Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 17, pp 21879–21904 | Cite as

Segmentation of cardiac tagged MR images using a snake model based on hybrid gradient vector flow

  • Zhuo Yu
  • Qian Wang
  • Wei Xiong
  • Chengde Zhang
  • Huaifei Hu
Article
  • 182 Downloads

Abstract

In the segmentation of cardiac tagging magnetic resonance (tMR) images, it is difficult to segment the left ventricle automatically by using the traditional segmentation model because of the interference caused by the tags. A new snake model based on hybrid gradient vector flow (HGVF) is proposed by us to improve this segmentation. Due to the different characteristics between endocardium and epicardium of the left ventricle (LV), several gradient vector flows (GVFs) with distinctive boundary information would be fused to segment these two sub regions individually. For segmentation of endocardium, we construct a new HGVF in snake model fused by three independent GVFs. These flows are respectively exported from the original cardiac tMR image, the tags-removed image and the local-filtered image. On the other hand, since the epicardium is with a nearly-circle shape, we construct the other HGVF which is composed of two different GVFs. One of them is derived from the tags-removed image either and the other one is derived from the ideal circle-shape image. Some experiments have been done to validate our new segmentation model. The average overlap of the endocardium segmentation is 89.67% (its mean absolute distance is 1.86 pixels), and the average overlap of the epicardium segmentation is 95.88% (its mean absolute distance is 1.64 pixels). Experimental results show that the proposed method improves the segmentation performance compared to some available methods effectively.

Keywords

The segmentation of left ventricle Tagging magnetic resonance image Notch bandstop filtering GVF snake 

Notes

Acknowledgements

We would like to thank Tongji Hospital, affiliated with Huazhong University of Science and Technology, for providing the experimental datasets used in this study and for offering useful medical suggestions.

This research was funded by the National Natural Science Foundation of China (Grant No. 61602519); Ministry of Education of China (MOE) Project of Humanities and Social Sciences (Project No. 16YJC860026); China Postdoctoral Science Foundation (Grant No. 2013M542021); China Postdoctoral Science Foundation (Grant No.2014M562026); the Natural Science Foundation of Hubei Province, China (Grant No. 2013CFC090); the Fundamental Research Funds for the Central Universities, Zhongnan University of Economics and Law (Grant No. 2012096).

