Skip to main content

Advertisement

Springer Nature Link
Log in

Segmentation of the left ventricle in cardiac MRI using a hierarchical extreme learning machine model

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) images is an essential step for calculation of clinical indices such as stroke volume, ejection fraction. In this paper, a new automatic LV segmentation method combines a Hierarchical Extreme Learning Machine (H-ELM) and a new location method is developed. An H-ELM can achieve more compact and meaningful feature representations and learn the segmentation task from the ground truth. A new automatic LV location method is integrated to improve the accuracy of classification and reduce the cost of segmentation. Experimental results (including 30 cases, 10 cases for training, 20 cases for testing) show that the mean absolute deviation of images segmented by our proposed method is about 67.9, 81.3 and 98.7% of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean maximum absolute deviation of images segmented by our proposed method is about 63.5, 77.3 and 98.0% of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean dice similarity coefficient of images segmented by our proposed method is about 13.7, 9.3 and 0.5% higher than that of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean speed of our proposed method is about 38.3, 6.7 and 23.8 times faster than that of the level set, the SVM and Hu’s method, respectively. The standard deviation of our proposed method is the lowest among four methods. The results validate that our proposed method is efficient and satisfactory for the LV segmentation.

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
$34.99 /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 excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. World Health Organization (2014) Global status report on noncommunicable diseases 2014. http://www.who.int/mediacentre/factsheets/fs317/en/. Accessed 5 April 2016

  2. Hu HF, Gao ZY, Liu LM et al (2014) Automatic segmentation of the left ventricle in cardiac MRI using local binary fitting model and dynamic programming techniques. PLoS One 9:e114760–e114760. doi:10.1371/journal.pone.0114760

    Article  Google Scholar 

  3. Frangi AF, Niessen WJ, Viergever MA (2001) Three-dimension modeling for functional analysis of cardiac images: a review. IEEE Trans Med Imaging 20:2–25. doi:10.1109/42.906421

    Article  Google Scholar 

  4. Avendi MR, Kheradvar A, Jafarkhani H (2016) A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Med Image Anal 30:108–19. doi:10.1016/j.media.2016.01.005

    Article  Google Scholar 

  5. Petitjean C, Dacher JN (2011) A review of segmentation methods in short axis cardiac MR images. Med Image Anal 15:169–84. doi:10.1016/j.media.2010.12.004.15

    Article  Google Scholar 

  6. Queir S, Barbosa D, Heyde B et al (2014) Fast automatic myocardial segmentation in 4D cine CMR datasets. Med Image Anal 18:1115–1131. doi:10.1016/j.media.2014.06.001

    Article  Google Scholar 

  7. Tavakoli V, Amini AA (2013) A survey of shaped-based registration and segmentation techniques for cardiac images. Comput Vis Image Underst 117:966–989. doi:10.1016/j.cviu.2012.11.017

    Article  Google Scholar 

  8. Cootes TF, Taylor CJ, Cooper DH et al (1995) Active shape models-their training and application. Comput Vis Image Und 61:38–59. doi:10.1006/cviu.1995.1004

    Article  Google Scholar 

  9. Georgescu B, Zhou XS, Comaniciu D et al (2005) Database-guided segmentation of anatomical structures with complex appearance. IEEE Comput Soc Conf Comput Vis Pattern Recognit (CVPR’05) 2:429–436. doi:10.1109/CVPR.2005.119

  10. Zheng Y, Barbu A, Georgescu B et al (2008) Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features. IEEE Trans Med Imaging 27:1668–1681. doi:10.1109/TMI.2008.2004421

    Article  Google Scholar 

  11. Ngo TA, Lu Z, Carneiro G (2016) Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance. Med Image Anal 35:159–71. doi:10.1016/j.media.2016.05.009

    Article  Google Scholar 

  12. Zhao YH, Wang GR, Zhang X et al (2014) Learning phenotype structure using sequence model. IEEE Trans Knowl Data Eng 26:667–681. doi:10.1109/TKDE.2013.31

    Article  Google Scholar 

  13. Tang J, Deng C, Huang GB (2016) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst 27:809–821. doi:10.1109/TNNLS.2015.2 424995

