-Constrained Template Deformation , 2012, MICCAI.

[6]  Stanley Durrleman,et al.  Statistical models of currents for measuring the variability of anatomical curves, surfaces and their evolution. (Modèles statistiques de courants pour mesurer la variabilité anatomique de courbes, de surfaces et de leur évolution) , 2010 .

[7]  Nikos Paragios,et al.  Shape Priors for Level Set Representations , 2002, ECCV.

[8]  Stefano Soatto,et al.  Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images , 2003, International Journal of Computer Vision.

[9]  Ali R. Khan,et al.  FreeSurfer-initiated fully-automated subcortical brain segmentation in MRI using Large Deformation Diffeomorphic Metric Mapping , 2008, NeuroImage.

[10]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[11]  L. Younes,et al.  Statistics on diffeomorphisms via tangent space representations , 2004, NeuroImage.

[12]  Dimitris N. Metaxas,et al.  Learning Coupled Prior Shape and Appearance Models for Segmentation , 2004, MICCAI.

[13]  Oudom Somphone,et al.  Template Deformation with User Constraints for Live 3D Interactive Surface Extraction , 2011 .

[14]  Farida Cheriet,et al.  Region-Based Segmentation via Non-Rigid Template Matching , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Dimitris N. Metaxas,et al.  Metamorphs: Deformable Shape and Appearance Models , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Laurent D. Cohen,et al.  Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity , 2008, ECCV.

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

[18]  O. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2002, 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002..

[19]  Laurent D. Cohen,et al.  Registration of Free-Breathing 3D+t Abdominal Perfusion CT Images via Co-segmentation , 2013, MICCAI.

[20]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[21]  Laurent D. Cohen,et al.  Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests , 2012, MICCAI.

[22]  Laurent D. Cohen,et al.  Incorporating Shape Variability in Image Segmentation via Implicit Template Deformation , 2013, MICCAI.

[23]  Guido Gerig,et al.  Unbiased diffeomorphic atlas construction for computational anatomy , 2004, NeuroImage.

[24]  Rachid Deriche,et al.  Implicit Active Shape Models for 3D Segmentation in MR Imaging , 2004, MICCAI.

[25]  Laurent D. Cohen,et al.  Kidney detection and real-time segmentation in 3D contrast-enhanced ultrasound images , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[26]  Laurent D. Cohen,et al.  A Hybrid Hyperquadric Model for 2-D and 3-D Data Fitting , 1996, Comput. Vis. Image Underst..

[27]  Nicholas Ayache,et al.  A Log-Euclidean Framework for Statistics on Diffeomorphisms , 2006, MICCAI.

[28]  Daniel Cremers,et al.  Shape statistics in kernel space for variational image segmentation , 2003, Pattern Recognit..

[29]  Rachid Deriche,et al.  A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape , 2007, International Journal of Computer Vision.

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

[31]  Alejandro F. Frangi,et al.  Automatic Construction of 3D Statistical Deformation Models Using Non-rigid Registration , 2001, MICCAI.

[32]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .