access icon free Cardiac image segmentation by random walks with dynamic shape constraint

The quantitative analysis of the left ventricle (LV) contractile function is one of the key steps in the assessment of cardiovascular disease. Such analysis greatly depends on the accurate delineation of LV boundary from cardiac sequences. However, segmentation of the LV still remains a challenging problem due to its subtle boundary, occlusion, and image inhomogeneity. To overcome such difficulties, the authors propose a novel segmentation method by incorporating a dynamic shape constraint into the weighting function of the random walks segmentation algorithm. This approach involves iterative updates on the intermediate result to achieve the desired solution. The inclusion of a shape constraint restricts the solution space of the segmentation result to handle misleading information that may come from noise, weak boundaries and clutter, leading to increased robustness of the algorithm. The authors describe the details of the proposed method and demonstrate its effectiveness in segmenting the LV from real cardiac magnetic resonance (CMR) image sets. The experimental results demonstrate that the proposed method obtains better segmentation performance than the standard method.

Inspec keywords: cardiovascular system; image segmentation; biomedical MRI; medical image processing; random processes; iterative methods; image sequences; diseases

Other keywords: cardiac magnetic resonance image; dynamic shape constraint; left ventricle contractile function; image inhomogeneity; shape constraint; weighting function; iterative approach; cardiovascular disease; cardiac sequences; cardiac image segmentation; random walks

Subjects: Medical magnetic resonance imaging and spectroscopy; Other topics in statistics; Computer vision and image processing techniques; Probability theory, stochastic processes, and statistics; Other topics in statistics; Optical, image and video signal processing; Interpolation and function approximation (numerical analysis); Biology and medical computing; Numerical approximation and analysis; Interpolation and function approximation (numerical analysis); Patient diagnostic methods and instrumentation; Biomedical magnetic resonance imaging and spectroscopy

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
    5. 5)
      • 41. Lu, Y., Radau, P., Connelly, K., et al: ‘Automatic image-driven segmentation of left ventricle in cardiac cine MRI’. MICCAI 2009 Workshop on Cardiac MR Left Ventricle Segmentation Challenge, MIDAS Journal, 2009. Available at http://hdl.handle.net/10380/3109.
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
    11. 11)
      • 22. Cui, H., Wang, X., Fulham, M., et al: ‘Prior knowledge enhanced random walk for lung tumor segmentation from low-contrast CT images’. Proc. of EMBS 2013, 2013, pp. 60716074.
    12. 12)
      • 18. Mahapatra, D., Sun, Y.: ‘Orientation histograms as shape priors for left ventricle segmentation using graph cuts’. Proc. of MICCAI 2011, 2011, vol. 6893, pp. 420427.
    13. 13)
    14. 14)
    15. 15)
    16. 16)
      • 30. Grady, L.: ‘Random walks MATLAB implementation source codes’. Available at: http://cns.bu.edu/~lgrady/software.
    17. 17)
    18. 18)
    19. 19)
      • 29. Yang, X., Yeo, S.Y., Lim, C., et al: ‘A framework for auto-segmentation of left ventricle from magnetic resonance images’. Proc. of APCOM&ISCM 2013, 2013, Available at: http://www.sci-en-tech.com/apcom2013/APCOM2013-Proceedings/PDF_FullPaper/1121_XuleiYang.pdf.
    20. 20)
    21. 21)
      • 28. Yang, X., Su, Y., Wan, M., et al: ‘Left ventricle segmentation by dynamic shape constrained random walks’. Proc. of EMBS 2014, 2014, pp. 47234726.
    22. 22)
    23. 23)
      • 42. Huang, S., Liu, J., Lee, L.C., et al: ‘Segmentation of the left ventricle from cine MR images using a comprehensive approach’. MICCAI 2009 Workshop on Cardiac MR Left Ventricle Segmentation Challenge, MIDAS Journal, 2009. Available at http://hdl.handle.net/10380/3121.
    24. 24)
      • 34. Constantinides, C., Roullot, E., Lefort, M., et al: ‘Fully automated segmentation of the left ventricle applied to cine MR images: description and results on a database of 45 subjects’. Proc. of EMBS 2012, 2012, pp. 32073210.
    25. 25)
    26. 26)
      • 35. Uzunbas, M., Zhang, S., Pohl, K., et al: ‘Segmentation of myocardium using deformable regions and graph cuts’. Proc. of ISBI 2012, 2012, pp. 254257.
    27. 27)
    28. 28)
    29. 29)
    30. 30)
      • 20. Baudin, P.Y., Azzabou, N., Carlier, P.G., et al: ‘Prior knowledge, random walks and human skeletal muscle segmentation’. Proc. of MICCAI 2012, 2012, vol. 7510, pp. 569576.
    31. 31)
    32. 32)
      • 39. Jolly, M.P.: ‘Fully automatic left ventricle segmentation in cardiac cine MR images using registration and minimum surfaces’. MICCAI 2009 Workshop on Cardiac MR Left Ventricle Segmentation Challenge, MIDAS Journal, 2009. Available at http://hdl.handle.net/10380/3114.
    33. 33)
      • 13. Dakua, S.P., Sahambi, J.S.: ‘Modified active contour model and random walk approach for left ventricular cardiac MR image segmentation’, Int. J. Numerical Methods Biomed. Eng., 2011, 27, (9), pp. 13501361.
    34. 34)
      • 27. Radau, P., Lu, Y., Connelly, K., et al: ‘Evaluation framework for algorithms segmenting short axis cardiac MRI’. MICCAI 2009 Workshop on Cardiac MR Left Ventricle Segmentation Challenge, MIDAS Journal, 2009. Available at: http://smial.sri.utoronto.ca/lv_challenge/home.html.
    35. 35)
    36. 36)
      • 21. Baudin, P.Y., Azzabou, N., Carlier, P.G., et al: ‘Manifold-enhanced segmentation through random walks on linear subspace priors’. Proc. of BMVC 2012, 2012, pp. 110.
    37. 37)
    38. 38)
      • 40. Wijnhout, J., Hendriksen, D., Van Assen, H., et al: ‘LV challenge LKEB contribution: fully automated myocardial contour detection’. MICCAI 2009 Workshop on Cardiac MR Left Ventricle Segmentation Challenge, MIDAS Journal, 2009. Available at http://hdl.handle.net/10380/3115.
    39. 39)
    40. 40)
    41. 41)
    42. 42)
    43. 43)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0450
Loading

Related content

content/journals/10.1049/iet-cvi.2014.0450
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading