Image segmentation using CUDA implementations of the Runge-Kutta-Merson and GMRES methods

Modern GPUs are well suited for performing image processing tasks. We utilize their high computational performance and memory bandwidth for image segmentation purposes. We segment cardiac MRI data by means of numerical solution of an anisotropic partial differential equation of the Allen-Cahn type. We implement two different algorithms for solving the equation on the CUDA architecture. One of them is based on the Runge-Kutta-Merson method for the approximation of solutions of ordinary differential equations, the other uses the GMRES method for the numerical solution of systems of linear equations. In our experiments, the CUDA imple- mentations of both algorithms are about 3-9 times faster than corresponding 12-threaded OpenMP implementations.

[1]  Arutyun Avetisyan,et al.  Automatically Tuning Sparse Matrix-Vector Multiplication for GPU Architectures , 2010, HiPEAC.

[2]  Michael Garland,et al.  Efficient Sparse Matrix-Vector Multiplication on CUDA , 2008 .

[3]  Weiguo Liu,et al.  Accelerating molecular dynamics simulations using Graphics Processing Units with CUDA , 2008, Comput. Phys. Commun..

[4]  K. Mikula.  5 PARALLEL CO-VOLUME SUBJECTIVE SURFACE METHOD FOR 3 D MEDICAL IMAGE SEGMENTATION , 2006 .

[5]  S. Dymarkowski,et al.  Clinical cardiac MRI , 2005 .

[6]  M. Beneš,et al.  Mathematical and computational aspects of solidification of pure substances. , 2001 .

[7]  Majid Sarrafzadeh,et al.  Fast GPU-based space-time correlation for activity recognition in video sequences , 2008, 2008 IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia.

[8]  Giorgio Valle,et al.  CUDA compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment , 2008, BMC Bioinformatics.

[9]  Rajesh Bordawekar,et al.  Optimizing Sparse Matrix-Vector Multiplication on GPUs , 2009 .

[10]  Cheol Hong Kim,et al.  Power analysis for decoding of the digital audio encoding format MP3: Decoding the central processing unit and the graphics processing unit. , 2010 .

[11]  Manuel Menezes de Oliveira Neto,et al.  Realistic real-time sound re-synthesis and processing for interactive virtual worlds , 2009, The Visual Computer.

[12]  Yousef Saad,et al.  Iterative methods for sparse linear systems , 2003 .

[13]  Gjlles Aubert,et al.  Mathematical problems in image processing , 2001 .

[14]  Arutyun Avetisyan,et al.  Implementing Blocked Sparse Matrix-Vector Multiplication on NVIDIA GPUs , 2009, SAMOS.

[15]  Xiaohui Ji,et al.  A simulation of large-scale groundwater flow on CUDA-enabled GPUs , 2010, SAC '10.

[16]  Dušan Maga,et al.  Numerické metódy – I , 2004 .

[17]  K. Mikula,et al.  Geometrical image segmentation by the Allen-Cahn equation , 2004 .

[18]  Ester M. Garzón,et al.  The sparse matrix vector product on GPUs , 2011 .

[19]  D. Sevcovic,et al.  APPLICATION OF A CURVATURE ADJUSTED METHOD IN IMAGE SEGMENTATION , 2008 .

[20]  Enhua Wu,et al.  Realtime Simulation of Burning Solids on GPU with CUDA , 2010, 2010 10th IEEE International Conference on Computer and Information Technology.

[21]  J. Cahn,et al.  A microscopic theory for antiphase boundary motion and its application to antiphase domain coasening , 1979 .

[22]  Y. Saad,et al.  GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems , 1986 .

[23]  G. Aubert,et al.  Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations (Applied Mathematical Sciences) , 2006 .