Advertisement

Dynamic Active Contour Model for Size Independent Blood Vessel Lumen Segmentation and Quantification in High-Resolution Magnetic Resonance Images

  • Catherine Desbleds-MansardEmail author
  • Alfred Anwander
  • Linda Chaabane
  • Maciej Orkisz
  • Bruno Neyran
  • Philippe C. Douek
  • Isabelle E. Magnin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2124)

Abstract

We are presenting a software tool developed for the purpose of atherosclerotic plaque study in high resolution Magnetic Resonance Images. A new implementation of balloon-type active contour model used for segmentation and quantification of blood vessel lumen is described. Its originality resides in a dynamic scaling process which makes the influence of the balloon force independent of the current size of the contour. The contour can therefore be initialized by single point. Moreover, system matrix inversion is performed only once. Hence computational cost is strongly reduced. This model was validated in ex vivo vascular images from Watanabe heritable hyperlipidaemic rabbits. Automatic quantification results were compared to measurements performed by experts. Mean quantification error was smaller than average intra-observer variability.

Keywords

medical imaging active contour model magnetic resonance images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Asdente, M., et al.: Evaluation of atherosclerotic lesions using NMR microimaging. Atherosclerosis 80(3) (1990) 243–53CrossRefGoogle Scholar
  2. 2.
    Yuan, C., et al.: Techniques for high-resolution MR imaging of atherosclerotic plaque. J Magn Reson Imaging 4(1) (1994) 43–49CrossRefGoogle Scholar
  3. 3.
    Toussaint, J.F., et al.: Magnetic resonance images lipid, fibrous, calcified, hemor-rhagic, and thrombotic components of human atherosclerosis in vivo. Circulation 94(5) (1996) 332–338MathSciNetGoogle Scholar
  4. 4.
    Serfaty, J.M., Chaabane, L., Tabib, A., Chevallier, J.M., Briguet, A. and Douek, P.: The value of T2-Weighted High Spatial Resolution Magnetic Resonance Imaging in Classifying and Characterizing Atherosclerotic Plaques: An In Vitro Study. Radiology (2001) (in press)Google Scholar
  5. 5.
    Chaabane, L., Canet, E., Serfaty, J.M., Contard, F., Guerrier, D., Douek, P., Briguet, A.: Microimaging of atherosclerotic plaque in animal models. Magnetic Resonance Materials in Physics, Biology and Medicine 11 (2000) 58–60CrossRefGoogle Scholar
  6. 6.
    Wink, O., et al.: Semi-automated quantification and segmentation of abdominal aorta aneurysins from CTA volumes. CARS Paris, France (1999) 208–212Google Scholar
  7. 7.
    Mc Inerney, T. and Terzopoulos, D.: Deformable models in medical image analysis: a survey. Med. Image Analysis 1(2) (1996) 91–108CrossRefGoogle Scholar
  8. 8.
    Rueckert, D., et al., Automatic tracking of the aorta in cardiovascular MR images using deformable models. IEEE Trans. Med. Imaging 16(5) (1997) 581–590CrossRefGoogle Scholar
  9. 9.
    Kass, M., Witkin, A., Terzopoulos, D.: Active contour models. Int. J Computer Vision 1 (1988) 321–331CrossRefGoogle Scholar
  10. 10.
    Hernández-Hoyos, M., Anwander, A., Orkisz, M., Roux, J.-P., Douek, P.C., Magnin, I.E.: A Deformable Vessel Model with Single Point Initialization for Segmentation, Quantification and Visualization of Blood Vessels in 3D MRA. MIC-CAI, Pittsburgh, Oct. 9–13 (2000) 735–745Google Scholar
  11. 11.
    Cohen, L.D.: On Active Contour Models and Balloons. Computer Vision, Graphics and Image Processing: Image Understanding, 53(2) (1991) 211–218zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Catherine Desbleds-Mansard
    • 1
    Email author
  • Alfred Anwander
    • 1
  • Linda Chaabane
    • 2
  • Maciej Orkisz
    • 1
  • Bruno Neyran
    • 1
  • Philippe C. Douek
    • 1
  • Isabelle E. Magnin
    • 1
  1. 1.CREATIS, CNRS Research Unit (UMR 5515) affiliated to INSERMLyonFrance
  2. 2.Laboratory RMNCNRS Research Unit (UMR 5012)LyonFrance

Personalised recommendations