Advertisement

Deformable templates for feature extraction from medical images

  • P. Lipson
  • A. L. Yuille
  • D. O'Keeffe
  • J. Cavanaugh
  • J. Taaffe
  • D. Rosenthal
Shape Description
Part of the Lecture Notes in Computer Science book series (LNCS, volume 427)

Abstract

We propose a method for detecting and describing features in medical images using deformable templates, for the purpose of diagnostic analysis of these features. The feature of interest can described by a parameterized template. An energy function is defined which links edges in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image content, by evaluating the energy function and accordingly altering its parameter values. A gradient maximization technique is used to optimize the placement and shape of the deformable template to fit the desired anatomical feature. The final parameter values can be used as descriptors for the feature. Measurements of intensity values within a region of the template can be used as inputs to a medical diagnostic system. We have developed a Picture Archive and Communication System (PACS) based image analysis program which employs the technique of deformable templates to localize features in dual energy CT images. Measurements can then be automatically made which can be used for maintenance of patients suffering from bone loss and abnormal marrow fat content. This system has been successfully tested on 552 (69 × 8) images and is currently in use at Massachusetts General Hospital, Boston, MA. Statistical comparisons between the system and previously used manual techniques show that their performances are practically equivalent and that the system has several advantages over the human operator, for example, consistency, accuracy and cost.

Keywords

Travelling Salesman Problem Massachusetts General Hospital Calcify Aorta Vertebral Trabecular Bone Parameterized Template 
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. Ayache, N, Boissonnat, J.D., Brunet, E., Cohen, L., Chieze, J.P., Geiger, B., Monga, O., Rocchisani, J.M. and Sander, P. “Building Highly Structured Volume Representations in 3D Medical Images”. Comp. Ass. Rad., Proc. Int. Symp.. Berlin. pp 765–772. 1989.Google Scholar
  2. Burr, D.J. “A Dynamic Model for Image Registration”. C.G.I.P. 15, pp 102–112. 1981.Google Scholar
  3. Burr, D.J. “Elastic Matching of Line Drawings”. IEEE Trans. P.A.M.I. PAMI-3, No. 6, pp 708–713. 1981.Google Scholar
  4. Chen, S-Y, Lin, W-C, Liang, C-C and Chen, C-T. “Improvement on Dynamic Elastic Interpolation Technique for Reconstructing 3-D Objects from Serial Cross Sections”. Comp. Ass. Rad.,, Proc. Int. Symp. Berlin. pp 702–706. 1989.Google Scholar
  5. Chow, Y., Grenander, U. and Keenan, D.M. “Hands: A Pattern Theoretic Study of Biological Shape”. Research Mongraph. Brown University, Providence, R.I. 1989.Google Scholar
  6. Durbin, R and Willshaw, D.J. “An Analogue Approach to the Travelling Salesman Problem using an Elastic Net Method”. Nature. 386. pp 689–691. 1987.Google Scholar
  7. Durbin, R., Szeliski, R. and Yuille, A.L. “The Elastic Net and the Travelling Salesman Problem”. Neural Computation. In press. 1989.Google Scholar
  8. Kass, M., Witkin, A. and Terzopoulos, D. “Snakes: Active Contour Models”. Proc. First Int. Conf. Comp. Vis. London. June 1987.Google Scholar
  9. Knoerr, A. “Global Models of Natural Boundaries: Theory and Applications”. Pattern Analysis Tech. Report No. 148. Brown University, Providence, R.I. 1989.Google Scholar
  10. Lipson, P., Yuille, A.L., O'Keeffe, D., Cavanaugh, J., Taaffe, J. and Rosenthal, D. Harvard Robotics Laboratory Technical Report. No. 89-14. 1989.Google Scholar
  11. Lipson, P., Yuille, A.L., O'Keeffe, D., Cavanaugh, J., Taaffe, J. and Rosenthal, D. “Automated Bone Density Calculation using a PACS Workstation Based Image Processing Technique of Deformable Templates”. In preparation. 1990.Google Scholar
  12. O'Keeffe, D., Taaffe, J. and Rosenthal, D. “The Application of uRSTAR, a Personal Computer-Based PACS to Quantitative CT: Early Experience,” Department of Radiology, Massachusetts General Hospital, Boston, MA., 1989.Google Scholar
  13. Pentland, A. “Recognition by Parts”. Proc. First Int. Conf. Comp. Vis. London. June 1987.Google Scholar
  14. Staib, L.H. and Duncan, J.S. “Parametrically Deformable Contour Models”. Proc. Comp. Vis. 89 and Patt. Recog. San Diego. 1989.Google Scholar
  15. Terzopoulos, D., Witkin, A., and Kass, M. “Symmetry-seeking Models for 3D Object Recognition”. Proc. First Int. Conf. Comp. Vis. London. June 1987.Google Scholar
  16. Vandermeuelen, D., Suetens, P., Gybels, J., Marchal, G. and Oosterlinck, A. “Delineation of Neuroanatomical Objects using Deformable Models”. Comp. Ass. Rad.: Proc. Int. Sym. Berlin. pp 645–650. 1989.Google Scholar
  17. Yuille, A.L., Cohen, D.S., and Hallinan, P.W. “Feature Extraction from Faces using Deformable Templates”. Proc. Comp. Vis. 89 Patt. Rec.. San Diego. 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • P. Lipson
    • 1
  • A. L. Yuille
    • 2
  • D. O'Keeffe
    • 3
  • J. Cavanaugh
    • 3
  • J. Taaffe
    • 3
  • D. Rosenthal
    • 3
  1. 1.A.I. LabM.I.T.USA
  2. 2.D.A.S. HarvardUSA
  3. 3.M.G.H.USA

Personalised recommendations