Statistical deformable models for cardiac Segmentation and Functional Analysis In Gated-Spect Studies

  • Catalina Tobon-Gomez
  • S. Ordas
  • A. F. Frangi
  • S. Aguade
  • J. Castell
Part of the Topics in Biomedical Engineering. International Book Series book series (ITBE)

This chapter describes the use of statistical deformable models for cardiac segmentation and functional analysis in Gated Single Positron Emission Computer Tomography (SPECT) perfusion studies. By means of a statistical deformable model, automatic delineations of the endo- and epicardial boundaries of the left ventricle (LV) are obtained, in all temporal phases and image slices of the dynamic study. Apriori spatio-temporal shape knowledge is captured from a training set of high-resolution manual delineations made on cine Magnetic Resonance (MR) studies. From the fitted shape, a truly 3D representation of the left ventricle, a series of functional parameters can be assessed, including LV volume–time curves, ejection fraction, and surface maps of myocardial perfusion, wall motion, thickness, and thickening. We present encouraging results of its application on a patient database that includes rest/rest studies with common cardiac pathologies, suggesting that statistical deformable models may serve as a robust and accurate technique for routine use.


Single Photon Emission Compute Tomography Perfusion Defect Shape Model Color Version Appearance Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Schaefer W, Lipke C, Standke D, Kulh HP, Nowak B, Kaiser HJ, Koch KC, Buell U. 2005. Quantification of left ventricular volumes and ejection fraction from gated 99mTc-MIBI SPECT: MRI validation and comparison of the Emory Cardiac Tool Box with QGS and 4D-MSPECT. J Nucl Med 46(8):1256-1263.Google Scholar
  2. 2.
    Lum DP, Coel MN. 2003. Comparison of automatic quantification software for the measurement of ventricular volume and ejection fraction in gated myocardial perfusion SPECT. Nucl Med Commun 24(4):259-266.CrossRefGoogle Scholar
  3. 3.
    Nakajima K, Higuchi T, Taki J, Kawano M, Tonami N. 2001. Accuracy of ventricular volume and ejection fraction measured by gated myocardial SPECT: comparison of 4 software programs. J Nucl Med 42:1571-1578.Google Scholar
  4. 4.
    Faber TL, Vansant JP, Pettigrew RI, Galt JR, Blais M, Chatzimavroudis G, Cooke CD, Folks RD, Waldrop SM, Gurtler-Krawczynska E, Wittry MD, Garcia E. 2001. Evaluation of left ventricular endocardial volumes and ejection fractions computed from gated perfusion SPECT with magnetic imaging: comparison of two methods. J Nucl Med 40:645-651.Google Scholar
  5. 5.
    Vaduganathan P, He Z, Vick III GW, Mahmarian JJ, Verani MS. 1998. Evaluation of left ventricular wall motion, volumes, and ejection fraction by gated myocardial tomography with technetium 99m-labeled tetrofosmin: a comparison with cine magnetic resonance imaging. J Nucl Cardiol 6:3-10.CrossRefGoogle Scholar
  6. 6.
    Lipke CSA, Kuhl HP, Nowak B, Kaiser HJ, Reinartz P, Koch KC, Buell U, Schaefer WM. 2004. Validation of 4D-MSPECT and QGS for quantification of left ventricular volumes and ejection fraction from gated 99mTc-MIBI SPET: comparison with cardiac magnetic resonance imaging. Eur J Nucl Med Mol Imaging 31(4):482-490.CrossRefGoogle Scholar
  7. 7.
    Tadamura E, Kudoh T, Motooka M, Inubushi M, Okada T, Kubo S, Hattori N, Matsuda T, Koshiji T, Nishimura K, Komeda M, Konishi J. 1999. Use of technetium-99m sestamibi ECG-gated single-photon emission tomography for the evaluation of left ventricular function following coronary artery bypass graft: comparison with threedimensional magnetic resonance imaging. Eur J Nucl Med 26:705-712.CrossRefGoogle Scholar
  8. 8.
    Thorley PJ, Plein S, Bloomer TN, Ridgway JP, Sivananthan UM. 2003. Comparison of 99mtc tetrofosmin gated SPECT measurements of left ventricular volumes and ejection fraction with MRI over a wide range of values. Nucl Med Commun 24:763-769.CrossRefGoogle Scholar
  9. 9.
