Advertisement

Multi-atlas and Gaussian Mixture Modeling Based Perirectal Fat Segmentation from CT Images

  • Soumya Ghose
  • Jim Denham
  • Martin Ebert
  • Angel Kennedy
  • Jhimli Mitra
  • Stephen Rose
  • Jason Dowling
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8198)

Abstract

Accurate perirectal fat segmentation in CT images aids in estimating radiation dose delivered to the region of fat around the rectum during radiation therapy treatment of prostate cancer. Such a process is important in determining the resulting toxicity of the neighboring tissues. However automatic or semi-automatic segmentation of the perirectal fat in CT images is a challenging task due to inter patient anatomical variability, contrast variability and imaging artifacts. We propose a combined schema of multi-atlas and multi parametric Gaussian mixture modeling for perirectal fat segmentation in CT images. Multi-atlas based soft segmentation and multi parametric Gaussian mixture modeling aids in identifying the volume of interest (VOI). Thereafter expectation maximization (EM) based soft clustering of the intensities of the VOI refined with positional probabilities of the perirectal fat provides the segmentation of the perirectal fat. The proposed method achieves a mean sensitivity value of 0.88±0.07 and a mean specificity value of 0.998±0.001 with 5 patient datasets in a leave-one-patient-out validation framework. Qualitative results show a good approximation of the perirectal fat volume compared to the ground truth.

Keywords

Multi-atlas gaussian mixture modeling computed tomography 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chandra, S.S., Dowling, J., Shen, K.K., Raniga, P., Pluim, J.P.W., Greer, P.B., Salvado, O., Fripp, J.: Patient specific prostate segmentation in 3D magnetic resonance images. IEEE Trans. Med. Imaging 31(10), 1955–1964 (2012)CrossRefGoogle Scholar
  2. 2.
    Clinical Trials, A.G.: Randomised androgen deprivation and radiotherapy (RADAR) trial (2013), http://www.ClinicalTrials.gov (accessed on May 19, 2013)
  3. 3.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society 39, 1–38 (1977)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Gao, Y., Sandhu, R., Fichtinger, G., Tannenbaum, A.R.: A Coupled Global Registration and Segmentation Framework with Application to Magnetic Resonance Prostate Imagery. IEEE Transactions on Medical Imaging 10, 17–81 (2010)Google Scholar
  5. 5.
    Australian Government: Cancer in Australia an overview 2012 (2013), http://www.aihw.gov.au (accessed on May 20, 2013)
  6. 6.
    Klein, S., van der Heide, U.A., Lipps, I.M., Vulpen, M.V., Staring, M., Pluim, J.P.W.: Automatic Segmentation of the Prostate in 3D MR Images by Atlas Matching Using Localized Mutual Information. Medical Physics 35, 1407–1417 (2008)CrossRefGoogle Scholar
  7. 7.
    Liao, S., Gao, Y., Lian, J., Shen, D.: Sparse patch-based label propagation for accurate prostate localization in CT images. IEEE Trans. Med. Imaging 32(2), 419–434 (2013)CrossRefGoogle Scholar
  8. 8.
    Modat, M., Ridgway, G.R., Taylor, Z.A., Lehmann, M., Barnes, J., Hawkes, D.J., Fox, N.C., Ourselin, S.: Fast free-form deformation using graphics processing units. Computer Methods and Programs in Biomedicine 98(3), 278–284 (2010)CrossRefGoogle Scholar
  9. 9.
    Ourselin, S., Roche, A., Subsol, G., Pennec, X., Ayache, N.: Reconstructing a 3D structure from serial histological sections. Image Vision Comput. 19(1-2), 25–31 (2001)CrossRefGoogle Scholar
  10. 10.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Non-rigid registration using free-form deformations: Application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  11. 11.
    Studholme, C., Hill, D.L.J., Hawkes, D.J.: An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognition 72(1), 71–86 (1999)CrossRefGoogle Scholar
  12. 12.
    Theodoridis, Koutroumbas.: Pattern Recognition, 4th edn. Academic Press (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Soumya Ghose
    • 1
  • Jim Denham
    • 2
  • Martin Ebert
    • 3
    • 4
  • Angel Kennedy
    • 3
  • Jhimli Mitra
    • 1
  • Stephen Rose
    • 1
  • Jason Dowling
    • 1
  1. 1.CSIRO Computational InformaticsHerstonAustralia
  2. 2.School of Medicine and Public HealthUniversity of NewcastleCallaghanAustralia
  3. 3.Radiation OncologySir Charles Gairdner HospitalNedlandsAustralia
  4. 4.School of PhysicsUniversity of Western AustraliaCrawleyAustralia

Personalised recommendations