Analysis of Myocardial Ischemia from Cardiac Magnetic Resonance Images Using Adaptive Fuzzy-Based Multiphase Level Set

  • M. Muthulakshmi
  • G. Kavitha
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)


In this research work, cardiac magnetic resonance (CMR) images are analyzed to study the pathophysiology of myocardial ischemia (MI). It is a cardiac disorder that causes irreversible damage to heart muscles. The images considered for this study are obtained from medical image computing and computer-assisted intervention (MICCAI) database. Adaptive fuzzy-based multiphase level set method is utilized to extract endocardium and epicardium of left ventricle from short-axis view of CMR images. The segmentation results are validated with similarity measures such as Dice coefficient and Jaccard index. Further, five indices are derived from the segmentation results. The obtained results provide average Dice coefficient for endocardium and epicardium as 0.867 and 0.918, respectively. The mean Jaccard index for epicardium and endocardium is 0.855 and 0.766, respectively. It is observed that the proposed method segments the left ventricle more precisely from CMR images. The ischemic subjects show a reduced mean ejection fraction (32.52) compared to the normal subjects (59.04). The average stroke volume is found to be 70.16 and 64.05 ml for healthy subjects and ischemic subjects, respectively. Reduction in stroke volume and ejection fraction for ischemic subjects indicates lower quantity of blood drained by heart. It is also observed that there is an increase in myocardial mass for ischemic subjects (182.11 g) compared to healthy subjects (127.47 g). The thickened heart muscle contributes to the increased myocardial mass in abnormal subjects. Further, ischemic subjects show an increase in endocardium volume at end-diastolic and end-systolic phase when compared to normal subjects. Thus, the clinical indices evaluated from adaptive fuzzy-based multiphase level set method could differentiate the normal and ischemic subjects. Hence, this study can be a useful supplement in diagnosis of myocardial ischemic disorder.


Ischemia Cardiac magnetic resonance images Multiphase level set Adaptive fuzzy Left ventricle 


  1. 1.
    Radico F, Cicchitti V, Zimarino M, Caterina RD (2014) Angina pectoris and myocardial ischemia in the absence of obstructive coronary artery disease: practical considerations for diagnostic tests CME. J Am Coll Cardiol Interv 7:453–463CrossRefGoogle Scholar
  2. 2.
    Detry J-MR (1996) The pathophysiology of myocardial ischaemia. Eur Heart J 17:48–52CrossRefGoogle Scholar
  3. 3.
    Miller CA, Pearce K, Jordan P, Argyle R, Clark D, Stout M, Ray S, Schmitt M (2012) Comparison of real-time three-dimensional echocardiography with cardio-vascular magnetic resonance for left ventricular volumetric assessment in unselected patients. Eur Heart J Cardiovasc Imaging 13:187–195CrossRefGoogle Scholar
  4. 4.
    Constantinides C, Chenoune Y, Kachenoura N, Roullot E, Mousseaux E, Herment A, Frouin F (2009) Semi-automated cardiac segmentation on cine magnetic resonance images using GVF-Snake deformable models. MIDAS J.
  5. 5.
    Marsousi M, Eftekhari A, Kocharian A, Alirezaie J (2010) Endocardial boundary extraction in left ventricular echocardiographic images using fast and adaptive B-spline snake algorithm. Int J Comput Assist Radiol Surg 5:501–513CrossRefGoogle Scholar
  6. 6.
    Pednekar A et al (2006) Automated left ventricular segmentation in cardiac MRI. IEEE Trans Biomed Eng 53:1425–1428CrossRefGoogle Scholar
  7. 7.
    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 30:108–119CrossRefGoogle Scholar
  8. 8.
    Zhuang X, Shen J (2016) Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Med Image Anal 31:77–87CrossRefGoogle Scholar
  9. 9.
    Ordas S, Oubel E, Leta R, Carreras F, Frangi AF (2007) A statistical shape model of the whole heart and its application to model-based segmentation. In: Proceedings for SPIE medical imaging, vol 6511Google Scholar
  10. 10.
    Petitjean C, Dacher J (2011) A review of segmentation methods in short axis cardiac MR images. Med Image Anal 15:169–184CrossRefGoogle Scholar
  11. 11.
    Lynch M, Ghita O, Whelan PF (2006) Left-ventricle myocardium segmentation using a coupled level-set with a priori knowledge. Comput Med Imag Graph 30:255–262CrossRefGoogle Scholar
  12. 12.
    Pham V-T, Tran T-T (2016) Active contour model and nonlinear shape priors with application to left ventricle segmentation in cardiac MR images. Opt-Int J Light Electron Opt 127:991–1002CrossRefGoogle Scholar
  13. 13.
    Li C et al (2008) A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity. Med Image Comput Comput Assist Interv 11:1083–1091Google Scholar
  14. 14.
    Zhang S, Limy C (2015) Distance regularized two level sets for segmentation of left and right ventricles from cine-MRI. Magn Reson Imag 34:699–706Google Scholar
  15. 15.
    Bevilacqua M, Dharmakumar R, Tsaftaris SA (2016) Dictionary-driven ischemia detection from cardiac phase-resolved myocardial BOLD MRI at rest. IEEE Trans Med Imag 35:282–293CrossRefGoogle Scholar
  16. 16.
    Huang QH et al (2012) A robust graph-based segmentation method for breast tumors in ultrasound images. Ultrasonics 52:266–275CrossRefGoogle Scholar
  17. 17.
    Bhadauria HS, Singh A, Dewal ML (2013) An integrated method for hemorrhage segmentation from brain CT imaging. Comput Electr Eng 39:1527–1536CrossRefGoogle Scholar
  18. 18.
    Elazab A et al (2015) Segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy C-means clustering. Comput Math Methods Med 2015(2015):1–12 (485495)Google Scholar
  19. 19.
    Radau P, Lu Y, Connelly K, Paul G, Dick AJ, Wright GA (2009) Evaluation framework for algorithms segmenting short axis cardiac MRI. MIDAS J Card MR Left Ventricle Segmentation Challenge.

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Electronics EngineeringMIT Campus, Anna UniversityChennaiIndia

Personalised recommendations