    Article  MathSciNet  Google Scholar 

  14. Huang GB (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cognit Comput 6:376–390. doi:10.1007/s12559-014-9255-2

    Article  Google Scholar 

  15. Huang GB, Zhou H, Ding X et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42:513–529. doi:10.1109/TSMC B. 2011.2168604

    Article  Google Scholar 

  16. Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2:107–122. doi:10.1007/s13042-011-0019-y

    Article  Google Scholar 

  17. Miche Y, Sorjamaa A, Bas P et al (2010) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Netw 21:158–162. doi:10.1109/TNN.2009.2036259

    Article  Google Scholar 

  18. Soria-Olivas E, Gomez-Sanchis J, Martin JD et al (2011) BELM: Bayesian extreme learning machine. IEEE Trans Neural Netw 22:505–509. doi:10.1109/TNN.2010.2103956

    Article  Google Scholar 

  19. Wang LJ, Pei MC, Codella NC et al (2015) Left ventricle: fully automated segmentation based on spatiotemporal continuity and myocardium information in cine cardiac magnetic resonance imaging (LV-FAST). Biomed Res Int 2015:1–9. doi:10.1155/2015/367583

    Google Scholar 

  20. Lee HY, Codella NC, Cham MD et al (2010) Automatic left ventricle segmentation using iterative thresholding and an active contour model with adaptation on short-axis cardiac MRI. IEEE Trans Biomed Eng 57:905–13. doi:10.1109/TBME.2009.2014545

    Article  Google Scholar 

  21. Geiger D, Gupta A, Costa LA et al (1995) Dynamic programming for detecting, tracking and matching deformable contours. IEEE Trans Pattern Anal Mach Intell 19:294–302. doi:10.1109/ 34.368194

    Article  Google Scholar 

  22. Lalande A, Legrand LP, Walker PM et al (1999) Automatic detection of left ventricular conours from cardiac cine magnetic resonance imaging using fuzzy logic. Invest Radiol 34:211–7. doi:10.1016/S0921-4534(98)00004-5

    Article  Google Scholar 

  23. Zmc M, van der Geest RJ, Swingen C et al (2006) Time continuous tracking and segmentation of cardiovascular magnetic resonance images using multidimensional dynamic programming. Invest Radiol 41:52–62. doi:10.1097/01.rli.0000194070.88432.24

  24. Yeh JY, Fu JC, Wu CC et al (2005) Myocardial border detection by brand-and-bound dynamic programming in magnetic resonance images. Comput Methods Programs Biomed 79:19–29. doi:10.1016/j.cmpb.2004.10.010

    Article  Google Scholar 

  25. Lu Y, Radau P, Connelly K et al (2009) Automatic image-driven segmentation of left ventricle in cardiac cine MRI. Midas J 5528:339–347. doi:10.1002/jmri.21451

    Google Scholar 

  26. Otsu N (1975) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66. doi:10.1109/TSMC.1979.4310076

    Article  Google Scholar 

  27. Hu H, Liu H, Gao Z et al (2013) Hybrid segmentation of left ventricle in cardiac MRI using Gaussian-mixture model and region restricted dynamic programming. Magn Reson Imaging 31:575–584. doi:10.1016/j.mri.2012.10.004

    Article  Google Scholar 

  28. Xu J, Monaco JP, Madabhushi A (2010) Markov random field driven region-based active contour model (MaRACel): application to medical image segmentation. Med Image Comput Comput Assist Intervent (MICCAI) 13:197–204. doi:10.1007/978-3-642-15711-0_25

    Google Scholar 

  29. Reyna RA, Hernandez N, Esteve D et al (2000) Segmenting images with support vector machines. Int Conf Image Process 1:820–823. doi:10.1109/ICIP.2000.901085

    Google Scholar 

  30. Cousty J, Najman L, Couprie M et al (2010) Segmentation of 4D cardiac MRI: automated method based on spatio-temporal watershed cuts. Image Vision Comput 28:1229–1243. doi:10.1016/j.imavis.2010.01.001

