Learning the Dynamics and Time-Recursive Boundary Detection of Deformable Objects

We propose a principled framework for recursively segmenting deformable objects across a sequence of frames. We demonstrate the usefulness of this method on left ventricular segmentation across a cardiac cycle. The approach involves a technique for learning the system dynamics together with methods of particle-based smoothing as well as nonparametric belief propagation on a loopy graphical model capturing the temporal periodicity of the heart. The dynamic system state is a low-dimensional representation of the boundary, and the boundary estimation involves incorporating curve evolution into recursive state estimation. By formulating the problem as one of state estimation, the segmentation at each particular time is based not only on the data observed at that instant, but also on predictions based on past and future boundary estimates. Although this paper focuses on left ventricle segmentation, the method generalizes to temporally segmenting any deformable object.

[1]  Ram Nevatia,et al.  Automatic Tracking and Labeling of Human Activities in a Video Sequence , 2004 .

[2]  Dorin Comaniciu,et al.  An information fusion framework for robust shape tracking , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Alan S. Willsky,et al.  Segmenting and Tracking the Left Ventricle by Learning the Dynamics in Cardiac Images , 2005, IPMI.

[4]  John S. Duncan,et al.  Measurement of end diastolic shape deformity using bending energy , 1988, Proceedings. Computers in Cardiology 1988.

[5]  Alexander T. Ihler,et al.  Maximally informative subspaces : nonparametric estimation for dynamical systems , 2000 .

[6]  Allan R. Robinson,et al.  Feature-oriented regional modeling of oceanic fronts , 2002 .

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

[8]  J.L. Bamber,et al.  Detection and tracking of oceanic thermal boundaries using passive microwave data , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[9]  Michael E. Leventon,et al.  Statistical models in medical image analysis , 2000 .

[10]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[11]  Anthony J. Yezzi,et al.  A Fully Global Approach to Image Segmentation via Coupled Curve Evolution Equations , 2002, J. Vis. Commun. Image Represent..

[12]  Yongmin Kim,et al.  A multiple active contour model for cardiac boundary detection on echocardiographic sequences , 1996, IEEE Trans. Medical Imaging.

[13]  J. Sethian.  Level set methods : evolving interfaces in geometry, fluid mechanics, computer vision, and materials science , 1996 .

[14]  Michael I. Jordan.  Graphical Models , 2003 .

[15]  A. Ardeshir Goshtasby,et al.  Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers , 1995, IEEE Trans. Medical Imaging.

[16]  Thomas Kailath,et al.  A further note on backwards Markovian models (Corresp.) , 1979, IEEE Trans. Inf. Theory.

[17]  Nicolae Duta,et al.  Segmentation of the Left Ventricle in Cardiac MR Images , 2001, ICCV.

[18]  Ming-Chieh Lee,et al.  Semiautomatic segmentation and tracking of semantic video objects , 1998, IEEE Trans. Circuits Syst. Video Technol..

[19]  Anthony J. Yezzi,et al.  Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification , 2001, IEEE Trans. Image Process..

[20]  T. M. Chin,et al.  Variational approaches on discontinuity localization and field estimation in sea surface temperature and soil moisture , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[21]  William T. Freeman,et al.  Nonparametric belief propagation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[22]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[23]  M. C. Jones,et al.  On optimal data-based bandwidth selection in kernel density estimation , 1991 .

[24]  A McCulloch,et al.  Computational biology of the heart: from structure to function. , 1998, Progress in biophysics and molecular biology.

[25]  Yunmei Chen,et al.  Using Prior Shapes in Geometric Active Contours in a Variational Framework , 2002, International Journal of Computer Vision.

[26]  James S. Duncan,et al.  Estimation of 3D left ventricular deformation from echocardiography , 2001, Medical Image Anal..

[27]  Gregory D. Hager,et al.  What Tasks can be Performed with an Uncalibrated Stereo Vision System? , 1999, International Journal of Computer Vision.

[28]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[29]  Brian D. O. Anderson,et al.  Smoothing algorithms for nonlinear finite-dimensional systems , 1983 .

[30]  Namrata Vaswani,et al.  Tracking Deforming Objects Using Particle Filtering for Geometric Active Contours , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Gustav Konrad von Schulthess.  The Effects of Motion and Flow on Magnetic Resonance Imaging , 1989 .

[32]  W. Eric L. Grimson,et al.  A shape-based approach to the segmentation of medical imagery using level sets , 2003, IEEE Transactions on Medical Imaging.

[33]  Namrata Vaswani,et al.  Time-varying Finite Dimensional Basis for Tracking Contour Deformations , 2006, Proceedings of the 45th IEEE Conference on Decision and Control.

[34]  H. Buxton,et al.  Advanced visual surveillance using Bayesian networks , 1997 .

[35]  James S. Duncan,et al.  Volumetric Deformation Analysis Using Mechanics-Based Data Fusion: Applications in Cardiac Motion Recovery , 1999, International Journal of Computer Vision.

[36]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[37]  Daniel Cremers,et al.  Dynamical statistical shape priors for level set-based tracking , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[39]  Alan S. Willsky,et al.  Nonparametric shape priors for active contour-based image segmentation , 2005, 2005 13th European Signal Processing Conference.

[40]  James A. Sethian,et al.  Level Set Methods and Fast Marching Methods: Evolving Interfaces in Computational Geometry, Fluid , 2012 .

[41]  Pengcheng Shi,et al.  BIOMECHANICALLY CONSTRAINED MULTIFRAME ESTIMATION OF NONRIGID CARDIAC KINEMATICS FROM MEDICAL IMAGE SEQUENCE , 2003 .

[42]  T. Kailath,et al.  Forwards and backwards models for finite-state Markov processes , 1979, Advances in Applied Probability.

[43]  G. Hamarneh,et al.  Combining snakes and active shape models for segmenting the human left ventricle in echocardiographic images , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[44]  A. Willsky,et al.  On the fixed-interval smoothing problem † , 1981 .

[45]  Michael Isard,et al.  Tracking loose-limbed people , 2004, CVPR 2004.

[46]  James S. Duncan,et al.  Shape-based tracking of left ventricular wall motion , 1997, IEEE Transactions on Medical Imaging.

[47]  Thomas Netsch,et al.  Segmentation of Medical Images with a Shape and Motion Model: A Bayesian Perspective , 2004, ECCV Workshops CVAMIA and MMBIA.

[48]  Yair Weiss,et al.  Correctness of Local Probability Propagation in Graphical Models with Loops , 2000, Neural Computation.

[49]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[50]  A. Murat Tekalp,et al.  Temporal video segmentation using unsupervised clustering and semantic object tracking , 1998, J. Electronic Imaging.

[51]  Walter Sun,et al.  Learning the dynamics of deformable objects and recursive boundary estimation using curve evolution techniques , 2005 .