Advertisement

Learning from Multiple Experts with Random Forests: Application to the Segmentation of the Midbrain in 3D Ultrasound

  • Pierre Chatelain
  • Olivier Pauly
  • Loïc Peter
  • Seyed-Ahmad Ahmadi
  • Annika Plate
  • Kai Bötzel
  • Nassir Navab
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)

Abstract

In the field of computer aided medical image analysis, it is often difficult to obtain reliable ground truth for evaluating algorithms or supervising statistical learning procedures. In this paper we present a new method for training a classification forest from images labelled by variably performing experts, while simultaneously evaluating the performance of each expert. Our approach builds upon state-of-the-art randomized classification forest techniques for medical image segmentation and recent methods for the fusion of multiple expert decisions. By incorporating the performance evaluation within the training phase, we obtain a novel forest framework for learning from conflicting expert decisions, accounting for both inter- and intra-expert variability. We demonstrate on a synthetic example that our method allows to retrieve the correct segmentation among other incorrectly labelled images, and we present an application to the automatic segmentation of the midbrain in 3D transcranial ultrasound images.

Keywords

Ground Truth Random Forest Classic Random Forest Medical Image Analysis Medical Image Segmentation 
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.

References

  1. 1.
    Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (STAPLE): An algorithm for the validation of image segmentation. IEEE Transactions on Medical Imaging 23, 903–921 (2004)CrossRefGoogle Scholar
  2. 2.
    Commowick, O., Warfield, S.K.: Incorporating priors on expert performance parameters for segmentation validation and label fusion: A maximum a posteriori STAPLE. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part III. LNCS, vol. 6363, pp. 25–32. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Martin-Fernandez, M., Bouix, S., Ungar, L., McCarley, R.W., Shenton, M.E.: Two methods for validating brain tissue classifiers. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 515–522. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Commowick, O., Akhondi-Asl, A., Warfield, S.: Estimating a reference standard segmentation with spatially varying performance parameters: Local MAP STAPLE. IEEE Transactions on Medical Imaging 31(8), 1593–1606 (2012)CrossRefGoogle Scholar
  5. 5.
    Raykar, V.C., Yu, S., Zhao, L.H., Valadez, G.H., Florin, C., Bogoni, L., Moy, L.: Learning from crowds. Journal of Machine Learning Research 11, 1297–1322 (2010)MathSciNetGoogle Scholar
  6. 6.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar
  7. 7.
    Criminisi, A., Shotton, J., Bucciarelli, S.: Decision forests with long-range spatial context for organ localization in CT volumes. In: MICCAI Workshop on Probabilistic Models for Medical Image Analysis (2009)Google Scholar
  8. 8.
    Pauly, O., Ahmadi, S.-A., Plate, A., Boetzel, K., Navab, N.: Detection of substantia nigra echogenicities in 3D transcranial ultrasound for early diagnosis of parkinson disease. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 443–450. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision 7(2-3), 81–227 (2012)CrossRefGoogle Scholar
  10. 10.
    Pauly, O., Glocker, B., Criminisi, A., Mateus, D., Martinez-Moeller, A., Nekolla, S., Navab, N.: Fast multiple organs detection and localization in whole-body MR dixon sequences. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 239–247. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Geng, D.Y., Li, Y.X., Zee, C.S.: Magnetic resonance imaging-based volumetric analysis of basal ganglia nuclei and substantia nigra in patients with parkinson’s disease. Neurosurgery 58(2), 256–262 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Pierre Chatelain
    • 1
    • 2
  • Olivier Pauly
    • 1
    • 3
  • Loïc Peter
    • 1
  • Seyed-Ahmad Ahmadi
    • 1
  • Annika Plate
    • 4
  • Kai Bötzel
    • 4
  • Nassir Navab
    • 1
  1. 1.Computer Aided Medical ProceduresTechnische Universität MünchenGermany
  2. 2.Ecole Normale Supérieure de CachanAntenne de BretagneFrance
  3. 3.Institute of Biomathematics and BiometryHelmholtz Zentrum MünchenGermany
  4. 4.Department of NeurologyLudwig-Maximilians-Universität MünchenGermany

Personalised recommendations