Skip to main content

Advertisement

SpringerLink
Log in
Menu
Find a journal Publish with us
Search
Cart
Book cover

International Conference on Medical Image Computing and Computer-Assisted Intervention

MICCAI 2012: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012 pp 98–105Cite as

  1. Home
  2. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012
  3. Conference paper
Uncertainty-Based Feature Learning for Skin Lesion Matching Using a High Order MRF Optimization Framework

Uncertainty-Based Feature Learning for Skin Lesion Matching Using a High Order MRF Optimization Framework

  • Hengameh Mirzaalian19,
  • Tim K. Lee19,20,21 &
  • Ghassan Hamarneh19 
  • Conference paper
  • 3984 Accesses

  • 5 Citations

Part of the Lecture Notes in Computer Science book series (LNIP,volume 7511)

Abstract

We formulate the pigmented-skin-lesion (PSL) matching problem as a relaxed labeling of an association graph. In this graph labeling problem, each node represents a mapping between a PSL from one image to a PSL in the second image and the optimal labels are those optimizing a high order Markov Random Field energy (MRF). The energy is made up of unary, binary, and ternary energy terms capturing the likelihood of matching between the points, edges, and cliques of two graphs representing the spatial distribution of the two PSL sets. Following an exploration of various MRF energy terms, we propose a novel entropy energy term encouraging solutions with low uncertainty. By interpreting the relaxed labeling as a measure of confidence, we further leverage the high confidence matching to sequentially constrain the learnt objective function defined on the association graph. We evaluate our method on a large set of synthetic data as well as 56 pairs of real dermatological images. Our proposed method compares favorably with the state-of-the-art.

Keywords

  • Markov Random Field
  • Match Problem
  • Successive Projection
  • Graph Match
  • Entropy Term

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.

Download conference paper PDF

References

  1. Duchenne, O., Bach, F., Kweon, I., Ponce, J.: A tensor-based algorithm for high-order graph matching. IEEE TPAMI 1(99), 1–13 (2011)

    Google Scholar 

  2. Gallagher, R., Rivers, J., Lee, T., Bajdik, C., McLean, D.I., Coldman, A.: Broad-Spectrum Sunscreen Use and the Development of New Nevi in White Children: A Randomized Controlled Trial. JAMA 283(22), 2955–2960 (2000)

    Google Scholar 

  3. Huang, H., Bergstresser, P.: A new hybrid technique for dermatological image registration. IEEE BIBE, 1163–1167 (2007)

    Google Scholar 

  4. Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Research Logistic Quarterly 2, 83–97 (1955)

    Google Scholar 

  5. Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: IEEE ICCV, vol. 2, pp. 1482–1489 (2005)

    Google Scholar 

  6. Leordeanu, M., Zanfir, A., Sminchisescu, C.: Semi-supervised Learning and Optimization for Hypergraph Matching. In: IEEE ICCV (2011)

    Google Scholar 

  7. Mirzaalian, H., Hamarneh, G., Lee, T.: Graph-based approach to skin mole matching incorporating template-normalized coordinates. In: IEEE CVPR, pp. 2152–2159 (2009)

    Google Scholar 

  8. Perednia, D.A., White, R.G.: Automatic registration of multiple skin lesions by use of point pattern matching. CMIG 16(3), 205–216 (1992)

    Google Scholar 

  9. Roning, J., Riech, M.: Registration of nevi in successive skin images for early detection of melanoma. In: IEEE ICPR, vol. 1, pp. 352–357 (1998)

    Google Scholar 

  10. Torresani, L., Kolmogorov, V., Rother, C.: Feature Correspondence Via Graph Matching: Models and Global Optimization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 596–609. Springer, Heidelberg (2008)

    CrossRef  Google Scholar 

  11. Zass, R., Shashua, A.: Probabilistic graph and hypergraph matching. In: IEEE CVPR, pp. 1–8 (2008)

    Google Scholar 

  12. Zeng, Y., Wang, C., Yang, W., Gu, X., Samaras, D., Paragios, N.: Dense non-rigid surface registration using high-order graph matching. In: IEEE CVPR, pp. 382–389 (2010)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Medical Image Analysis Lab, Simon Fraser University, Canada

    Hengameh Mirzaalian, Tim K. Lee & Ghassan Hamarneh

  2. Cancer Control Research, BC Cancer Agency, Canada

    Tim K. Lee

  3. Department of Dermatology and Skin Science, University of British Columbia, Canada

    Tim K. Lee

Authors
  1. Hengameh Mirzaalian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tim K. Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ghassan Hamarneh
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Project Team Asclepios, Inria Sophia Antipolis, 06902, Sophia-Antipolis, France

    Nicholas Ayache & Hervé Delingette & 

  2. MIT, CSAIL, 02139, Cambridge, MA, USA

    Polina Golland

  3. Information and Communication Headquarters, Nagoya University, 464-8603, Nagoya, Japan

    Kensaku Mori

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Mirzaalian, H., Lee, T.K., Hamarneh, G. (2012). Uncertainty-Based Feature Learning for Skin Lesion Matching Using a High Order MRF Optimization Framework. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012. MICCAI 2012. Lecture Notes in Computer Science, vol 7511. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33418-4_13

Download citation

  • .RIS
  • .ENW
  • .BIB
  • DOI: https://doi.org/10.1007/978-3-642-33418-4_13

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-33417-7

  • Online ISBN: 978-3-642-33418-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Share this paper

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Search

Navigation

  • Find a journal
  • Publish with us

Discover content

  • Journals A-Z
  • Books A-Z

Publish with us

  • Publish your research
  • Open access publishing

Products and services

  • Our products
  • Librarians
  • Societies
  • Partners and advertisers

Our imprints

  • Springer
  • Nature Portfolio
  • BMC
  • Palgrave Macmillan
  • Apress
  • Your US state privacy rights
  • Accessibility statement
  • Terms and conditions
  • Privacy policy
  • Help and support

167.114.118.210

Not affiliated

Springer Nature

© 2023 Springer Nature