A GPU-based implementations of the fuzzy C-means algorithms for medical image segmentation

Fuzzy clustering is one of the most popular techniques in medical image segmentation. The fuzzy C-means (FCM) algorithm has been widely used as it provides better performance and more information than other algorithms. As the data set becomes large, the serial implementation of the FCM algorithm becomes too slow to accomplish the clustering task within acceptable time. Hence, a parallel implementation [for example, using today’s fast graphics processing unit (GPU)] is needed. In this paper, we implement brFCM algorithm, a faster variant of the FCM algorithm, on two different GPU cards, Tesla M2070 and Tesla K20m. We compare our brFCM GPU-based implementation with its CPU-based sequential implementation. Moreover, we compare brFCM with the traditional version of the FCM algorithm. The experiments used lung CT and knee MRI images for clustering. The results show that our implementation has a significant improvement over the traditional CPU sequential implementation. GPU parallel brFCM is 2.24 times faster than its CPU implementation, and 23.43 times faster than a GPU parallel implementation of the traditional FCM.

[1]  Hamid R. Arabnia,et al.  A Transputer Network for the Arbitrary Rotation of Digitised Images , 1987, Comput. J..

[2]  Atsushi Suzuki,et al.  Image segmentation using CUDA implementations of the Runge-Kutta-Merson and GMRES methods , 2012 .

[3]  Manoranjan Dash,et al.  Graphics Hardware based Efficient and Scalable Fuzzy C-Means Clustering , 2008, AusDM.

[4]  James M. Keller,et al.  Incorporation of Non-euclidean Distance Metrics into Fuzzy Clustering on Graphics Processing Units , 2007, Analysis and Design of Intelligent Systems using Soft Computing Techniques.

[5]  Prabhjot Kaur,et al.  Performance Comparison of Various Robust Data Clustering Algorithms , 2013 .

[6]  Hamid R. Arabnia,et al.  A Reconfigurable Architecture for Image Processing and Computer Vision , 1995, Int. J. Pattern Recognit. Artif. Intell..

[7]  Amit Konar,et al.  Clustering using vector membership: An extension of the Fuzzy C-Means algorithm , 2013, 2013 Fifth International Conference on Advanced Computing (ICoAC).

[8]  Hamid R. Arabnia,et al.  Parallel Edge-Region-Based Segmentation Algorithm Targeted at Reconfigurable MultiRing Network , 2003, The Journal of Supercomputing.

[9]  Jarosław Gocławski,et al.  Cuda Based Fuzzy C-Means Acceleration for the Segmentation of Images with Fungus Grown in Foam Matrices , 2012 .

[10]  Ahmet Cinar,et al.  GPU-Based Image Segmentation Using Level Set Method With Scaling Approach , 2013 .

[11]  Heungsun Hwang,et al.  HIERARCHICALLY STRUCTURED FUZZY C-MEANS CLUSTERING , 2013 .

[12]  Chris Harris,et al.  Iterative Solutions using Programmable Graphics Processing Units , 2005, FUZZ-IEEE.

[13]  Haiyang Li,et al.  An Improved Image Segmentation Algorithm Based on GPU Parallel Computing , 2014, J. Softw..

[14]  James M. Keller,et al.  Speedup of Fuzzy Clustering Through Stream Processing on Graphics Processing Units , 2008, IEEE Transactions on Fuzzy Systems.

[15]  Ismail Hmeidi,et al.  Localization of Coronary Artery Thrombosis Using Coronary Angiography , 2014 .

[16]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[17]  Prafulla N. Aerkewar,et al.  Image Segmentation Methods for Dermatitis Disease : A Survey , 2013 .

[18]  Ieee Xplore,et al.  International Conference on Innovations in Information Technology , 2004 .

[19]  Anders Eklund,et al.  Medical image processing on the GPU - Past, present and future , 2013, Medical Image Anal..

[20]  Mahmoud Al-Ayyoub,et al.  Improving FCM and T2FCM algorithms performance using GPUs for medical images segmentation , 2015, 2015 6th International Conference on Information and Communication Systems (ICICS).

[21]  Lei Pan,et al.  Implementation of medical image segmentation in CUDA , 2008, 2008 International Conference on Information Technology and Applications in Biomedicine.

[22]  Mahmoud Al-Ayyoub,et al.  Computer-aided diagnosis of lumbar disc herniation , 2015, 2015 6th International Conference on Information and Communication Systems (ICICS).

[23]  Susan L. Graham,et al.  Gprof: A call graph execution profiler , 1982, SIGPLAN '82.

[24]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[25]  Lawrence O. Hall,et al.  Fast Accurate Fuzzy Clustering through Data Reduction , 2003 .

[26]  Yong Cao,et al.  GPU accelerated fuzzy connected image segmentation by using CUDA , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  Chih-Cheng Hung,et al.  An Adaptive Weighted Fuzzy C-means Clustering Algorithm for Remote Sensing Image Classification , 2013 .

[28]  Frank Lindseth,et al.  GPU accelerated segmentation and centerline extraction of tubular structures from medical images , 2013, International Journal of Computer Assisted Radiology and Surgery.

[29]  Patel Janakkumar Baldevbhai.  Review of Graph, Medical and Color Image base Segmentation Techniques , 2012 .

[30]  Jiang Cheng,et al.  ECG, Bi-Polar, Discrete Wavelet Transform, Hilbert-Huang Transform , 2012 .

[31]  Andrzej Urbanik,et al.  Segmentation of bones in magnetic resonance images of the wrist , 2014, International Journal of Computer Assisted Radiology and Surgery.

[32]  S. Hariri,et al.  Exploiting GPUs for compute-intensive medical applications , 2012, 2012 International Conference on Multimedia Computing and Systems.

[33]  Gabor Fichtinger,et al.  Intraoperative segmentation of iodine and palladium radioactive sources in C-arm images , 2014, International Journal of Computer Assisted Radiology and Surgery.

[34]  Andrew D. Pangborn.  Scalable data clustering using GPUs , 2010 .

[35]  McCabe.  Jordan chosen to open SESAME. Synchrotron-light for Experimental Science and Applications in the Middle East , 2000, Nature.