[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

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

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Aerkewar PN, Agrawal G (2013) Image segmentation methods for dermatitis disease: a survey. Int J Eng Inven 2(1):01–06

    Google Scholar 

  2. Oqaily A et al (2014) Localization of coronary artery thrombosis using coronary angiography. In: The Third international conference on informatics engineering and information science (ICIEIS2014), pp 310–316

  3. Alawneh K et al (2015) Computer-aided diagnosis of lumbar disk herniation. In: Proceedings of the 6th international conference on information and communication systems (ICICS 2015)

  4. Jain AK (2010) Data clustering: 50 years beyond k-means. Pattern Recogn Lett 31(8):651–666. doi:10.1016/j.patrec.2009.09.011

    Article  Google Scholar 

  5. Bezdek JC, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(23):191–203. doi:10.1016/j.patrec.2009.09.011

    Article  Google Scholar 

  6. Eklund A, Dufort P, Forsberg D, LaConte SM (2013) Medical image processing on the GPU past, present and future. Med Image Anal 17(8):1073–1094. doi:10.1016/j.media.2013.05.008

    Article  Google Scholar 

  7. Eschrich S, Ke J, Hall L, Goldgof D (2003) Fast accurate fuzzy clustering through data reduction. IEEE Trans Fuzzy Syst 11(2):262–270. doi:10.1109/TFUZZ.2003.809902

    Article  Google Scholar 

  8. (n.d.) Lung image database consortium (lidc). http://imaging.cancer.gov/programsandresources/informationsystems/lidc. Accessed Oct 2014

  9. (n.d.) Knee MRI. http://www.mr-tip.com/serv1.php?type=img&img=Sagittal+Knee+MRI+Images+T1+Weighted. Accessed Oct 2014

  10. di San Amat, Filippo C, Fichtinger G, Morris W, Salcudean S, Dehghan E, Fallavollita P (2014) Intraoperative segmentation of iodine and palladium radioactive sources in C-arm images. Int J Comput Assist Radiol Surg 9(5):769–776. doi:10.1007/s11548-014-0983-2

    Article  MATH  Google Scholar 

  11. Al-Darabsah K, Al-Ayyoub M (2013) Breast cancer diagnosis using machine learning based on statistical and texture features extraction. In: Proceedings of the 4th International conference on information and communication systems (ICICS 2013)

  12. Al-Ayyoub M, Alawad D, Al-Darabsah K, Aljarrah I (2013) Automatic detection and classification of brain hemorrhages. WSEAS Trans Comput 12(10):395–405

    Google Scholar 

  13. Baldevbhai PJ, Anand R (2012) Review of graph, medical and color image base segmentation techniques. IOSR J Electr Electron Eng 1(1):1–19

    Article  Google Scholar 

  14. Sharma S, Goel M, Kaur P (2013) Performance comparison of various robust data clustering algorithms. Int J Intell Syst Appl 5(7):63

    Google Scholar 

  15. Lm YIN, JIANG C, JIANG C, HU Yb (2012) The fast gpu parallel algorithm based on image segmentation of a level set. J Converg Inf Technol 7(18):332–339

    Article  Google Scholar 

  16. Guler Z, Cinar A (2013) GPU-based image segmentation using level set method with scaling approach. In: International conference on advanced information technologies and applications (ICAITA), pp 81–92. doi:10.5121/csit.2013.3808

  17. Oberhuber T, Suzuki A, Vacata J, Žabka V (2011) Image segmentation using CUDA implementations of the runge-kutta-merson and GMRES methods. J Math Ind 3:73–79

    Google Scholar 

  18. Zhuge Y, Cao Y, Miller R (2009) Gpu accelerated fuzzy connected image segmentation by using cuda. In: Engineering in medicine and biology society, 2009. EMBC 2009. Annual International conference of the IEEE, pp 6341–6344. doi:10.1109/IEMBS.2009.5333158

  19. Smistad E, Elster A, Lindseth F (2014) GPU accelerated segmentation and centerline extraction of tubular structures from medical images. Int J Comput Assist Radiol Surg 9(4):561–575. doi:10.1007/s11548-013-0956-x

    Article  Google Scholar 

  20. Pan L, Gu L, Xu J (2008) Implementation of medical image segmentation in CUDA. In: Information technology and applications in biomedicine, 2008. ITAB 2008. International conference on, pp 82–85. doi:10.1109/ITAB.2008.4570542

  21. Wani MA, Arabnia HR (2003) Parallel edge-region-based segmentation algorithm targeted at reconfigurable multi-ring network. J Supercomput 25(1):43–63

    Article  MATH  Google Scholar 

  22. Bhandarkar SM, Arabnia HR, Smith JW (1995) A reconfigurable architecture for image processing and computer vision. Int J Pattern Recogn Artif Intell 9(2):201–229

    Article  Google Scholar 

  23. Shehab MA et al (2015) Improving FCM and T2FCM algorithms performance using GPUS for medical images segmentation. In: Proceedings of the 6th international conference on information and communication systems (ICICS 2015)

  24. Wlodarczyk J, Czaplicka K, Tabor Z, Wojciechowski W, Urbanik A (2014) Segmentation of bones in magnetic resonance images of the wrist. Int J Comput Assist Radiol Surg, pp 1–13. doi:10.1007/s11548-014-1105-x

  25. Won Suk H, Yeh Choi J, Hwang H (2012) Hierarchically structured fuzzy c-means clustering. Behaviormetrika 40(1):1–17. doi:10.2333/bhmk.40.1

