Skip to main content
SpringerLink
Log in

Two-stage active contour model for robust left ventricle segmentation in cardiac MRI

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Segmentation of the endocardial and epicardial boundaries on 3D cardiac magnetic resonance images plays a vital role in the assessment of ejection fraction, wall thickness, end-diastolic volume, end-systolic volume, and stroke volume. Accurate segmentation is significantly challenged by intensity inhomogeneity artifacts, low contrast, and ill-defined organ/region boundaries. We propose a two stage hybrid active contour model for robust left ventricle (LV) segmentation accompanied with a new initialization technique based on prior of the LV structure. The proposed approach includes a new level set method using local, spatially-varying, statistical model for image intensity, an edge-based term to capture region boundaries, and regularization functionals for smooth evolution of the segmenting curve and to avoid expensive reinitialization. Moreover, convex hull interpolation is employed to include the papillary muscles within the endocardial boundary for a refined depiction of LV geometry. The accuracy and robustness of the proposed algorithm were assessed using York, Sunnybrook and ACDC datasets (33 + 45 + 100 subjects), with a wide spectrum of normal hearts, congenital heart diseases, and cardiac dysfunction. Experiments showed that the proposed approach significantly outperformed other active contour methods (overall Dice score 0.90), generating accurate segmentations of left ventricular outflow tract (Dice score 0.91), apical slices (Dice score 0.82), systolic and diastolic phases (Dice scores 0.92 and 0.88 respectively). The percentage of good contours was about 92% and the average perpendicular distance was less than 1.8 mm. Automatically generated segmentation yielded superior estimates of ejection fraction with an R2 ≥ 0.937. Furthermore, the proposed method was validated using 100 cine MRI cases consisting of five different cardiac classes from the ACDC MICCAI 2017 challenge. The proposed algorithm yielded superior segmentation performance compared with existing active contour models and other state-of-the-art cardiac segmentation techniques, with extensive validation on three standard cardiac datasets, with different cardiac pathologies and phases.

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

Access this article

Log in via an institution

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
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Aditya J, Tandri H, Calkins H, Bluemke DA (2008) Role of cardiovascular magnetic resonance imaging in arrhythmogenic right ventricular dysplasia. J Cardiovasc Magnetic Resonance 10(1):32

    Article  Google Scholar 

  2. Aganj I, Harisinghani M, Weissleder R, Fischl B (2018) Unsupervised Medical Image Segmentation Based on the Local Center of Mass. Scientific Reports 8(1):13012

    Article  Google Scholar 

  3. Andreopoulos A, Tsotsos JK (2008) Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Med Image Anal 12(3):335–357

    Article  Google Scholar 

  4. Avendi MR, Kherdavar 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 30:108–119

    Article  Google Scholar 

  5. Barba L, Escalante-Ramírez B, Vallejo Venegas E (2017) A 3D Hermite-based multiscale local active contour method with elliptical shape constraints for segmentation of cardiac MR and CT volumes. Medical Biol Eng Comput 56(5):833–851

    Article  Google Scholar 

  6. Bernard O, Lalande A, Zotti C (2018) Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved ? IEEE Trans Med Imaging 37:2514–2525

    Article  Google Scholar 

  7. Bomma C, Dalal D, Tandri H, Prakasa K (2005) Regional differences in systolic and diastolic function in Arrhythmogenic right ventricular dysplasia/cardiomyopathy using magnetic resonance imaging. Am J Cardiol 95(12):1507–1511

    Article  Google Scholar 

  8. Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22:61–79

    Article  MATH  Google Scholar 

  9. Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277

    Article  MATH  Google Scholar 

  10. Chang P-L, Teng W-G (2007) "exploiting the self-organizing map for medical image segmentation," in 20th IEEE Symposium on Computer based Medical Systems. Maribor, Slovenia

  11. Codella N, Cham M, Wong R, Chu C, Min J, Prince M (2010) Rapid and accurate left ventricular chamber quantification using a novel CMR segmentation algorithm: a clinical validation study. J Magn Reson Imaging 31(4):845–853

