Unsupervised Assessment of Subcutaneous and Visceral Fat by MRI

  • Peter S. Jørgensen
  • Rasmus Larsen
  • Kristian Wraae
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)


This paper presents a method for unsupervised assessment of visceral and subcutaneous adipose tissue in the abdominal region by MRI. The identification of the subcutaneous and the visceral regions were achieved by dynamic programming constrained by points acquired from an active shape model. The combination of active shape models and dynamic programming provides for a both robust and accurate segmentation. The method features a low number of parameters that give good results over a wide range of values.The unsupervised segmentation was compared with a manual procedure and the correlation between the manual segmentation and unsupervised segmentation was considered high.


Image processing Abdomen Visceral fat Dynamic programming Active shape model 


  1. 1.
    Vague, J.: The degree of masculine differentiation of obesity: a factor determining predisposition to diabetes, atherosclerosis, gout, and uric calculous disease. Obes. Res. 4 (1996)Google Scholar
  2. 2.
    Bjorntorp, P.P.: Adipose tissue as a generator of risk factors for cardiovascular diseases and diabetes. Arteriosclerosis 10 (1990)Google Scholar
  3. 3.
    McNeill, G., Fowler, P.A., Maughan, R.J., McGaw, B.A., Gvozdanovic, D., Fuller, M.F.: Body fat in lean and obese women measured by six methods. Prof. Nutr. Soc. 48 (1989)Google Scholar
  4. 4.
    Van der Kooy, K., Seidell, J.C.: Techniques for the measurement of visceral fat: a practical guide. Int. J. Obes. 17 (1993)Google Scholar
  5. 5.
    Abate, N., Burns, D., Peshock, R.M., Garg, A., Grundy, S.M.: Estimation of adipose tissue by magnetic resonance imaging: validation against dissection in human cadavers. Journal of Lipid Research 35 (1994)Google Scholar
  6. 6.
    Poll, L.W., Wittsack, H.J., Koch, J.A., Willers, R., Cohnen, M., Kapitza, C., Heinemann, L., Mödder, U.: A rapid and reliable semiautomated method for measurement of total abdominal fat volumes using magnetic resonance imaging. Magnetic Resonance Imaging 21 (2003)Google Scholar
  7. 7.
    Jin, Y., Imielinska, C.Z., Laine, A.F., Udupa, J., Shen, W., Heymsfield, S.B.: Segmentation and evaluation of adipose tissue from whole body MRI scans. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 635–642. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    Positano, V., Gastaldelli, A., Sironi, A.M., Santarelli, M.F., Lmobardi, M., Landini, L.: An accurate and robust method for unsupervised assessment of abdominal fat by MRI. Journal of Magnetic Resonance Imaging 20 (2004)Google Scholar
  9. 9.
    Engholm, R., Dubinskiy, A., Larsen, R., Hanson, L.G., Christoffersen, B.Ø.: An adipose segmentation and quantification scheme for the abdominal region in minipigs. In: International Symposium on Medical Imaging 2006, San Diego, CA, USA. The International Society for Optical Engineering, SPIE (February 2006)Google Scholar
  10. 10.
    Green, P.J., Silverman, B.W.: Nonparametric regression and generalized linear models, a roughness penalty approach. Chapman & Hall, Boca Raton (1994)CrossRefzbMATHGoogle Scholar
  11. 11.
    Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  12. 12.
    Cootes, T.F., Taylor, C.J.: Statistical models of appearence for medical image analysis and computer vision. In: Proc. SPIE Medical Imaging (2001) (to appear)Google Scholar
  13. 13.
    Gower, J.C.: Generalized procrustes analysis. Psychometrika 40 (1975)Google Scholar
  14. 14.
    Ten Berge, J.M.F.: Orthogonal procrustes rotation for two or more matrices. Psychometrika 42 (1977)Google Scholar
  15. 15.
    Glasbey, C.A., Young, M.J.: Maximum a posteriori estimation of image boundaries by dynamic programming. Journal of the Royal Statistical Society - Series C Applied Statistics 51(2), 209–222 (2002)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Peter S. Jørgensen
    • 1
    • 2
  • Rasmus Larsen
    • 1
  • Kristian Wraae
    • 3
  1. 1.Department of Informatics and Mathematical ModellingTechnical University of DenmarkDenmark
  2. 2.Fuel Cells and Solid State Chemistry Division, National Laboratory for Sustainable EnergyTechnical University of DenmarkDenmark
  3. 3.Odense University HospitalDenmark

Personalised recommendations