Advertisement

Segmentation and Blood Flow Simulations of Patient-Specific Heart Data

  • Dimitris MetaxasEmail author
  • Scott Kulp
  • Mingchen Gao
  • Shaoting Zhang
  • Zhen Qian
  • Leon Axel
Chapter

Abstract

In this chapter, we present a fully automatic and accurate segmentation framework for 2D cardiac tagged MR images, a semiautomatic method for 3D segmentation from CT data, and the results of blood flow simulation using these highly detailed models. The 2D segmentation system consists of a semiautomatic segmentation framework to obtain the training contours, and a learning-based framework that is trained by the semiautomatic results, and achieves fully automatic and accurate segmentation.

We then present a method to simulate and visualize blood flow through the human heart, using the reconstructed 4D motion of the endocardial surface of the left ventricle as boundary conditions. The reconstruction captures the motion of the full 3D surfaces of the complex features, such as the papillary muscles and the ventricular trabeculae. We use visualizations of the flow field to view the interactions between the blood and the trabeculae in far more detail than has been achieved previously, which promises to give a better understanding of cardiac flow. Finally, we use our simulation results to compare the blood flow within one healthy heart and two diseased hearts.

Keywords

Patient specific simulation Magnetic resonance images Image segmentation Hemodynamic Heart flow Flow visualization Metamorphs segmentation Shape model Adaboost learning Deformable model Valves deformation Heart disease Ejection fraction 