    Article  Google Scholar 

  12. Contantinides C, Chenoune Y, Kachenoura N (2009) Semi-automated cardiac segmentation on cine magnetic resonance images using GVF-Snake deformable models. MIDAS J. Card. MR Left Ventricle Segmentation Challenge

  13. Dweck MR, Williams MC, Moss AJ, Newby DE, Fayad ZA (2016) CT and CMR in ischemic heart disease. J Am Coll Cardiol 68(20):2201–2216

    Article  Google Scholar 

  14. Fedkiw S, Osher R (2003) Level Set Methods and, New York: Cambridge Univ. Press

  15. Franco M, Preparata P ( 1985) convex hulls: basic algorithms," in Computational Geometry, Springer

  16. Grosgeorge D, Petitgean C, Caudron J, Fares J, Dacher J (2010) Automatic cardiac ventricle segmentation in MR images: a validation study. Int J Comput Assist Radiol Surg 6(5):573–581

    Article  Google Scholar 

  17. Hajiaghayi M, Groves EM, Eng M, Jafarkhani H, Kheradvar A (2017) A 3D active contour method for automated segmentation of the left ventricle from magnetic resonance images. IEEE Trans Biomed Eng 64:134–144

    Article  Google Scholar 

  18. Hazirolan T, Tasbas B, Dağoğlu M, Canyiğit M, Abali G, Aytemir K, Oto A, Balkanci F (2007) Comparison of short and long axis methods in cardiac MR imaging and echocardiography for left ventricular function. Diagn Interv Radiol 13(1):33–38

    Google Scholar 

  19. Hu H, Gao Z, Liu L, Liu H, Gao J, Xu S, Li W, Huang L (2014) Automatic Segmentation of the Left Ventricle in Cardiac MRI Using Local Binary Fitting Model and Dynamic Programming Techniques. PLOS One 9(12)

  20. Hu H, Gao Z, Liu L, Liu H, Gao J, Xu S, Li W, Huang L (2014) Automatic Segmentation of the Left Ventricle in Cardiac MRI Using Local Binary Fitting Model and Dynamic Programming Techniques. PLOS One 9(12)

  21. Huang S, Liu J, Venkatesh S, Teo L, Au C (2011) An image based comprehensive approach for automatic segmentation of left ventricle from cardiac short axis cine MR images. J Digit Imag 24:598–608

    Article  Google Scholar 

  22. Khamechian MB, Saadatmand M (2018) FoCA: a new framework of coupled geometric active contours for segmentation of 3D cardiac magnetic resonance images. Magn Reson Imaging 51:51–60

    Article  Google Scholar 

  23. Lankton S, Tannenbaum A (2008) Localizing region-based active contours. IEEE Trans Image Process 17:2029–2039

    Article  MathSciNet  MATH  Google Scholar 

  24. Lankton S, Tannenbaum A (2008) Localizing Region-Based Active Contours," IEEE Transactions on Image Processing, vol. 17

  25. Li C, Xu C, Gui C, Fox M (2005) "level set evolution without re-initialization: a new Variational formulation," in CVPR'05

  26. Li C, Kao CY, Gore JC, Ding Z (2007) "implicit active contours driven by local binary fitting energy," in IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN

  27. Li B, Liu Y, Occleshaw CJ, Cowan BR, Young A (2010) In-line automated tracking for ventricular function with magnetic resonance imaging. JACC Cardiovasc Imag 3:860–866

    Article  Google Scholar 

  28. Liu H, Hu H, Xu X, Song E (2012) Automatic left ventricle segmentation in cardiac MRI using topological stable-state thresholding and region restricted dynammic pogramming. Acad Radiol 19:723–731

    Article  Google Scholar 

  29. Liu T, Xu H, Jin W, Liu Z, Zhao Y, Tian AW ( 2014) Medical Image Segmentation Based on a Hybrid Region-Based Active Contour Model. Computational and Mathematical Methods Med

  30. Luijnenburg SE, Robbers-Visser D, Moelker A, Vliegen HW, Mulder BJM, Helbing WA (2009) Intra-observer and interobserver variability of biventricular function, volumes and mass in patients with congenital heart disease measured by CMR imaging. Int J Cardiovasc Imaging 26(1):57–64

