Advertisement

Deformable Contour Based Algorithm for Segmentation of the Hippocampus from MRI

  • Jan Klemenčič
  • Vojko Valenčič
  • Nuška Pečarič
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2124)

Abstract

Automatic segmentation of MR images is a complex task, particularly for structures which are barely visible on MR. Hippocampus is one of such structures. We present an active contour based segmentation algorithm, suited to badly defined structures, and test it on 8 hippocampi. The basic algorithm principle could also be applied for object tracking on movie sequences. Algorithm initialisation consists of manual segmentation of some key images. We discuss and solve numerous problems: partially blurred or discontinuous object boundaries; low image contrasts and S/N ratios; multiple distracting edges, surrounding the correct object boundaries. The active contours’ inherent limitations were overcome by encoding a priori geometric information into the deformation algorithm. We present a geometry encoding algorithm, followed by specializations needed for hippocampus segmentation. We validate the algorithm by segmenting normal and atrophic hippocampi. We achieve volumetric errors in the same range as those of manual segmentation (±5%). We also evaluate the results by false positive/negative errors and relative amounts of volume agreements.

Keywords

image segmentation active contour method MRI imaging 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jack, C.R.: Mesial Temporal Sclerosis: MR based Hippocampal Volume Measurements. In: Cascino, G.D., Jack, C.R. (eds.): Neuroimaging in Epilepsy. Butterworth-Heinemann (1996) 111–119Google Scholar
  2. 2.
    Pfluger, T., Weil, S., Weis, S., Vollmar, C., Heiss, D., Egger, J., Scheck, R., Hahn, K.: Normative Volumetric Data of the Developing Hippocampus in Children Based on Magnetic Resonance Imaging. Epilepsia 40(4) (1999) 414–423CrossRefGoogle Scholar
  3. 3.
    Kass, M., Witkin, A., Terzopoulus, D.: Snakes: Active Contour Models. Proc. of 1st Int. Conf. Vision, London (1987) 259–269Google Scholar
  4. 4.
    Ghanei, A., Soltanian-Zadeh, H., Windham, J.P.: Segmentation of the Hippocampus from Brain MRI Using Deformable Contours. Med. Img. Graph., vol. 22 (1998) 203–216CrossRefGoogle Scholar
  5. 5.
    Webb, J., Guimond, A., Eldridge, P., Chadwick, D., Meunier, J., Thirion, J.P., Roberts, N.: Automatic Detection of Hippocampal Atrophy on Magnetic Resonance Images. Mag. Reson. Imaging, vol. 17, no. 8 (1999) 1149–1161CrossRefGoogle Scholar
  6. 6.
    Christensen, G.E., Rabbitt, R.D., Miller, M.I.: Deformable Templates Using Large Deformation Kinematics. Tr. Img. Proc., vol. 5, no. 10 (1996) 1435–1447CrossRefGoogle Scholar
  7. 7.
    Haller, J.W., Christensen, G.E., Joshi, S.C., Newcomer, J.W., Miller, M.I., Csernansky, J.G., Vannier, M.W.: Hippocampal MR imaging morphometry by means of general pattern matching. Radiology, 199(3) (1996) 787–791Google Scholar
  8. 8.
    Klemenčič, A., Kovačič, S., Pernuš, F.: Automated Segmentation of Muscle Fiber Images Using Active Contour Models. Cytometry 32 (1998) 317–326CrossRefGoogle Scholar
  9. 9.
    Olstad, V., Torp, A.H.: Encoding of a priori Information in Active Contour Models. Tr. Pat. Anal. Mach. Intellig., vol. 18, no. 9 (1996) 836–872Google Scholar
  10. 10.
    Radeva, P., Serrat, J., Marti, E.: A Snake for Model-Based Segmentation. Proc. of 5th Int. Conf. Vision, Massachusetts (1995) 816–821Google Scholar
  11. 11.
    Rao, K.R., Ben-Arie, J.: Optimal Edge Detection Using Expansion Matching and Restoration. Tr. Pat. Anal. Mach. Intellig., vol. 16 (1994) 1169–1182CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Jan Klemenčič
    • 1
  • Vojko Valenčič
    • 1
  • Nuška Pečarič
    • 2
  1. 1.Faculty of Electrical EngineeringLaboratory for Biomedical Visualisation and Muscle BiomechanicsLjubljanaSlovenia
  2. 2.Clinical Institute of RadiologyUniversity Clinical CentreLjubljanaSlovenia

Personalised recommendations