    Article  Google Scholar 

  31. Grosgeorge D, Petitjean C, Caudron J et al (2011) Automatic cardiac ventricle segmentation in MR images: a validation study. Int J Comput Assist Radiol Surg 6:573–581. doi:10.1007/s1154 8-010-0532-6

    Article  Google Scholar 

  32. Kaus MR, Berg J, Weese J et al (2004) Automated segmentation of the left ventricle in cardiac MRI. Med Image Anal 8:245–254. doi:10.1016/j.media.2004.06.015

    Article  Google Scholar 

  33. Santarelli MF, Positano V, Michelassi C et al (2003) Automated cardiac MR image segmentation: theory and measurement evaluation. Med Eng Phys 25:149–159. doi:10.1016/S1350-4533(0 2)00144-3

    Article  Google Scholar 

  34. Ammar M, Mahmoudi S, Chikh MA et al (2012) Endocardial border detection in cardiac magnetic resonance images using level set method. J Digit Imaging 25:294–306. doi:10.1007/s10278-011-9404-z

    Article  Google Scholar 

  35. Chen T, Babb J, Kellman P et al (2008) Semiautomated segmentation of myocardial contours for fast strain analysis in cine displacement-encoded MRI. IEEE Trans Med Imaging 27:1084–1094. doi:10.1109/TMI.2008.918327

    Article  Google Scholar 

  36. Li CM, Huang R, Ding Z et al (2011) A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans Image Process 20:2007–2016. doi:10.1109/TIP.2011.2146190

    Article  MathSciNet  MATH  Google Scholar 

  37. Pham VT, Tran TT, Shyu KK et al (2014) Multiphase B-spline level set and incremental shape priors with applications to segmentation and tracking of left ventricle in cardiac MR images. PLoS One 25:1967–1987. doi:10.1007/s00138-014-0626-1

    Google Scholar 

  38. OBrien SP, Ghita O, Whelan PF, (2011) A novel model-based 3D+ time left ventricular seg-mentation technique. IEEE Trans Med Imaging 30:461–474. doi:10.1109/TMI.2010.2086465

  39. Pednekar A, Kurkure U, Muthupillai R et al (2006) Automated left ventricular segmentation in cardiac MRI. IEEE Trans Biomed Eng 53:1425–1428. doi:10.1109/TBME.2006.873684

  40. Zhang HH, Wahle A, Johnson RK et al (2010) 4-D cardiac MR image analysis: left and right ventricular morphology and function. IEEE Trans Med Imaging 29:350–364. doi:10.1109/TMI.2009.2030799

    Article  Google Scholar 

  41. Pluempitiwiriyawej C, Moura JM, Wu YJ et al (2005) New active contour scheme for cardiac MR image segmentation. IEEE Trans Med Imaging 24:593–603. doi:10.1109/TMI.2005.843740

    Article  Google Scholar 

  42. Paragios N (2002) A variational approach for the segmentation of the left ventricle in cardiac image analysis. Int J Comput Vision 50:345–362. doi:10.1023/A:1020882509893

    Article  MATH  Google Scholar 

  43. Edwards GJ, Taylor CJ, Cootes TF (1998) Interpreting face images using active appearance models. Int Conf Autom Face Gest Recogn 92:145–149. doi:10.1109/AFGR.1998.670965

    Google Scholar 

  44. Zambal S, Hladvka J, Bhler K (2006) Improving segmentation of the left ventricle using a two-component statistical model. Med Image Comput Comp Assist Intervent (MICCAI) 9:151–158. doi:10.1007/11866565_19

    Google Scholar 

  45. Lorenzo-Valds M, Sanchez-Ortiz GI, Mohiaddin R et al (2002) Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration. Med Image Comput Comp Assist Intervent (MICCAI) 2488:642–650. doi:10.1007/3-540-45786-0_79

    MATH  Google Scholar 

  46. Lorenzo-Valds M, Sanchez-Ortiz GI, Elkington AG et al (2004) Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal 8:255–265. doi:10.1007/978-3-540-39899-8_55

    Article  Google Scholar 

  47. Ltjnen J, Kivist S, Koikkalainen J (2004) Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Med Image Anal 8:371–386. doi:10.1016/j. media.06.013