    Article  Google Scholar 

  31. Margeta J, Geremia E, Criminisi A (2011) layered Spatio-temporal forests for left ventricle segmentation from 4D cardiac MRI data," in Lecture Notes in Computer Science

  32. Meng X, Gu W, Yungie C, Jianwei Z (2017) Brain MR image segmentation based on an improved active contour mode. PLOS One 12(8):e0183943

    Article  Google Scholar 

  33. Mohammad-Bagher Khamechian MS-T (2018) FoCA: a new framework of coupled geometric active contours for segmentation of 3D cardiac magnetic resonance images. Magn Reson Imaging 51:51–60

    Article  Google Scholar 

  34. Nambakhsh C, Yuan M, Punithakumar K, Goelaa A (2013) Left ventricle segmentation in MRI via convex relaxed distribution matching. Med Image Anal 17:1010–1024

    Article  Google Scholar 

  35. Nameirakpam D, Khumanthem M, Jina C (2015) Image segmentation using K -means clustering algorithm and subtractive clustering algorithm. Procedia Comput Sci 54:764–771

    Article  Google Scholar 

  36. Nasr M, Mohrekesh M, Akbari M, Soroushmehr S (2018) Left ventricle segmentation in cardiac mr images using fully convolutional network, ArXiv Preprint:ArXiv:1802.07778

  37. Navab N, Navab N, Ahmadi S-A (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation," in Computer Vision and Pattern Recognition

  38. Neill C, Thompson W, Spevak P (2009) Critical heart disease in infants and children. Mosby

  39. Ngo TGC (2013) Left ventricle segmentation from cardiac MRI combining level set methods with deep belief networks.," in IEEE International Conference on Image Processing

  40. Noureldin R, Liu S, Nacif M, Judge D, Halushka M, Abraham T (2012) The diagnosis of hypertrophic cardiomyopathy by cardiovascular magnetic resonance. J Cardiovasc Magnetic Resonance 14(1):17

    Article  Google Scholar 

  41. Papernot N, McDaniel P, Jha S, Fredrickson M, Berkay ZC, Swami A (2016) "the limitations of deep learning in adversarial settings," in 2016 IEEE European Symposium on Security and Privacy. Saarbrucken, Germany

  42. Peng P, Lekadir K, Gooya A, Shao L, Petersen S, Frangi A (2016) A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. MAGMA 29(2):155–195

    Article  Google Scholar 

  43. Peterzan MA, Rider OJ, Lisa AJ (2016) The role of cardiovascular magnetic resonance imaging in heart failure. Cardiac Failure Rev:115–122

  44. Piazzese C, Carminati C, Krause A, Potse M (2016) Segmentation of the left ventricular endocardium from magnetic resonance images by using different statistical shape models. J Cardiol 49(3):383–391

    Google Scholar 

  45. Pluempitiwirijawej C, Moura J, Wu J, Ho C (2005) STACS: new active contour scheme for cardiac MR image. Med Imaging, IEEE Trans 24

  46. Queirós S, Barbosa D, Heyde B, Morais P (2014) Fast automatic myocardial segmentation in 4D cine CMR datasets. Med Image Anal 18:1115–1131

    Article  Google Scholar 

  47. Radau P, Lu Y, Connelly K, Paul G, Dick A and G. Wright (2009) Evaluation Framework for Algorithms Segmenting Short Axis Cardiac MRI," The MIDAS Journal-Cardiac MR Left Ventricle Segmentation Challenge., vol. 49

  48. Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation," in International Conference on Medical Image Computing and Computer-Assisted Intervention

  49. Sakuma H (2007) Magnetic resonance imaging for ischemic heart. J Magn Reson Imaging 26(1):3–13

    Article  MathSciNet  Google Scholar 

  50. Santiago JCNJSMC (2017) Fast segmentation of the left ventricle in cardiac MRI using dynamic programming. Comput Methods Prog Biomed 154:9–23

