Advertisement

Towards automated analysis in 3D cardiac MR imaging

  • M Bister
  • J Cornelis
  • Y Taeymans
4. Segmentation: Specific Applications
Part of the Lecture Notes in Computer Science book series (LNCS, volume 511)

Abstract

The main purpose of the work described in this paper is to make a first step towards the automatization of the quantification of the ventricular volume in systole and diastole using MR Images.

To achieve this result, we pursue three partial objectives:
  1. 1.

    Obtain objective image segmentation. Manual organ delineations vary from physician to physician. An automatic segmentation, taking into account the typical nature of cardiac MR Images, should produce objective and reproducible results and take less time than manual segmentation.

     
  2. 2.

    Obtain reliable segment labeling. A computer system, which takes into account descriptions of the organs (scene knowledge), has to be developed to assist the physician in labeling the segments produced by the automatic segmentation. Interactive tools should be provided to show the results of segmentation and labeling to the physician and ask him for confirmation or corrections.

     
  3. 3.

    Obtain accurate volume measurement. Volume measurements will allow the evaluation and partial validation of the results obtained by the previous parts of the system.

     

The paper describes a prototype of a complete system for cardiac volume estimation. Detailed descriptions of the individual segmentation and labeling modules have been published previously. In this paper the emphasis lies on the interaction between these modules, their performances in the system, their 3D generalisation, and their evaluation based on cardiac volume estimations.

Keywords

Image analysis segmentation labeling multiresolution pyramids distance transforms 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bister M, Taeymans Y and Cornelis J (1989). Automatic segmentation of cardiac MR Images. In: Proc. Comp. in Card. '89. Ripley KL (ed), IEEE Computer Society, Los Alamitos, pp. 215–218.Google Scholar
  2. Bister M, Cornelis J and Rosenfeld A (1990a). A critical view of pyramid segmentation algorithms. Patt. Recogn. Lett. 11:605–617.Google Scholar
  3. Bister M, Cornelis J, Taeymans Y and De Cuyper B (1990b). A generic labeling scheme for segmented cardiac MR Images. In: Proc. Comp. in Card. '90. Ripley KL (ed), IEEE Computer Society, Los Alamitos.Google Scholar
  4. Bister M, Schnall D, Deklerck R, Cornelis J and Taeymans Y (1990c). The Cavity Detector: a generic image segmentation algorithm. In: Proc. North Sea Conf. on Biomed. Eng. Cornelis J and Peeters S (eds), TI-K. VIV, Antwerp, topic 2.Google Scholar
  5. Bister M (1990d). Computer analysis of cardiac MR Images. PhD Thesis, IRIS, VUB, Brussels.Google Scholar
  6. Borgefors G (1986). Distance transformations in digital images. Comp. Vis. Graph. Im. Proc. 34:344–371.Google Scholar
  7. Eiho S, Kuwahara M, Fujita Y, Matsuda T, Sakurai T and Kawai C (1987). 3-D Reconstruction of the left ventricle from Magnetic Resonance Images. In: Proc. Comp. in Card. '87. Ripley KL (ed), IEEE Computer Society, Los Alamitos, pp. 51–56.Google Scholar
  8. Haralick RH and Shapiro LG (1985). Survey — Image segmentation techniques. Comp. Vis. Graph. Im. Proc. 29:100–132.Google Scholar
  9. Harwood D, Subbarao M, Hakalahti H and Davis LS (1984). A new class of edge-preserving smoothing filters. CAR-TR-59, CVL, Univ. Maryland.Google Scholar
  10. Harwood D, Prasannappa R and Davis LS (1988). Preliminary design of a Programmed Picture Logic. CAR-TR-364, CVL, Univ. Maryland.Google Scholar
  11. Horowitz SL and Pavlidis T (1976). Picture segmentation by a tree traversal algorithm. J. ACM. 23:368–388.Google Scholar
  12. Kittler J and Illingworth J (1986). Minimum error thresholding. Patt. Recogn. 19:41–47.Google Scholar
  13. Koenderink JJ (1984). The structure of images. Biol. Cybern. 50:363–370.Google Scholar
  14. Rosenfeld A (1984). Multiresolution image processing and analysis. Springer-Verlag, Berlin.Google Scholar
  15. Vossepoel AM (1988). A note on distance transformations in digital images. Comp. Vis. Graph. Im. Proc. 43:88–97.Google Scholar
  16. Weyman AE (1982). Cross-sectional echocardiography. Lea & Febiger, Philadelphia.Google Scholar
  17. Yang SS, Bentivoglio LG, Maranhão V and Goldberg H (1978). From cardiac catheterization data to hemodynamic parameters. F.A. Davis Company, Philadelphia.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • M Bister
    • 1
  • J Cornelis
    • 1
  • Y Taeymans
    • 2
  1. 1.IRIS Research GroupBrusselsBelgium
  2. 2.Dept. of Cardiology5K12IE, UZ-RUGGentBelgium

Personalised recommendations