A GPU framework for parallel segmentation of volumetric images using discrete deformable models

Despite the ability of current GPU processors to treat heavy parallel computation tasks, its use for solving medical image segmentation problems is still not fully exploited and remains challenging. A lot of difficulties may arise related to, for example, the different image modalities, noise and artifacts of source images, or the shape and appearance variability of the structures to segment. Motivated by practical problems of image segmentation in the medical field, we present in this paper a GPU framework based on explicit discrete deformable models, implemented over the NVidia CUDA architecture, aimed for the segmentation of volumetric images. The framework supports the segmentation in parallel of different volumetric structures as well as interaction during the segmentation process and real-time visualization of the intermediate results. Promising results in terms of accuracy and speed on a real segmentation experiment have demonstrated the usability of the system.

[1]  Wei Pan.  Improving Interactive Image Segmentation via Appearance Propagation , 2009, Eurographics.

[2]  Martin Rumpf,et al.  Image Registration by a Regularized Gradient Flow. A Streaming Implementation in DX9 Graphics Hardware , 2004, Computing.

[3]  Guido Brunnett,et al.  Tile-based Image Forces for Active Contours on GPU , 2009, Eurographics.

[4]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[5]  Nadia Magnenat-Thalmann,et al.  Extreme leg motion analysis of professional ballet dancers via MRI segmentation of multiple leg postures , 2010, International Journal of Computer Assisted Radiology and Surgery.

[6]  Benjamin B. Kimia,et al.  Segmentation of carpal bones from CT images using skeletally coupled deformable models , 2003, Medical Image Anal..

[7]  Jayaram K. Udupa,et al.  Interactive segmentation and boundary surface formation for 3-D digital images , 1982, Comput. Graph. Image Process..

[8]  Enrico Gobbetti,et al.  A single-pass GPU ray casting framework for interactive out-of-core rendering of massive volumetric datasets , 2008, The Visual Computer.

[9]  G C Sharp,et al.  GPU-based streaming architectures for fast cone-beam CT image reconstruction and demons deformable registration , 2007, Physics in medicine and biology.

[10]  Kari Tanderup,et al.  Acceleration and validation of optical flow based deformable registration for image-guided radiotherapy , 2008, Acta oncologica.

[11]  Horst Bischof,et al.  Interactive Texture Segmentation using Random Forests and Total Variation , 2009, BMVC.

[12]  John Paul Walters,et al.  Evaluating the use of GPUs in liver image segmentation and HMMER database searches , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[13]  Daniel Cremers,et al.  TVSeg - Interactive Total Variation Based Image Segmentation , 2008, BMVC.

[14]  Thomas Sangild Sørensen,et al.  A GPU accelerated spring mass system for surgical simulation. , 2005, Studies in health technology and informatics.

[15]  Ross T. Whitaker,et al.  GIST: an interactive, GPU-based level set segmentation tool for 3D medical images , 2004, Medical Image Anal..

[16]  Wolfgang Straßer,et al.  Extracting regions of interest applying a local watershed transformation , 2000, Proceedings Visualization 2000. VIS 2000 (Cat. No.00CH37145).

[17]  Ross T. Whitaker,et al.  Interactive, GPU-Based Level Sets for 3D Segmentation , 2003, MICCAI.

[18]  Nadia Magnenat-Thalmann,et al.  Interactive Segmentation of Volumetric Medical Images for Collaborative Telemedicine , 2009, 3DPH.

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

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

[21]  Heinz-Otto Peitgen,et al.  GPU Accelerated Image Registration in Two and Three Dimensions , 2006, Bildverarbeitung für die Medizin.

[22]  John D. Owens,et al.  Fast Deformable Registration on the GPU: A CUDA Implementation of Demons , 2008, 2008 International Conference on Computational Sciences and Its Applications.

[23]  Falko Kuester,et al.  GPU-Based Active Contour Segmentation Using Gradient Vector Flow , 2006, ISVC.

[24]  Harry Shum,et al.  Paint selection , 2009, ACM Trans. Graph..

[25]  Sylvain Lefebvre,et al.  GigaVoxels: ray-guided streaming for efficient and detailed voxel rendering , 2009, I3D '09.

[26]  Nadia Magnenat-Thalmann,et al.  MRI Bone Segmentation Using Deformable Models and Shape Priors , 2008, MICCAI.

[27]  Jeroen G. Snel,et al.  Deformable triangular surfaces using fast 1-D radial Lagrangian dynamics-segmentation of 3-D MR and CT images of the wrist , 2002, IEEE Transactions on Medical Imaging.

[28]  Nadia Magnenat-Thalmann,et al.  Medical image analysis , 1999, Medical Image Anal..

[29]  Antonio Susín,et al.  Non structured meshes for Cloth GPU simulation using FEM , 2006, VRIPHYS.

[30]  Olivier D. Faugeras,et al.  Segmentation of Bone in Clinical Knee MRI Using Texture-Based Geodesic Active Contours , 1998, MICCAI.

[31]  Peter Hastreiter,et al.  GPU Accelerated Normalized Mutual Information and B-Spline Transformation , 2008, VCBM.

[32]  Robert Strzodka,et al.  Exploring weak scalability for FEM calculations on a GPU-enhanced cluster , 2007, Parallel Comput..

[33]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Thomas Ertl,et al.  Large steps in GPU-based deformable bodies simulation , 2005, Simul. Model. Pract. Theory.

[35]  Arnold W. M. Smeulders,et al.  Interaction in the segmentation of medical images: A survey , 2001, Medical Image Anal..

[36]  Hervé Delingette,et al.  General Object Reconstruction Based on Simplex Meshes , 1999, International Journal of Computer Vision.

[37]  Rüdiger Westermann,et al.  Mass-spring systems on the GPU , 2005, Simul. Model. Pract. Theory.

[38]  P. J. Narayanan,et al.  Singular value decomposition on GPU using CUDA , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[39]  B. Ginneken,et al.  3D Segmentation in the Clinic: A Grand Challenge , 2007 .

[40]  Anthony J. Sherbondy,et al.  Fast volume segmentation with simultaneous visualization using programmable graphics hardware , 2003, IEEE Visualization, 2003. VIS 2003..

[41]  David J. Hawkes,et al.  Voxel Similarity Measures for 3D Serial MR Brain Image Registration , 2000, IEEE Trans. Medical Imaging.

[42]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[43]  L. Verlet.  Computer "Experiments" on Classical Fluids. I. Thermodynamical Properties of Lennard-Jones Molecules , 1967 .