    Article  Google Scholar 

  51. Sardanelli F, Quarenghi M, Di Leo DrSci G, Boccacini L (2008) Segmentation of cardiac cine MR images of left and right ventricles: interactive semiautomated methods and manual contouring by two readers with different education and experience. J Magnetic Resonance Imaging (JMRI) 27(4):785–792

    Article  Google Scholar 

  52. Shahzad R, Gao S, et al (2017) Automated Cardiovascular Segmentation inPatients with Congenital Heart Disease from 3D CMR Scans: Combining Multi-atlases and Level-Sets," in Lecture Notes in Computer Science

  53. Song Y, Peng G (2019) A fast two-stage active contour model for intensity inhomogeneous image segmentation. Plos One

  54. Soomro S, Munir A, Choi KN (2018) Hybrid two-stage active contour method with region and edge information for intensity inhomogeneous image segmentation. PLOS One 13(1):e0191827

    Article  Google Scholar 

  55. Tian Y, Duan F, Zhou M (2013) Active contour model combining region and edge information. Mach Vis Appl 24:47–61

    Article  Google Scholar 

  56. Tobias OJ, Seara R (2002) Image segmentation by histogram thresholding using fuzzy sets. IEEE Trans Image Process 11(12):1457–1465

    Article  Google Scholar 

  57. Tran PV (2017) A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI, https://arxiv.org/abs/1604.00494

  58. Tseng W, Marine M, Tseng Y (2016) Introduction to cardiovascular magnetic resonance: technical principles and clinical applications. Acta Cardiologica Sinica 32(2):129–144

    Google Scholar 

  59. Uznabus M, Zhang M, Pohl P, Metaxas K, Axel D (2012) Segmentation of myocardium using deformable regions and graph cuts. IEEE Int Symp Biomed Imaging:254–257

  60. Wang L, He L, Mishra A, Li C (2009) Active contours driven by local Gaussian distribution fitting energy. Signal Process 89:2435–2447

    Article  MATH  Google Scholar 

  61. Wang T, Han B, Collomosse J (2014) TouchCut: fast image and video segmentation using single-touch interaction. Comput Vis Image Underst 120:14–30

    Article  Google Scholar 

  62. Wang H, Huang T, Xu Z, Wang Y (2016) A two-stage image segmentation via global and local region active contours. Neurocomputing 205:130–140

    Article  Google Scholar 

  63. y. Gao R, Sanghu GF, Tannenbaum A (2010) A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE Trans Med Imaging 29(10):1781–1794

    Article  Google Scholar 

  64. Yu H, He F, Pan Y (2018) A novel region-based active contour model via local patch similarity measure for image segmentation. Multimed Tools Appl 77:24097–24119

    Article  Google Scholar 

  65. Zhang K, Zhang L, Lam K-M, Zhang D (2016) A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans Cybernet 46(2):546–557

    Article  Google Scholar 

  66. Zheng Q, Delingette H, Duchateau N, Ayache N (2018) 3D consistent & robust segmentation of cardiac images by deep learning with spatial propagation. IEEE Trans Med Imaging 37(9):2137–2148

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by fellowship, awarded by National University of Computer and Emerging Sciences, Lahore. We are grateful to [8, 9, 17, 23, 60] for sharing their codes.

Author information

Authors and Affiliations

  1. Department of Computer Science, National University of Computer and Emerging Sciences, Lahore, Pakistan

    Maria Tamoor & Irfan Younas

  2. Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering, LUMS, Lahore, 54792, Pakistan

    Hassan Mohy-ud-Din

Authors
  1. Maria Tamoor
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Irfan Younas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hassan Mohy-ud-Din
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hassan Mohy-ud-Din.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Hassan Mohy-ud-Din Member, IEEE

Supplementary Information

ESM 1

(DOCX 1046 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tamoor, M., Younas, I. & Mohy-ud-Din, H. Two-stage active contour model for robust left ventricle segmentation in cardiac MRI. Multimed Tools Appl 80, 32245–32271 (2021). https://doi.org/10.1007/s11042-021-11155-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11155-w

Keywords

Search

Navigation