References

  1. 1.
    Avendi MR, Kheradvar A, Jafarkhani H (2015) A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac mri. Med Image Anal 30:108–119CrossRefGoogle Scholar
  2. 2.
    Chen M, Mao S, Liu Y (2014) Big data: a survey. Mob Netw Appl 19(2):171–209CrossRefGoogle Scholar
  3. 3.
    Chen M, Ma Y, Li Y, Wu D, Zhang Y (2017) Wearable 2.0: enabling Human-Cloud integration in next generation healthcare systems. IEEE Commun Mag 54(12):3–9Google Scholar
  4. 4.
    Dakua SP, Sahambi JS (2010) A strategic approach for cardiac mr left ventricle segmentation. Cardiovasc Eng 10(3):163CrossRefGoogle Scholar
  5. 5.
    Dharanibai G, Raina JP (2014) Automatic segmentation of left ventricle endocardium from cardiac mr images using active contours driven by local and global intensity fitting energy. Int J Med Eng Inform 6(2):115–134CrossRefGoogle Scholar
  6. 6.
    Hajiaghayi M, Groves E, Jafarkhani H, Kheradvar A (2016) A 3d active contour method for automated segmentation of the left ventricle from magnetic resonance images. IEEE Trans Biomed Eng, pp 1–1Google Scholar
  7. 7.
    Huang S, Liu J, Lee LC, Venkatesh SK, Teo LL, Au C et al (2011) An image-based comprehensive approach for automatic segmentation of left ventricle from cardiac short axis cine mr images. J Digit Imaging 24(4):598–608CrossRefGoogle Scholar
  8. 8.
    Kasai M (1990) Clinical application of magnetic resonance imaging (mri) in uterine disease. Nihon Sanka Fujinka Gakkai Zasshi 42(7):711–718Google Scholar
  9. 9.
    Li ZL (2011) Tagged cardiac mr image segmentation based on texture analysis. J Clin Rehabilitative Tissue Eng Res 15(9):1521–1524Google Scholar
  10. 10.
    Liu FC, Chen Q, Sun QS, Ann HP, Xia DS (2009) Texture classification and shape statistics variational approach for segmentation of left ventricle tagged mr images. J Softw 20(1):30–40CrossRefGoogle Scholar
  11. 11.
    Liu L, Wu Y, Wang Y (2009) A novel method for segmentation of the cardiac mr images using generalized ddgvf snake models with shape priors. Inf Technol J 8 (4):486–494CrossRefGoogle Scholar
  12. 12.
    Liu L, Song J, Chen M, Liu B (2012) Segmentation of the left ventricle from cardiac mr images using active contours with negvf. J Bioinforma Intell Control 1(1):56–63CrossRefGoogle Scholar
  13. 13.
    Liu Y, Captur G, Moon JC, Guo S, Yang X, Zhang S, et al. (2015) Distance regularized two level sets for segmentation of left and right ventricles from cine-mri. Magn Reson Imaging 34(5):699–706CrossRefGoogle Scholar
  14. 14.
    Makram AW, Khalifa AM, El-Wakad MT, El-Rewaidy H (2014) Evaluation of cardiac left ventricular mass from tagged magnetic resonance imaging. Biomed Eng Conf, pp 67–70Google Scholar
  15. 15.
    Ngo TA, Lu Z, Carneiro G (2017) 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 35:159–171CrossRefGoogle Scholar
  16. 16.
    Pham VT, Tran TT (2016) Active contour model and nonlinear shape priors with application to left ventricle segmentation in cardiac mr images. Optik - Int J Light Electron Opt 127(3):991–1002CrossRefGoogle Scholar
  17. 17.
    Pham VT, Tran TT, Shyu KK, Lin LY, Wang YH, Lo MT (2014) Multiphase b-spline level set and incremental shape priors with applications to segmentation and tracking of left ventricle in cardiac mr images. Mach Vis Appl 25 (8):1967–1987CrossRefGoogle Scholar
  18. 18.
    Qin X, Tian Y, Yan P (2015) Feature competition and partial sparse shape modeling for cardiac image sequences segmentation. Neurocomputing 149(PB):904–913CrossRefGoogle Scholar
  19. 19.
    Rm FIV (2014) Automatic cardiac lv segmentation in mri using modified graph cuts with smoothness and interslice constraints. Magn Reson Med 72(6):1775–1784CrossRefGoogle Scholar
  20. 20.
    Varghese T, Schultz WM, Mccue AA, Lambert CT, Sandesara PB, Eapen DJ et al (2016) Physical activity in the prevention of coronary heart disease: implications for the clinician. Heart, heartjnl-2015-308773Google Scholar
  21. 21.
    Wang B, Gu X, Fan C, Xie H, Zhang S, Tian X et al (2015) Sparse group composition for robust left ventricular epicardium segmentation. Comput Med Imaging Graph 46:56–63CrossRefGoogle Scholar
  22. 22.
    Xu C, Prince JL (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process A Publ IEEE Signal Process Soc 7(3):359MathSciNetzbMATHGoogle Scholar
  23. 23.
    Xu L, Yan Q, Xia Y, Jia J (2012) Structure extraction from texture via relative total variation. Acm Trans Graph 31(6):139Google Scholar
  24. 24.
    Yuwei W, Liang J, Wang Y (2010) A method for segmentation of the cardiac mr images based on ggvf snake. J Image GraphGoogle Scholar
  25. 25.
    Zhang N, Xue-Fei YU, Guang-Wen LU (2012) Endocardium and epicardium segmentation of left ventricle in cardiac magnetic resonance images based on directional snake model. J Comput Appl 32(7):1902–1901Google Scholar
  26. 26.
    Zhang Y, Qiu M, Tsai CW, Hassan MM, Alamri A (2015) Health-cps: healthcare cyber-physical system assisted by cloud and big data. IEEE Syst J, pp 1–8Google Scholar
  27. 27.
    Zhang Y, Zhang D, Hassan MM, Alamri A, Peng L (2015) Cadre: cloud-assisted drug recommendation service for online pharmacies. Mob Netw Appl 20(3):348–355CrossRefGoogle Scholar
  28. 28.
    Zhang Y, Chen M, Huang D, Wu D, Li Y (2016) Idoctor: personalized and professionalized medical recommendations based on hybrid matrix factorization. Futur Gener Comput Syst 66:30–35CrossRefGoogle Scholar
  29. 29.
    Zhu Y (2010) Segmentation of the left ventricle from cardiac mr images using a subject-specific dynamical model. IEEE Trans Med Imaging 29(3):669–687CrossRefGoogle Scholar
  30. 30.
    Zhu M, Zhang W, Qu Q, Li M, Gao L (2015) A segmentation method of left ventricle in cardiac magnetic resonance images based on improved snake model. Sichuan Daxue Xuebao 47(2):82–88Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  1. 1.School of Information and Safety EngineeringZhongnan University of Economics and LawWuhanChina
  2. 2.Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis & TreatmentWuhanChina
  3. 3.College of Computer ScienceSouth-Central University for NationalitiesWuhanChina
  4. 4.Faculty of Science, Engineering and building environmentDeakin UniversityMelbourneAustralia
  5. 5.The Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), Department of Electronic and Electrical EngineeringThe University of SheffieldSheffieldUK
  6. 6.School of Biomedical EngineeringSouth-Central University for NationalitiesWuhanChina

Personalised recommendations