Layered Spatio-temporal Forests for Left Ventricle Segmentation from 4D Cardiac MRI Data

  • Ján Margeta
  • Ezequiel Geremia
  • Antonio Criminisi
  • Nicholas Ayache
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7085)


In this paper we present a new method for fully automatic left ventricle segmentation from 4D cardiac MR datasets. To deal with the diverse dataset, we propose a machine learning approach using two layers of spatio-temporal decision forests with almost no assumptions on the data nor explicitly specifying the segmentation rules. We introduce 4D spatio-temporal features to classification with decision forests and propose a method for context aware MR intensity standardization and image alignment. The second layer is then used for the final image segmentation. We present our first results on the STACOM LV Segmentation Challenge 2011 validation datasets.


Validation Dataset Intensity Standardization Lesion Segmentation Decision Forest Forest Layer 
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.
    Lempitsky, V., Verhoek, M., Noble, J., Blake, A.: Random Forest Classification for Automatic Delineation of Myocardium in Real-Time 3D Echocardiography. In: Ayache, N., Delingette, H., Sermesant, M. (eds.) FIMH 2009. LNCS, vol. 5528, pp. 447–456. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Geremia, E., Clatz, O., Menze, B.H., Konukoglu, E., Criminisi, A., Ayache, N.: Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. NeuroImage 57(2), 378–390 (2011)CrossRefGoogle Scholar
  3. 3.
    Shi, W., Zhuang, X., Wang, H., Duckett, S., Oregan, D., Edwards, P., Ourselin, S., Rueckert, D.: Automatic Segmentation of Different Pathologies from Cardiac Cine MRI Using Registration and Multiple Component EM Estimation. In: Metaxas, D., Axel, L. (eds.) FIMH 2011. LNCS, vol. 6666, pp. 163–170. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  4. 4.
    Lu, X., Wang, Y., Georgescu, B., Littman, A., Comaniciu, D.: Automatic Delineation of Left and Right Ventricles in Cardiac MRI Sequences Using a Joint Ventricular Model. In: Metaxas, D., Axel, L. (eds.) FIMH 2011. LNCS, vol. 6666, pp. 250–258. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  5. 5.
    Fonseca, C., Backhaus, M., Bluemke, D., Britten, R., Chung, J., Cowan, B., Dinov, I., Finn, J., Hunter, P., Kadish, A., Lee, D., Lima, J., Medrano-Gracia, P., Shivkumar, K., Suinesiaputra, A., Tao, W., Young, A.: The Cardiac Atlas Project- an Imaging Database for Computational Modeling and Statistical Atlases of the Heart. Bioinformatics 27(16), 2288–2295 (2011)CrossRefGoogle Scholar
  6. 6.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, pp. I-511–I-518. IEEE Computer Society (2001)Google Scholar
  7. 7.
    Nyúl, L.G., Udupa, J.K.: On standardizing the MR image intensity scale. Magnetic Resonance in Medicine 42(6), 1072–1081 (1999)CrossRefGoogle Scholar
  8. 8.
    Shah, M., Xiao, Y., Subbanna, N., Francis, S., Arnold, D.L., Collins, D.L., Arbel, T.: Evaluating intensity normalization on MRIs of human brain with multiple sclerosis. Medical Image Analysis 15(2), 267–282 (2010)CrossRefGoogle Scholar
  9. 9.
    Bergeest, J., Florian Jäger, F.: A Comparison of Five Methods for Signal Intensity Standardization in MRI. In: Tolxdorff, T., Braun, J., Deserno, T.M., Horsch, A., Handels, H., Meinzer, H.P., Brauer, W. (eds.) Bildverarbeitung für die Medizin 2008, pp. 36–40. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  10. 10.
    Nyúl, L.G., Udupa, J.K., Zhang, X.: New Variants of a Method of MRI Scale Standardization. IEEE Transactions on Medical Imaging 19(2), 143–150 (2000)CrossRefGoogle Scholar
  11. 11.
    Jain, R., Chlamtac, I.: The P2 algorithm for dynamic calculation of quantiles and histograms without storing observations. Communications of the ACM 28(10), 1076–1085 (1985)CrossRefGoogle Scholar
  12. 12.
    Egloff, D.: Weighted P2 quantile, Boost Accumulators 1.46 (2005),
  13. 13.
    Konukoglu, E., Criminisi, A., Pathak, S., Robertson, D., White, S., Haynor, D., Siddiqui, K.: Robust linear registration of CT images using random regression forests. In: SPIE Medical Imaging, vol. 7962, pp. 79621X–79621X-8 (2011) Google Scholar
  14. 14.
    Ourselin, S., Roche, A., Prima, S., Ayache, N.: Block Matching: A General Framework to Improve Robustness of Rigid Registration of Medical Images. In: Delp, S., DiGoia, A., Jaramaz, B. (eds.) MICCAI 2000. LNCS, vol. 1935, pp. 557–566. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  15. 15.
    Hoogendoorn, C., Whitmarsh, T., Duchateau, N., Sukno, F.M., De Craene, M., Frangi, A.F.: A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction. In: SPIE Medical Imaging, vol. 7962, pp. 76231R–76231R-9 (2010)Google Scholar
  16. 16.
    Iglesias, J., Konukoglu, E., Montillo, A., Tu, Z., Criminisi, A.: Combining Generative and Discriminative Models for Semantic Segmentation of CT Scans via Active Learning. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 25–36. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  17. 17.
    Krishnan, K., Ibanez, L., Turner, W., Avila, R.: Algorithms, architecture, validation of an open source toolkit for segmenting CT lung lesions. In: Brown, M., de Bruijne, M., van Ginneken, B., Kiraly, A., Kuhnigk, J.M., Lorenz, C., McClelland, J.R., Mori, K., Reeves, A., Reinhardt, J.M. (eds.) MICCAI Workshop on Pulmonary Image Analysis, CreateSpace, pp. 365–375 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ján Margeta
    • 1
  • Ezequiel Geremia
    • 1
  • Antonio Criminisi
    • 2
  • Nicholas Ayache
    • 1
  1. 1.Asclepios Research Project, INRIASophia-AntipolisFrance
  2. 2.Machine Learning and Perception GroupMicrosoft ResearchCambridgeUK

Personalised recommendations