A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system

Abstract This paper presents the sequential and parallel data decomposition strategies implemented on a Particle Swarm Optimization (PSO) algorithm based Artificial Neural Network (PSO-ANN) weights optimization for image reconstruction. The application system is developed for the reconstruction of two-dimensional spatial standard Computed Tomography (CT) phantom images. It is running on a multi-core computer by varying the number of cores. The feed forward ANN initializes the weight between the ‘ideal’ images that are reconstructed using filtered back projection (FBP) technique and the corresponding projection data of CT phantom. In an earlier work, ANN training time is too long. Hence, we propose that the ANN exemplar datasets are decomposed into subsets. Using these subsets, artificial sub neural nets (subnets) are initialized and each subnet initial weights are optimized using PSO. Consequently, it was observed that the sequential approach of the proposed method consumes more training time. Hence the parallel strategy is attempted to reduce the computational training time. The parallel approach is further explored for image reconstruction from ‘noisy’ and ‘limited-angle’ datasets also.

[1]  D. Rowe,et al.  Signal and noise of Fourier reconstructed fMRI data , 2007, Journal of Neuroscience Methods.

[2]  S. Mirza,et al.  Fitness Function Evaluation for Image Reconstruction using Binary Genetic Algorithm for Parallel Ray Transmission Tomography , 2006, 2006 International Conference on Emerging Technologies.

[3]  Robert Cierniak,et al.  A New Approach to Image Reconstruction from Projections Using a Recurrent Neural Network , 2008, Int. J. Appl. Math. Comput. Sci..

[4]  Robert Cierniak,et al.  New neural network algorithm for image reconstruction from fan-beam projections , 2009, Neurocomputing.

[5]  Neeraj Sharma,et al.  Image Processing Tasks using Parallel Computing in Multi core Architecture and its Applications in Medical Imaging , 2013 .

[6]  Yoram Bresler,et al.  O(N2log2N) filtered backprojection reconstruction algorithm for tomography , 2000, IEEE Trans. Image Process..

[7]  Yazid Mohd Saman,et al.  Divide and Conquer Approach in Reducing ANN Training Time for Small and Large Data , 2013 .

[8]  Ramachandran Murugesan,et al.  Evaluation of Algebraic Iterative Algorithms for Reconstruction of Electron Magnetic Resonance Images , 2004, ICVGIP.

[9]  Robert Cierniak,et al.  A 2D approach to tomographic image reconstruction using a Hopfield-type neural network , 2008, Artif. Intell. Medicine.

[10]  P. Nagabhushan,et al.  Parallel Levenberg-Marquardt-Based Neural Network Training on Linux Clusters - A Case Study , 2002, ICVGIP.

[11]  Mumtazimah Mohamad.  Parallel Pattern Back Propagation Neural Network Training of Multilayer Perceptron , 2010 .

[12]  Huazhong Shu,et al.  Reconstruction of tomographic images from limited range projections using discrete Radon transform and Tchebichef moments , 2010, Pattern Recognit..

[13]  Kees Joost Batenburg,et al.  Fast Tomographic Reconstruction From Limited Data Using Artificial Neural Networks , 2013, IEEE Transactions on Image Processing.

[14]  Khalil A. Barhoum,et al.  Grayscale Image Compression Based on Min Max Block Truncating Coding , 2011 .

[15]  Genshe Chen,et al.  2D and 3D ISAR image reconstruction through filtered back projection , 2012, Defense + Commercial Sensing.

[16]  P. Bones,et al.  MRI with TRELLIS: a novel approach to motion correction. , 2008, Magnetic resonance imaging.

[17]  Zhou Yu,et al.  Recent Advances in CT Image Reconstruction , 2013, Current Radiology Reports.

[18]  Rafal Zdunek,et al.  On image reconstruction algorithms for binary electromagnetic geotomography , 2008, Theor. Comput. Sci..

[19]  S. R. Sathe,et al.  Comparison of OpenMP & OpenCL Parallel Processing Technologies , 2012, ArXiv.

[20]  J. G. Alessi,et al.  The Algebraic Reconstruction Technique (ART) , 1997, Proceedings of the 1997 Particle Accelerator Conference (Cat. No.97CH36167).

[21]  Jeffrey A. Fessler,et al.  Model-Based Image Reconstruction for MRI , 2010, IEEE Signal Processing Magazine.

[22]  D. Christopher Durairaj,et al.  A neural network approach for image reconstruction in electron magnetic resonance tomography , 2007, Comput. Biol. Medicine.

[23]  Ming Jiang,et al.  Convergence of the simultaneous algebraic reconstruction technique (SART) , 2003, Conference Record of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers (Cat.No.01CH37256).

[24]  David N Mastronarde,et al.  A fast reconstruction algorithm for electron microscope tomography. , 2003, Journal of structural biology.

[25]  B. F. Logan,et al.  The Fourier reconstruction of a head section , 1974 .

[26]  Yogendra Kumar Jain,et al.  Min Max Normalization Based Data Perturbation Method for Privacy Protection , 2011 .

[27]  Richard Gordon,et al.  Experiments with the nonlinear and chaotic behaviour of the multiplicative algebraic reconstruction technique (MART) algorithm for computed tomography. , 2004, Physics in medicine and biology.

[28]  Xavier Sierra-Canto,et al.  Parallel Training of a Back-Propagation Neural Network Using CUDA , 2010, 2010 Ninth International Conference on Machine Learning and Applications.

[29]  Lukás Burget,et al.  Parallel training of neural networks for speech recognition , 2010, INTERSPEECH.

[30]  Rong Gu,et al.  A parallel computing platform for training large scale neural networks , 2013, 2013 IEEE International Conference on Big Data.

[31]  N. Giokaris,et al.  Tomographic image reconstruction using Artificial Neural Networks , 2004 .

[32]  Victor G. Tsaregorodtsev.  Parallel Implementation of Back-Propagation Neural Network Software on SMP Computers , 2005, PaCT.

[33]  Michael Egmont-Petersen,et al.  Image processing with neural networks - a review , 2002, Pattern Recognit..

[34]  George Bosilca,et al.  Improvement of parallelization efficiency of batch pattern BP training algorithm using Open MPI , 2010, International Conference on Conceptual Structures.

[35]  David A. Bader,et al.  SWARM: A Parallel Programming Framework for Multicore Processors , 2007, IPDPS.