    Article  Google Scholar 

  26. Ganguly S, Bose D, Konar A (2013) Clustering using vector membership: an extension of the fuzzy c-means algorithm. CORR abs/1312.4074

  27. Liua W, Cuia T, Hungb CC, Chenc S (2013) An adaptive weighted fuzzy c-means clustering algorithm for remote sensing image classification. J Inform Comput Sci 10(7):2009–2020. doi:10.12733/jics20101678

    Article  Google Scholar 

  28. AlZubi S et al (2012) Medical volume segmentation using 3d multiresolution analysis. In: 2012 international conference on innovations in information technology (IIT)

  29. Jararweh Y, Jarrah M, Hariri S (2012) Exploiting gpus for compute-intensive medical applications. In: Multimedia computing and systems (ICMCS), 2012 international conference on, IEEE, pp 29–34

  30. Jararweh Y, Hariri S, Moukabary T (2009) Simulating of cardiac electrical activity with autonomic run time adjustments. AHSC frontiers in biomedical research

  31. (n.d.) Parallel programming and computing platform CUDA NVIDIA. http://www.nvidia.com/object/cuda_home_new.html. Accessed Oct 2014

  32. (n.d.) Nvcc: Cuda toolkit documentation. http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/. Accessed Oct 2014

  33. Harris C, Haines K (2005) Iterative solutions using programmable graphics processing units. In: Fuzzy systems, 2005. FUZZ ’05. The 14th IEEE international conference on, pp 12–18

  34. Anderson D, Luke R, Keller J (2007) Incorporation of non-euclidean distance metrics into fuzzy clustering on graphics processing units. In: Melin P, Castillo O, Ramrez E, Kacprzyk J, Pedrycz W (eds) Analysis and design of intelligent systems using soft computing techniques, advances in soft computing, vol 41, Springer, Berlin Heidelberg, pp 128–139. doi:10.1007/978-3-540-72432-2_14

  35. Shalom SAA, Dash M, Tue M (2008) Graphics hardware based efficient and scalable fuzzy c-means clustering. In: Proceedings of the 7th Australasian data mining conference, volume 87, Australian Computer Society Inc, Darlinghurst, Australia, AusDM ’08, pp 179–186

  36. Anderson D, Luke R, Keller J (2008) Speedup of fuzzy clustering through stream processing on graphics processing units. IEEE Trans Fuzzy Syst 16(4):1101–1106. doi:10.1109/TFUZZ.2008.924203

    Article  Google Scholar 

  37. Pangborn AD (2010) Scalable data clustering using GPUS. Master’s thesis, Rochester Institute of Technology

  38. Rowińska Z, Gocławski J (2012) Cuda based fuzzy c-means acceleration for the segmentation of images with fungus grown in foam matrices. Image Process Commun 17(4):191–200. doi:10.2478/v10248-012-0046-7

    Google Scholar 

  39. Li H, Yang Z, He H (2014) An improved image segmentation algorithm based on GPU parallel computing. J Softw 9(8):1985–1990. doi:10.4304/jsw.9.8.1985-1990

    Google Scholar 

  40. Arabnia HR, Smith JW (1993) A reconfigurable interconnection network for imaging operations and its implementation using a multi-stage switching box. In: Proceedings of the 7th annual international high performance computing conference, pp 349–357

  41. Arabnia HR, Oliver MA (1987) A transputer network for the arbitrary rotation of digitised images. Comput J 30(5):425–432

    Article  Google Scholar 

  42. Graham SL, Kessler PB, Mckusick MK (1982) Gprof: a call graph execution profiler. ACM Sigplan Not 17(6):120–126. doi:10.1145/872726.806987

    Article  MATH  Google Scholar 

  43. (n.d.) The Cy-Tera project. http://www.linksceem.eu/ls2/project/hpc-sites/castorc/cytera.html. Accessed Oct 2014

  44. Sesame synchrotron-light for experimental science and applications in the middle east. http://sesame.org.jo/sesame/. Accessed Oct 2014

  45. (n.d.) Soroosh129/GPU-FCM. https://github.com/Soroosh129/GPU-FCM. Accessed Oct 2014

  46. (n.d.) Unified memory in CUDA 6. http://devblogs.nvidia.com/parallelforall/unified-memory-in-cuda-6/. Accessed Oct 2014

Download references

Acknowledgments

This work was supported in part by the Deanship of Research at the Jordan University of Science and Technology Grant number 20130195. For the experiments, this work benefited from the computing resources of IMAN1 provided by the Synchrotron-Light for Experimental Science and Applications in the Middle East (SESAME). Also, this work was co-funded by the European Regional Development Fund and the Republic of Cyprus through the Research Promotion Foundation (Project Cy-Tera NEA Y\(\varPi \)O\(\varDelta \)OMH/*\(\sum \)TPATH/0308/31).

Author information

Authors and Affiliations

  1. Jordan University of Science and Technology, Irbid, Jordan

    Mahmoud Al-Ayyoub, Ansam M. Abu-Dalo, Yaser Jararweh & Moath Jarrah

  2. Department of Physics, University of Cambridge, Cambridge, UK

    Mohammad Al Sa’d

Authors
  1. Mahmoud Al-Ayyoub
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ansam M. Abu-Dalo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yaser Jararweh
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Moath Jarrah
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mohammad Al Sa’d
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahmoud Al-Ayyoub.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Al-Ayyoub, M., Abu-Dalo, A.M., Jararweh, Y. et al. A GPU-based implementations of the fuzzy C-means algorithms for medical image segmentation. J Supercomput 71, 3149–3162 (2015). https://doi.org/10.1007/s11227-015-1431-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-015-1431-y

Keywords

Search

Navigation