References

  1. 1.
    Amini AA, Chen Y, Elayyadi M, Radeva P (2001) Tag surface reconstruction and tracking of myocardial beads from SPAMM-MRI with parametric b-spline surfaces. IEEE Trans Med Imaging 20(2):94–103CrossRefGoogle Scholar
  2. 2.
    Cootes T, Taylor C, Cooper D, Graham J (1995) Active shape models - their training and application. Comput Vis Image Underst 61(1):38–59CrossRefGoogle Scholar
  3. 3.
    Daugman J (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A 2(7): 1160–1169CrossRefGoogle Scholar
  4. 4.
    de Zélicourt D, Ge L, Wang C, Sotiropoulos F, Gilmanov A, Yoganathan A (2009) Flow simulations in arbitrarily complex cardiovascular anatomies - an unstructured cartesian grid approach. Comput Fluids 38(9):1749–1762CrossRefzbMATHGoogle Scholar
  5. 5.
    Dunn D, Higgins WE, Wakeley J (1994) Texture segmentation using 2-d Gabor elementary functions. IEEE Trans Pattern Anal Mach Intell 16:130–149CrossRefGoogle Scholar
  6. 6.
    Foster N, Metaxas D (1996) Realistic animation of liquids. Graph Models Image Process 58:471–483CrossRefGoogle Scholar
  7. 7.
    Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: EuroCOLT ’95: proceedings of the second European conference on computational learning theory, pp 23–37Google Scholar
  8. 8.
    Gilmanov A, Sotiropoulos F (2005) A hybrid cartesian/immersed boundary method for simulating flows with 3D, geometrically complex, moving bodies. J Comput Phys 207(2): 457–492CrossRefzbMATHGoogle Scholar
  9. 9.
    Ginneken BV, Frangi AF, Staal JJ et al (2002) Active shape model segmentation with optimal features. IEEE Trans Med Imaging 21(8):924–933CrossRefGoogle Scholar
  10. 10.
    Huang X, Paragios N, Metaxas D (2003) Establishing local correspondences towards compact representations of anatomical structures. In: Proceedings of international conference on medical imaging computing and computer-assisted intervention. Lecture notes in computer science, vol 2879, pp 926–934Google Scholar
  11. 11.
    Huang X, Li Z, Metaxas DN (2004) Learning coupled prior shape and appearance models for segmentation. In: Medical image computing and computer-assisted intervention - MICCAI (1), pp 60–69Google Scholar
  12. 12.
    Huang X, Metaxas D, Chen T (2004) Metamorphs: deformable shape and texture models. In: IEEE conference on computer vision and pattern recognition, vol 1, pp 496–503Google Scholar
  13. 13.
    Jiao F, Li S, Shum H, Schuurmans D (2003) Face alignment using statistical models and wavelet features. In: IEEE conference on CVPR, vol 1, pp 321–327Google Scholar
  14. 14.
    Jones T, Jones TN, Metaxas DN (1998) Patient-specific analysis of left ventricular blood flow. In: Medical image computing and computer-assisted intervention (MICCAI), pp 156–166Google Scholar
  15. 15.
    Kulp S, Metaxes D, Qian Z, Voros S, Axel L, Mihalef V (2011) Patient-specific modeling and visualization of blood flow through the heart. In: IEEE international symposium on biomedical imagingGoogle Scholar
  16. 16.
    Li S, Zhu L, Jiang T (2004) Active shape model segmentation using local edge structures and Adaboost. In: Medical imaging augmented reality, pp 121–128Google Scholar
  17. 17.
    Long Q, Merrifield R, Yang GZ, Xu XY, Kilner PJ, Firmin DN (2003) The influence of inflow boundary conditions on intra left ventricle flow predictions. J Biomech Eng 125(6):922–927CrossRefGoogle Scholar
  18. 18.
    Manglik T, Axel L, Pai W, Kim D, Dugal P, Montillo A, Qian Z (2004) Use of bandpass Gabor filters for enhancing blood-myocardium contrast and filling-in tags in tagged MR images. In: Proceedings of international society for magnetic resonance in medicine, p 1793Google Scholar
  19. 19.
    Mihalef V, Metaxas D, Sussman M (2007) Textured liquids based on the marker level set. Comput Graph Forum 26(3):457–466CrossRefGoogle Scholar
  20. 20.
    Mihalef V, Ionasec R, Wang Y, Zheng Y, Georgescu B, Comaniciu D (2010) Patient-specific modeling of left heart anatomy, dynamics and hemodynamics from high resolution 4D CT. In: IEEE international symposium on biomedical imaging, pp 504–507Google Scholar
  21. 21.
    Montillo A, Metaxas D, Axel L (2002) Automated segmentation of the left and right ventricles in 4d cardiac SPAMM images. In: Medical imaging computing and computer-assisted intervention, pp 620–633Google Scholar
  22. 22.
    Paraview - Open Source Scientific Visualization. http://www.paraview.org
  23. 23.
    Saber NR, Wood NB, Gosman AD, Merrifield RD, Yang G-Z, Charrier CL, Gatehouse PD, Firmin DN (2003) Progress towards patient-specific computational flow modeling of the left heart via combination of magnetic resonance imaging with computational fluid dynamics. Ann Biomed Eng 31:42–52CrossRefGoogle Scholar
  24. 24.
    Schapire RE (2002) The boosting approach to machine learning: an overview. In: MSRI workshop on nonlinear estimation and classificationGoogle Scholar
  25. 25.
    Schapire RE, Freund Y, Bartlett P, Lee WS (1998) Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat 26(5):1651–1686MathSciNetCrossRefzbMATHGoogle Scholar
  26. 26.
    Sederberg TW, Parry SR (1986) Free-form deformation of solid geometric models. In: Proceedings of the 13th annual conference on computer graphics, pp 151–160Google Scholar
  27. 27.
    Shen D, Davatzikos C (2000) Adaptive-focus statistical shape model for segmentation of 3D MR structures. In: Medical image computing and computer assisted intervention, pp 206–215Google Scholar
  28. 28.
    Shen T, Li H, Qian Z, Huang X (2009) Active volume models for 3d medical image segmentation. In: IEEE conference on computer vision and pattern recognition, pp 707–714Google Scholar
  29. 29.
    Sussman M (2005) A parallelized, adaptive algorithm for multiphase flows in general geometries. Comput Struct 83(6–7):435–444CrossRefGoogle Scholar
  30. 30.
    Viola P, Jones M (2001) Robust real-time object detection. In: Second international workshop on statistical and computational theories of vision - modeling, learning, and sampling, Vancouver, 13 July 2001Google Scholar
  31. 31.
    Yokoi K, Xiao F, Liu H, Fukasaku K (2005) Three-dimensional numerical simulation of flows with complex geometries in a regular cartesian grid and its application to blood flow in cerebral artery with multiple aneurysms. J Comput Phys 202(1):1–19MathSciNetCrossRefzbMATHGoogle Scholar
  32. 32.
    Zhu S, Lee T, Yuille A (1995) Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation. In: International conference on computer vision, June 1995, pp 416–423CrossRefGoogle Scholar

Copyright information

© Springer New York 2014

Authors and Affiliations

  • Dimitris Metaxas
    • 1
    Email author
  • Scott Kulp
    • 1
  • Mingchen Gao
    • 1
  • Shaoting Zhang
    • 1
  • Zhen Qian
    • 2
  • Leon Axel
    • 3
  1. 1.CBIM, Rutgers UniversityNew BrunswickUSA
  2. 2.Piedmont Heart InstituteAtlantaUSA
  3. 3.NYU School of MedicineNew YorkUSA

Personalised recommendations