Particle methods enable fast and simple approximation of Sobolev gradients in image segmentation

Bio-image analysis is challenging due to inhomogeneous intensity distributions and high levels of noise in the images. Bayesian inference provides a principled way for regularizing the problem using prior knowledge. A fundamental choice is how one measures "distances" between shapes in an image. It has been shown that the straightforward geometric L2 distance is degenerate and leads to pathological situations. This is avoided when using Sobolev gradients, rendering the segmentation problem less ill-posed. The high computational cost and implementation overhead of Sobolev gradients, however, have hampered practical applications. We show how particle methods as applied to image segmentation allow for a simple and computationally efficient implementation of Sobolev gradients. We show that the evaluation of Sobolev gradients amounts to particle-particle interactions along the contour in an image. We extend an existing particle-based segmentation algorithm to using Sobolev gradients. Using synthetic and real-world images, we benchmark the results for both 2D and 3D images using piecewise smooth and piecewise constant region models. The present particle approximation of Sobolev gradients is 2.8 to 10 times faster than the previous reference implementation, but retains the known favorable properties of Sobolev gradients. This speedup is achieved by using local particle-particle interactions instead of solving a global Poisson equation at each iteration. The computational time per iteration is higher for Sobolev gradients than for L2 gradients. Since Sobolev gradients precondition the optimization problem, however, a smaller number of overall iterations may be necessary for the algorithm to converge, which can in some cases amortize the higher per-iteration cost.

[1]  P. Koumoutsakos MULTISCALE FLOW SIMULATIONS USING PARTICLES , 2005 .

[2]  Johan Montagnat,et al.  A review of deformable surfaces: topology, geometry and deformation , 2001, Image Vis. Comput..

[3]  Gaudenz Danuser,et al.  Computer Vision in Cell Biology , 2011, Cell.

[4]  Luis Ibáñez,et al.  The ITK Software Guide , 2005 .

[5]  Ivo F. Sbalzarini,et al.  Discretization correction of general integral PSE Operators for particle methods , 2010, J. Comput. Phys..

[6]  Anton Osokin,et al.  Fast Approximate Energy Minimization with Label Costs , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[8]  Gene Myers,et al.  Why bioimage informatics matters , 2012, Nature Methods.

[9]  R. Eils,et al.  Computational imaging in cell biology , 2003, The Journal of cell biology.

[10]  D. Mumford,et al.  Riemannian geometries on the space of plane curves , 2003 .

[11]  Leslie Greengard,et al.  A fast algorithm for particle simulations , 1987 .

[12]  A. Yezzi,et al.  On the relationship between parametric and geometric active contours , 2000, Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154).

[13]  P. Koumoutsakos,et al.  A Lagrangian particle method for reaction–diffusion systems on deforming surfaces , 2010, Journal of mathematical biology.

[14]  A. Roy-Chowdhury,et al.  Automated tracking of stem cell lineages of Arabidopsis shoot apex using local graph matching. , 2010, The Plant journal : for cell and molecular biology.

[15]  Jo A. Helmuth,et al.  Shape reconstruction of subcellular structures from live cell fluorescence microscopy images. , 2009, Journal of structural biology.

[16]  John William Neuberger,et al.  Sobolev gradients and differential equations , 1997 .

[17]  Alan L. Yuille,et al.  Sobolev gradients and joint variational image segmentation, denoising, and deblurring , 2009, Electronic Imaging.

[18]  Olivier D. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[19]  Guillermo Sapiro,et al.  New Possibilities with Sobolev Active Contours , 2007, International Journal of Computer Vision.

[20]  Anthony J. Yezzi,et al.  Global Regularizing Flows With Topology Preservation for Active Contours and Polygons , 2007, IEEE Transactions on Image Processing.

[21]  F. Del Bene,et al.  Optical Sectioning Deep Inside Live Embryos by Selective Plane Illumination Microscopy , 2004, Science.

[22]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[23]  Petros Koumoutsakos,et al.  Simulations of (an)isotropic diffusion on curved biological surfaces. , 2006, Biophysical journal.

[24]  Ivo F Sbalzarini,et al.  Modeling and simulation of biological systems from image data , 2013, BioEssays : news and reviews in molecular, cellular and developmental biology.

[25]  R W Hockney,et al.  Computer Simulation Using Particles , 1966 .

[26]  Nahum Kiryati,et al.  Unlevel-Sets: Geometry and Prior-Based Segmentation , 2004, ECCV.

[27]  W. Clem Karl,et al.  A Real-Time Algorithm for the Approximation of Level-Set-Based Curve Evolution , 2008, IEEE Transactions on Image Processing.

[28]  Robert J. Renka,et al.  Image segmentation with a Sobolev gradient method , 2009 .

[29]  Rachid Deriche,et al.  Universität Des Saarlandes Fachrichtung 6.1 – Mathematik Colour, Texture, and Motion in Level Set Based Segmentation and Tracking Colour, Texture, and Motion in Level Set Based Segmentation and Tracking , 2022 .

[30]  Olivier D. Faugeras,et al.  Designing spatially coherent minimizing flows for variational problems based on active contours , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[31]  Jean-Christophe Olivo-Marin,et al.  3-D Active Meshes: Fast Discrete Deformable Models for Cell Tracking in 3-D Time-Lapse Microscopy , 2011, IEEE Transactions on Image Processing.

[32]  V. Rokhlin,et al.  Rapid Evaluation of Potential Fields in Three Dimensions , 1988 .

[33]  James A. Sethian,et al.  Level Set Methods and Fast Marching Methods , 1999 .

[34]  Guillermo Sapiro,et al.  New Possibilities with Sobolev Active Contours , 2007, SSVM.

[35]  Gábor Székely,et al.  Bayesian image analysis with on-line confidence estimates and its application to microtubule tracking , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[36]  Tim Colonius,et al.  A general deterministic treatment of derivatives in particle methods , 2002 .

[37]  Anthony J. Yezzi,et al.  Sobolev Active Contours , 2005, International Journal of Computer Vision.

[38]  Ivo F. Sbalzarini,et al.  Discrete Region Competition for Unknown Numbers of Connected Regions , 2012, IEEE Transactions on Image Processing.

[39]  A. Yezzi,et al.  Metrics in the space of curves , 2004, math/0412454.

[40]  Ivo F. Sbalzarini,et al.  Deconvolving Active Contours for Fluorescence Microscopy Images , 2009, ISVC.

[41]  Mohamed-Jalal Fadili,et al.  Region-Based Active Contours with Exponential Family Observations , 2009, Journal of Mathematical Imaging and Vision.

[42]  Ivo F. Sbalzarini,et al.  Coupling Image Restoration and Segmentation: A Generalized Linear Model/Bregman Perspective , 2013, International Journal of Computer Vision.