Advertisement

Automated Interpretation of Ventilation-Perfusion Lung Scintigrams for the Diagnosis of Pulmonary Embolism Using Support Vector Machines

  • Anders Ericsson
  • Amelié Huart
  • Andreas Ekefjärd
  • Kalle Åström
  • Holger Holst
  • Eva Evander
  • Per Wollmer
  • Lars Edenbrandt
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

The purpose of this study was to develop a new completely automated method for the interpretation of ventilation-perfusion (V-P) lung scintigrams for the diagnosis of pulmonary embolism. A new way of extracting features, characteristic for pulmonary embolism is presented. These features are then used as input to a Support Vector Machine, which discriminates between pulmonary embolism or no embolism. Using a material of 509 training cases and 104 test cases, the performance of the system, measured as the area under the ROC curve, was 0.86 in the test group. It is concluded that a completely automatic method can be used for interpretation of V-P scintigrams. It is faster and more robust than a previously presented method [4, 5] and the accuracy is at the same level as the the previous method. It also handles abnormalities in the lungs.

References

  1. 1.
    GH. Burton, P. Vernon, and WA. Seed. An automated quantative analysis of ventilation-perfusion lung scintigrams. Journal of Nuclear Medicine, 25:564–570, 1984.Google Scholar
  2. 2.
    Nello Cristianini and John Shawe-Talor. An Introduction to Support Vector Ma chines. Cambrige, 2000.Google Scholar
  3. 3.
    Tourassi GD, Floyd CE, Sostman HD, and Coleman RE. Acute pulmonary embolism: artificial neural networks approach for diagnosis. Acute pulmonary embolism, (189):555–558, 1993.Google Scholar
  4. 4.
    H. Holger, K. Åström, A. Järund, J. Palmer, A. Heyden, F. Kahl, K. Tägil, E. Evander, G. Sparr, and L. Edenbrandt. Automated interpretation of ventilation-perfusion lung scintigrams for the diagnosis of pulmonary embolism. European Journal of Nuclear Medicine, 27(4):400–406, 2000.CrossRefGoogle Scholar
  5. 5.
    H. Holger, K. Måre, and et al. Järund, A. An independent evaluation of a new method for automated interpretation of lung scintigrams using artificial neural networks. European Journal of Nuclear Medicine, 28:33–38, 2001.CrossRefGoogle Scholar
  6. 6.
    Scott JA and Palmer EL. Neural network analysis of ventilation-perfusion lung scans. Radiology, (186):661–664, 1993.Google Scholar
  7. 7.
    Scott JA, Fisher RE, and Palmer EL. Neural networks in ventilation-perfusion imaging. Radiology, (198):707–713, 1996.Google Scholar
  8. 8.
    Junshui Ma, Yi Zhao, and Stanley Ahalt. Osu svm classifier matlab toolbox. web http://eewww.eng.ohio-state.edu/~maj/osu_svm.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Anders Ericsson
    • 1
  • Amelié Huart
    • 1
  • Andreas Ekefjärd
    • 1
  • Kalle Åström
    • 1
  • Holger Holst
    • 2
  • Eva Evander
    • 2
  • Per Wollmer
    • 2
  • Lars Edenbrandt
    • 2
  1. 1.Mathematics, Center for Mathematical Sciences, Institute of TechnologyLund UniversityLundSweden
  2. 2.Department of Clinical PhysiologyLund UniversityLundSweden

Personalised recommendations