    Germano G, Kavanagh P, Su H, Mazzati M, Kiat H. 1995. Automatic reorientation of 3-dimensional transaxial myocardial perfusion SPECT images. J Nucl Med 36:1107-1114.Google Scholar
  10. 10.
    Faber T, Cooke C, Folks R, Vansant J, Nichos K, DePuey E, Pettigrew R, Garcia E. 1999. Left ventricular function and perfusion from gated SPECT perfusion images: an intergrated method. J Nucl Med 40:650-659.Google Scholar
  11. 11.
    Akincioglu C, Berman DS, Nishina H, Kavanagh PB, Slomka PJ, Abidov A, Hayes S, Friedman JD, Germano G. 2005. Assessment of diastolic function using 16-frame 99mTc-Sestamibi gated myocardial perfusion SPECT: normal values. J Nucl Med 46:1102-1108.Google Scholar
  12. 12.
    Boyer J, Thanigaraj S, Schechtman K, Perez J. 2004. Prevalence of ventricular diastolic dysfunc-tion in asymtomatic, normotensive patients with diabetes mellitus. Am J Cardiol 93:870-875.CrossRefGoogle Scholar
  13. 13.
    Yuda S, Fang Z. 2003. Association of severe coronary stenosis with subclinical left ventricular dysfunction in the absence of infarction. J Am Soc Echocardiogr 16:1163-1170.CrossRefGoogle Scholar
  14. 14.
    Yamada H, Goh PP, Sun JP, Odabashian J, Garcia MJ, Thomas JD, Klein AL. 2002. Prevalence of left ventricular diastolic dysfunction by doppler echocardiography: clinical application of the canadian consensus guidelines. J Am Soc Echocardiogr 15:1238-1244.CrossRefGoogle Scholar
  15. 15.
    Bayata S, Susam I, Pinar A, Dinckal M, Postaci N, Yesil M. 2000. New doppler echocardio-graphic applications for the evaluation of early alterations in left ventricular diastolic function after coronary angioplasty. Eur J Echocardiogr 1:105-108.CrossRefGoogle Scholar
  16. 16.
    Matsumura Y, Elliott P, Virdee M, Sorajja P, Doi Y, McKenna W. 2002. Left ventricular diastolic function assessed using doppler tissue imaging in patients with hypertrophic cardiomyopathy: relation to symptoms and exercise capacity. Heart 87(4):247-251.CrossRefGoogle Scholar
  17. 17.
    Galderisi M, Cicala S, Caso P, De Simone L, D’Errico A, Petrocelli A, de Divitiis O. 2002. Coronary flow reserve and myocardial diastolic dysfunction in arterial hypertension. Am J Cardiol 90:860-864.CrossRefGoogle Scholar
  18. 18.
    Germano G. 2001. Technical aspects of myocardial SPECT imaging. J Nucl Med 42:1499-1507.Google Scholar
  19. 19.
    Germano G, Berman D. 1999. Quantitative gated perfusion SPECT. In Clinical gated cardiac SPECT, pp. 115-146. Ed G Germano, D. Berman. Armonk, NY: Futura Publishing.Google Scholar
  20. 20.
    Cauvin J, Boire J, Bonny J, Zanca M, Veyre A. 1992. Automatic detection of the left ventricular myocardium long axis and center in thallium-201 single photon emission computed tomography. Eur J Nucl Med 19(21):1032-1037.Google Scholar
  21. 21.
    Germano G, Kiat H, Kavanagh B, Moriel M, Mazzanti M, Su H, Van Train KF, Berman D. 1995. Automatic quantification of ejection fraction from gated myocardial perfusion SPECT. J Nucl Med 36: 2138-2147.Google Scholar
  22. 22.
    Lomsky M, El-Ali H, Astrom K, Ljungberg M, Richter J, Johansson L, Edenbrandt L. 2005. A new automated method for analysis of gated- SPECT images based on a three-dimensional heart shaped model. Clin Physiol Funct Imaging 25(4):234-240.CrossRefGoogle Scholar
  23. 23.
    Frangi AF, Niessen WJ, Viergever MA. 2000. Three-dimensional modeling for functional analysis of cardiac images: a review. IEEE Trans Med Imaging 20(1):2-25.CrossRefGoogle Scholar
  24. 24.
