Volumetric Measurement of Heart Using PA and Lateral View of Chest Radiograph

  • I. C. Mehta
  • Z. J. Khan
  • R. R. Khotpal
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3285)


Heart size is of fundamental importance in diagnosis and radiography is a reliable method of estimating size. Volume of the heart is computed by cardiac measurements in postero-anterior (PA) and lateral view of chest radiograph Determination of heart size is a major factor in the clinical evaluation of the healthy or failing heart. In this paper, we describe an automatic method for computing the approximate volume of the heart based on cardiac rectangle. The cardiac rectangle varies in size depending on the heart size. The chief measurement is made on the PA view. The measurement is also made in true lateral view. The first step in computer processing was to extract size, contour and shape of the heart from the standard PA and lateral chest radiograph using fuzzy c-means. An algorithm that constructs a cardiac rectangle around the heart is developed. The extent of rectangle is found from features present in horizontal and vertical profiles of the chest X ray. Once cardiac outline is obtained it is straightforward to obtain measurements characterizing the shape of the heart. Volume of the heart is computed from various features obtained from pa and lateral chest radiograph. The measurements have proved of most value in estimating alteration in size of the heart shadow due to physiological or toxic causes.


Lateral View Chest Radiograph Transverse Diameter Heart Size Lateral Chest Radiograph 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hinshaw, Murray: Diseases of the chest. Prentice Hall, Englewood Cliffs (1985)Google Scholar
  2. 2.
    Sonka, M., Fitzpatrick, J.M. (eds.): Hand book of medical imaging, SPIE, vol. II (2000)Google Scholar
  3. 3.
    Harlow, C.A.: On radiographics image analysis. In: Rosenfield, A. (ed.) Digital picture processing (1991)Google Scholar
  4. 4.
    Abe, K., Dei, K., MacMahon, H., et al.: Analysis of results in large clinical series of computer aided diagnosis in chest radiology. In: Proc.of Int. Symp. on Compute Assisted Radiology, pp. 600–605 (1993)Google Scholar
  5. 5.
    Yue, Z., Goshtaby, A.: Automatic Detection of Rib Borders in chest Radiographs. IEEE Transaction on Medical Imaging 14(3), 525–536 (1995)CrossRefGoogle Scholar
  6. 6.
    Xu, X.W., Doi, K.: Image feature analysis for computer-aided diagnosis: Accurate determination of ribcage boundary in chest radiographs. Med. Phys. 22(5), 617–626 (1995)CrossRefGoogle Scholar
  7. 7.
    Cannon, R.L., dave, J., Bezdek, J.C.: Efficient implementation of the fuzzy c-means clustering algorithm. IEEE Trans on pattern Analysis and machine intelligence 8, 248–255 (1986)zbMATHCrossRefGoogle Scholar
  8. 8.
    Benzek, J.C., Pal, S.K.: Fuzzy models for pattern recognition. IEEE press, New York (1992)Google Scholar
  9. 9.
    Bak-Jensen, B., Bak-Jensen, J., Mikkelsen, S.D., Sorensen, J.T.: Curve-fitting method for transfer function determination. In: 9th IEEE Conference on Instrumentation and Measurement Technology, pp. 71–74 (1992)Google Scholar
  10. 10.
    Miller, E.K.: Smart curve fitting. Potentials 21(1), 20–23 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • I. C. Mehta
    • 1
  • Z. J. Khan
    • 1
  • R. R. Khotpal
    • 1
  1. 1.Rail TolyGondiaIndia

Personalised recommendations