Advertisement

VETOT, Volume Estimation and Tracking Over Time: Framework and Validation

  • Jean-Philippe Guyon
  • Mark Foskey
  • Jisung Kim
  • Zeynep Firat
  • Barbara Davis
  • Karen Haneke
  • Stephen R. Aylward
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2879)

Abstract

We have implemented an effective and publicly available tool, VETOT, to track and quantify the evolution of tumors and organs over time. VETOT includes a framework both for registration and segmentation. We have evaluated the accuracy and reliability of different level set segmentation methods in order to validate this part of our software and evaluate its usability. In addition to the registration and segmentation frameworks, our program allows the creation of inter- and intra-patient atlases based on a common coordinate system defined by the landmarks selected during the registration process. Based on the National Library of Medicine’s Insight toolkit, this free software is extensible and provides an intuitive interface that allows very fast processing with minimum training. This paper details VETOT and our level set segmentation evaluation.

Keywords

Volume Estimation Rigid Registration Smoothness Constraint Deformable Registration Geodesic Active Contour 
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.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic Active Contours. Int. J. Computer Vision 22, 61–97 (1997)zbMATHCrossRefGoogle Scholar
  2. 2.
    Sethian, J.A.: Level Set Methods and Fast Marching Methods. Cambridge Press, Cambridge (1999)zbMATHGoogle Scholar
  3. 3.
    Whitaker, R., Xue, X.: Variable-Conductance, Level-Set Curvature for Image Denoising. In: Proc. International Conf. Signal Processing (2001)Google Scholar
  4. 4.
    Weeks, S.M., Wilber, K.P., Aylward, S.R.: Volume estimantion using conventional hand tracing techniques versus automatic thresholding techniques: can we be more accurate and save time? In: Proceedings of the Radiological Society of North America, Chicago IL (November 2001)Google Scholar
  5. 5.
    Gerig, G., Jomier, M., Chakos, M.: Valmet: A new validation tool for assessing and improving 3D object segmentation Medical Image Computing and Computer-Assisted Intervention (2001)Google Scholar
  6. 6.
    Wells, W.M., Viola, P., Kikinis, R.: Multi-Modal Volume Registration by Maximization of Mutual InformationGoogle Scholar
  7. 7.
    Welti, D., Gerig, G., Radue, E.-W., Kappos, L., Szekely, G.: Spatio-temporal Segmentation of Active Multiple Scleroris Lesions in Serial MRI Data. In: Insana, M.F., Leahy, R.M. (eds.) IPMI 2001. LNCS, vol. 2082, pp. 438–445. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Gerig, G., Welti, D., Guttmann, C., Colchester, A., Szekely, G.: Exploring the discrimination power of the time domain for segmentation and characterization of lesions in serial MR data. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 469–480. Springer, Heidelberg (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jean-Philippe Guyon
    • 1
  • Mark Foskey
    • 1
  • Jisung Kim
    • 1
  • Zeynep Firat
    • 2
  • Barbara Davis
    • 3
  • Karen Haneke
    • 4
  • Stephen R. Aylward
    • 1
  1. 1.Computer Aided Display and Diagnosis Laboratory, Department of RadiologyThe University of North Carolina at Chapel HillUSA
  2. 2.Department of RadiologyUniversity of North Carolina HospitalChapel HillUSA
  3. 3.National Institute of Environmental Health SciencesCaryUSA
  4. 4.Integrated Laborator SystemsResearch Triangle ParkUSA

Personalised recommendations