Active Learning for Interactive 3D Image Segmentation (original) (raw)

Abstract

We propose a novel method for applying active learning strategies to interactive 3D image segmentation. Active learning has been recently introduced to the field of image segmentation. However, so far discussions have focused on 2D images only. Here, we frame interactive 3D image segmentation as a classification problem and incorporate active learning in order to alleviate the user from choosing where to provide interactive input. Specifically, we evaluate a given segmentation by constructing an “uncertainty field” over the image domain based on boundary, regional, smoothness and entropy terms. We then calculate and highlight the plane of maximal uncertainty in a batch query step. The user can proceed to guide the labeling of the data on the query plane, hence actively providing additional training data where the classifier has the least confidence. We validate our method against random plane selection showing an average DSC improvement of 10% in the first five plane suggestions (batch queries). Furthermore, our user study shows that our method saves the user 64% of their time, on average.

Chapter PDF

Similar content being viewed by others

Keywords

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. Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vision 22(1), 61–79 (1997)
    Article MATH Google Scholar
  2. Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Proc. 10(2), 266–277 (2001)
    Article MATH Google Scholar
  3. Grady, L.: Random walks for image segmentation. IEEE Trans. Pat. Anal. and Mach. Intel. 28(11), 1768–1783 (2006)
    Article Google Scholar
  4. Grady, L., Schiwietz, T., Aharon, S., Westermann, R.: Random walks for interactive organ segmentation in two and three dimensions: Implementation and validation. In: Duncan, J., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3750, pp. 773–780. Springer, Heidelberg (2005)
    Chapter Google Scholar
  5. Li, J., Bioucas-Dias, J., Plaza, A.: Supervised hyperspectral image segmentation using active learning. In: 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, pp. 1–4 (2010)
    Google Scholar
  6. Ma, A., Patel, N., Li, M., Sethi, I.: Confidence based active learning for whole object image segmentation. In: Gunsel, B., Jain, A., Tekalp, A., Sankur, B. (eds.) MRCS 2006. LNCS, vol. 4105, pp. 753–760. Springer, Heidelberg (2006)
    Chapter Google Scholar
  7. Mortensen, E.N., Barrett, W.A.: Intelligent scissors for image composition. In: 22nd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH, pp. 191–198. ACM, New York (1995)
    Chapter Google Scholar
  8. Olabarriaga, S., Smeulders, A.: Interaction in the segmentation of medical images: a survey. Med. Image Anal. 5(2), 127–142 (2001)
    Article Google Scholar
  9. Pavlopoulou, C., Kak, A.C., Brodley, C.: Application of semi-supervised and active learning to interactive contour delineation. In: ICML 2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining, pp. 26–33 (2003)
    Google Scholar
  10. Rother, C., Kolmogorov, V., Blake, A.: GrabCutTM: Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics 23, 309–314 (2004)
    Article Google Scholar
  11. Settles, B.: Active learning literature survey. Tech. Rep. 1648, University of Wisconsin-Madison (2010)
    Google Scholar
  12. Top, A., Hamarneh, G., Abugharbieh, R.: Spotlight: Automated confidence-based user guidance for increasing efficiency in interactive 3D image segmentation. In: Menze, B., Langs, G., Tu, Z., Criminisi, A. (eds.) MICCAI 2010. LNCS, vol. 6533, pp. 204–213. Springer, Heidelberg (2011)
    Chapter Google Scholar

Download references

Author information

Authors and Affiliations

  1. Medical Image Analysis Lab, Simon Fraser University, Canada
    Andrew Top & Ghassan Hamarneh
  2. Biomedical Signal and Image Computing Lab, University of British Columbia, Canada
    Rafeef Abugharbieh

Authors

  1. Andrew Top
    You can also search for this author inPubMed Google Scholar
  2. Ghassan Hamarneh
    You can also search for this author inPubMed Google Scholar
  3. Rafeef Abugharbieh
    You can also search for this author inPubMed Google Scholar

Editor information

Editors and Affiliations

  1. Queen’s University, K7L 2N6, Kingston, ON, Canada
    Gabor Fichtinger
  2. Sunnybrook Hospital, M4N 3M5, Toronto, ON, Canada
    Anne Martel
  3. Robarts Research Institute, N6A 5K8, London, ON, Canada
    Terry Peters

Rights and permissions

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Top, A., Hamarneh, G., Abugharbieh, R. (2011). Active Learning for Interactive 3D Image Segmentation. In: Fichtinger, G., Martel, A., Peters, T. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011. MICCAI 2011. Lecture Notes in Computer Science, vol 6893. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23626-6\_74

Download citation

Publish with us