Accurate Regression-Based 4D Mitral Valve Surface Reconstruction from 2D+t MRI Slices

  • Dime Vitanovski
  • Alexey Tsymbal
  • Razvan Ioan Ionasec
  • Michaela Schmidt
  • Andreas Greiser
  • Edgar Mueller
  • Xiaoguang Lu
  • Gareth Funka-Lea
  • Joachim Hornegger
  • Dorin Comaniciu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)

Abstract

Cardiac MR (CMR) imaging is increasingly accepted as the gold standard for the evaluation of cardiac anatomy, function and mass. The multi-plan ability of CMR makes it a well suited modality for evaluation of the complex anatomy of the mitral valve (MV). However, the 2D slice-based acquisition paradigm of CMR limits the 4D capabilities for precise and accurate morphological and pathological analysis due to long through-put times and protracted study. In this paper we propose a new CMR protocol for acquiring MR images for 4D MV analysis. The proposed protocol is optimized regarding the number and spatial configuration of the 2D CMR slices. Furthermore, we present a learning- based framework for patient-specific 4D MV segmentation from 2D CMR slices (sparse data). The key idea with our Regression-based Surface Reconstruction (RSR) algorithm is the use of available MV models from other imaging modalities (CT, US) to train a dynamic regression model which will then be able to infer the absent information pertinent to CMR. Extensive experiments on 200 transesophageal echochardiographic (TEE) US and 20 cardiac CT sequences are performed to train the regression model and to define the CMR acquisition protocol. With the proposed acquisition protocol, a stack of 6 parallel long-axis (LA) planes, we acquired CMR patient images and regressed 4D patient-specific MV model with an accuracy of 1.5±0.2 mm and average speed of 10 sec per volume.

Keywords

Mitral Valve Shape Descriptor Weak Learner Active Shape Model Throughput Time 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Djavidani, B., et al.: Planimetry of mitral valve stenosis by magnetic resonance imaging. In: American College of Cardiology, vol. 45, pp. 2048–2053 (2005)Google Scholar
  2. 2.
    van Assen, H.C., et al.: Spasm: a 3d-asm for segmentation of sparse and arbitrarily oriented cardiac mri data. In: Medical Image Analysis, vol. 10, pp. 286–303 (2006)Google Scholar
  3. 3.
    Frangi, A.F., et al.: Threedimensional modeling for functional analysis of cardiac images: A review. IEEE Trans. Medical Imaging 20, 2–25 (2001)CrossRefGoogle Scholar
  4. 4.
    Wang, X., et al.: Reconstruction of detailed left ventricle motion from tmri using deformable models. In: Functional Imaging and Modeling of the Heart (2007)Google Scholar
  5. 5.
    Cootes, T.F., et al.: Active shape models-their training and application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  6. 6.
    Conti, C.A., et al.: Mitral valve modelling in ischemic patients: Finite element analysis from cardiac magnetic resonance imaginge. In: Computing in Cardiology, pp. 1059–1062 (2010)Google Scholar
  7. 7.
    Ionasec, R., et al.: Patient-specific modeling and quantification of the aortic and mitral valves from 4d cardiac ct and tee. In: TMI (2010) (in Press)Google Scholar
  8. 8.
    Grbić, S., Ionasec, R., Vitanovski, D., Voigt, I., Wang, Y., Georgescu, B., Navab, N., Comaniciu, D.: Complete valvular heart apparatus model from 4D cardiac CT. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 218–226. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Zhou, S.K., et al.: Image based regression using boosting method. In: ICCV (2005)Google Scholar
  10. 10.
    Vitanovski, D., Tsymbal, A., Ionasec, R.I., Georgescu, B., Huber, M., Taylor, A., Schievano, S., Zhou, S.K., Hornegger, J., Comaniciu, D.: Cross-modality assessment and planning for pulmonary trunk treatment using CT and MRI imaging. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 460–467. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  11. 11.
    Osada, R., et al.: Shape distributions. ACM Transactions on Graphics 21, 807–832 (2002)CrossRefMATHGoogle Scholar
  12. 12.
    Friedman, J.H.: Greedy function approximation: A gradient boosting machine. Annals of Statistics 29, 1189–1232 (2000)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  14. 14.
    Webb, G.I.: Multiboosting: A technique for combining boosting and wagging. Machine Learning, 159–196 (2000)Google Scholar
  15. 15.
    Lu, X., et al.: Discriminative joint context for automatic landmark set detection from a single cardiac mr long axis slice. In: FIHM (2009)Google Scholar
  16. 16.
    Tu, Z.: Probabilistic boosting-tree: Learning discriminativemethods for classification, recognition, and clustering. In: ICCV (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Dime Vitanovski
    • 2
    • 3
  • Alexey Tsymbal
    • 2
  • Razvan Ioan Ionasec
    • 1
  • Michaela Schmidt
    • 3
  • Andreas Greiser
    • 4
  • Edgar Mueller
    • 4
  • Xiaoguang Lu
    • 1
  • Gareth Funka-Lea
    • 1
  • Joachim Hornegger
    • 3
  • Dorin Comaniciu
    • 1
  1. 1.Siemens Corporate ResearchPrincetonUSA
  2. 2.Siemens Corporate TechnologyErlangenGermany
  3. 3.Siemens Health CareErlangenGermany
  4. 4.Pattern Recognition LabFriedrich-Alexander-UniversityErlangenGermany

Personalised recommendations