    Cootes TF, Taylor CJ, Cooper DH, Graham J. 1995. Active shape models — their training and application. Comput Vision Image Understand 61(1):38-59.CrossRefGoogle Scholar
  25. 25.
    Kelemen A, Szekely G, Guerig G. 1999. Elastic model-based segmentation of 3D neuroradiolog-ical data sets. IEEE Trans Med Imaging 18:828-839.CrossRefGoogle Scholar
  26. 26.
    McInerney T, Terzopoulos D. 1996. Deformable models in medical image analysis: a survey. Med Image Anal 1(2):91-108.CrossRefGoogle Scholar
  27. 27.
    Montagnat J, Delingette H. 2005. Deformable models with temporal constraints: application to 4D cardiac image segmentation. Med Image Anal 9(1):87-100.CrossRefGoogle Scholar
  28. 28.
    Cootes TF, Edwards GJ, Taylor CJ. 1998. Active appearance models. Proc Eur Conf Comput Vision 2:484-498.Google Scholar
  29. 29.
    Ordas S, Boisrobert L, Bossa M, Laucelli M, Huguet M, Olmos S, Frangi AF. 2004. Grid-enabled automatic construction of a two-chamber cardiac PDM from a large database of dynamic 3D shapes. In Proceedings of the 2004 IEEE international symposium on biomedical imaging, pp. 416-419. Washington, DC: IEEE.Google Scholar
  30. 30.
    Mitchell SC, Bosch JG, Lelieveldt BPF, van der Geest RJ, Reiber JHC, Sonka M. 2002. D active appearance models: segmentation of cardiac MR and ultrasound images. IEEE Trans Med Imaging 21(9):1167-1179.CrossRefGoogle Scholar
  31. 31.
    Stegmann MB. 2004. Generative interpretation of medical images. Phd dissertation, Informatics and Mathematical Modelling, Technical University of Denmark, Lyngby.Google Scholar
  32. 32.
    van Assen HC, Danilouchkine MG, Frangi AF, Ordas S, Westenberg JJM, Reiber JHC, Lelieveldt BPF. 2005. SPASM: segmentation of sparse and arbitrarily oriented cardiac MRI data using a 3D-ASM. In Lecture notes in computer science, vol. 3504: 33-43. Ed AF Frangi, P Radeva, A Santos, M Hernandez. New York: Springer.Google Scholar
  33. 33.
    Bardinet E, Cohen LD, Ayache N. 1995. Superquadrics and free-form deformations: A global model to fit and track 3D medical data. In Lecture notes in computer science, Vol. 905, pp. 319-326. Ed N Ayache. New York: Springer.Google Scholar
  34. 34.
    Montagnat J, Delingette H. Space and time shape constrained deformable surfaces for 4D medical image segmentation. 2000. In Lecture notes in computer science, Vol. 1935, pp. 196-205. Ed SL Delp, AM Digioia, B Jarmaz. New York: Springer.Google Scholar
  35. 35.
    Frangi AF, Rueckert D, Schnabel JA, Niessen WJ. 2002. Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling. IEEE Trans Med Imaging 21(9):1151-1166.CrossRefGoogle Scholar
  36. 36.
    American Heart Association. 1998. American Heart Association 1999 heart and stroke statistical update., Dallas, Texas.
  37. 37.
    Behiels G, Maes F, Vandermeulen D, Suetens P. 2002. Evaluation of image features and search strategies for segmentation of bone structures in radiographs using active shape models. Med Image Anal 6(1):47-62.CrossRefGoogle Scholar
  38. 38.
    van Assen HC, Danilouchkine MG, Dirksen MS, Rieber JHC, Lelieveldt BPF. 2006. A 3D-ASM driven by fuzzy inference: application to cardiac CT and MR. Med Image Anal. In press.Google Scholar
  39. 39.
    Bland JM, Altman DG. 1986. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 8476:307-310.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Catalina Tobon-Gomez
    • 1
  • S. Ordas
    • 1
  • A. F. Frangi
    • 1
  • S. Aguade
    • 2
  • J. Castell
    • 2
  1. 1.Computational Imaging LaboratoryUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Vall d' Hebron University HospitalBarcelonaSpain

Personalised recommendations