    Article  Google Scholar 

  48. Zhao YH, Wang GR, Yin Y et al (2014) Improving ELM-based microarray data classification by diversified sequence features selection. Neural Comput Appl 27:155–166. doi:10.1007/s00521-014-1571-7

    Article  Google Scholar 

  49. Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501. doi:10.1016/j.neucom.2005.12.126

    Article  Google Scholar 

  50. Cao J, Zhang K, Luo M et al (2016) Extreme learning machine and adaptive sparse representation for image classification. Neural Netw 81:91–102. doi:10.1016/j.neunet.2016.06.001

    Article  Google Scholar 

  51. Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17:879–892. doi:10.1109/TNN.2006.875977

    Article  Google Scholar 

  52. Kasun LLC, Zhou H, Huang GB et al (2013) Representational learning with extreme learning machine for big data. IEEE Intell Syst 28:31–34. doi:10.1109/MIS.2013.140

    Article  Google Scholar 

  53. Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imag Sci 2:183–202. doi:10.1137/080716542

    Article  MathSciNet  MATH  Google Scholar 

  54. Beck A, Teboulle M (2009) Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans Image Process 18:2419–2434. doi:10.1109/TIP.2009.2028250

    Article  MathSciNet  MATH  Google Scholar 

  55. Wan SY, William H (2003) Symmetric region growing. IEEE Trans Image Process 12:1007–1015. doi:10.1109/TIP.2003.815258

    Article  Google Scholar 

  56. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) 1:886–893. doi:10.1109/CVPR.2005.177

  57. Kang C, Liao S, Xiang S, Pan C (2014) Kernel sparse representation with pixel-level and region-level local feature kernels for face recognition. Neurocomputing 133:141–152. doi:10.1016/j.neucom.2013.11.022

    Article  Google Scholar 

  58. Ojala T, Pietikainen M, Maenpaa T (2002) Multi resolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987. doi:10.1109/TPAMI.2002.1017623

    Article  MATH  Google Scholar 

  59. Zheng Q, Lu Z, Zhang M et al (2015) Automatic segmentation of myocardium from black-blood MR images using entropy and local neighborhood information. PloS One 10:e0120018. doi:10.1371/ journal.pone.0120018

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China (Nos. 61374015, 61202258), and the Fundamental Research Funds for the Central Universities (Nos. N130404016, N110219001).

Author information

Author notes

    Authors and Affiliations

    1. Sino-Dutch Biomedical and Information Engineering School, Northeastern University Shenyang, Shenyang, 110167, Liaoning, China

      Yang Luo, Lisheng Xu, Liling Hao, Jun Liu & Yang Yao

    2. Anshan Normal University, Anshan, 114005, Liaoning, China

      Yang Luo

    3. General Hospital of Shenyang Military, Shenyang, 110016, Liaoning, China

      Benqiang Yang

    4. Key Laboratory of Medical Image Computing, Ministry of Education, Shenyang, 110819, China

      Lisheng Xu

    5. Department of Biomedical Engineering, Eindhoven University of Technology, 5600 MB, Eindhoven, The Netherlands

      Frans van de Vosse

    Authors
    1. Yang Luo
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Benqiang Yang
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Lisheng Xu
      View author publications

      You can also search for this author in PubMed Google Scholar

    4. Liling Hao
      View author publications

      You can also search for this author in PubMed Google Scholar

    5. Jun Liu
      View author publications

      You can also search for this author in PubMed Google Scholar

    6. Yang Yao
      View author publications

      You can also search for this author in PubMed Google Scholar

    7. Frans van de Vosse
      View author publications

      You can also search for this author in PubMed Google Scholar

    Corresponding author

    Correspondence to Lisheng Xu.

    Additional information

    Yang Luo and Benqiang Yang contributed equally to this work and are co-first authors.

    Rights and permissions

    Reprints and permissions

    About this article

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this article

    Luo, Y., Yang, B., Xu, L. et al. Segmentation of the left ventricle in cardiac MRI using a hierarchical extreme learning machine model. Int. J. Mach. Learn. & Cyber. 9, 1741–1751 (2018). https://doi.org/10.1007/s13042-017-0678-4

    Download citation

    • Received:

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s13042-017-0678-4

    Keywords