Advertisement

European Radiology

, Volume 18, Issue 12, pp 2745–2755 | Cite as

Automated classification of normal and pathologic pulmonary tissue by topological texture features extracted from multi-detector CT in 3D

  • H. F. BoehmEmail author
  • C. Fink
  • U. Attenberger
  • C. Becker
  • J. Behr
  • M. Reiser
Computer Tomography

Abstract

To provide a novel, robust algorithm for classification of lung tissue depicted by multi-detector computed tomography (MDCT) based on the topology of CT-attenuation values and to compare discriminative results with densitometric methods. Two hundred seventy-five cubic volumes of interest (VOI, edge length 40 pixels) were obtained from MDCT chest CT (isotropic voxel size, edge length 0.6 mm) of 21 subjects with and without pathology (emphysema, fibrosis). All VOIs were visually consensus-classified by two radiologists. Texture features based on the Minkowski functionals (MF) as well as on the CT attenuation values are determined. Classification results of both approaches were assessed by receiver-operator characteristic and discriminant analysis. By densitometric (topological) parameters, normal and abnormal VOIs were distinguished with an area under the curve ranging from 0.78 to 0.85 (0.87 to 0.96). Correlation between both groups of parameters was non-significant (p ≥ 0.36). By combined information of densitometric and topological quantities, the radiologists’ ratings were reproduced for 92% of VOIs, ranging from 85.7% (fibrosis) to 98% (normal VOIs). Our method performs well for identification of VOIs containing abnormal lung-tissue. Combined information of densitometry and topology increases the number of correctly classified VOIs further. When extended to CT data depicting whole lungs, topological analysis may allow to enhance density-based analysis and improve monitoring texture changes with progression of pulmonary disease.

Keywords

Fibrosis Emphysema Classification Image processing Minkowski functionals 

References

  1. 1.
    American Thoracic Society (1962) Chronic bronchitis, asthma, and pulmonary emphysema: a statement by the committee on diagnostic standards for nontuberculous respiratory diseases. Am Rev Respir Dis 85:762–768Google Scholar
  2. 2.
    American Thoracic Society/European Respiratory Society (2002) International multidisciplinary consensus classification of the idiopathic interstitial pneumonias. Am J Respir Crit Care Med 165:277–304Google Scholar
  3. 3.
    Sanders C (1991) The radiographic diagnosis of emphysema. Radiol Clin North Am 29:1019–1030PubMedGoogle Scholar
  4. 4.
    Epler GR, McCloud TC, Gaensler EA et al (1978) Normal chest roentgenograms in chronic diffuse infiltrative lung disease. N Engl J Med 298:935–939Google Scholar
  5. 5.
    Kuwano K, Matsuba K, Ikeda T et al (1990) The diagnosis of mild emphysema. Correlation of computed tomography and pathology scores. Am Rev Respir Dis 141:169–178PubMedGoogle Scholar
  6. 6.
    Miller RR, Muller NL, Vedal S et al (1989) Limitations of computed tomography in the assessment of emphysema. Am Rev Respir Dis 139:980–983PubMedGoogle Scholar
  7. 7.
    Brody AS, Kosorok MR, Li Z et al (2006) Reproducibility of a scoring system for computed tomography scanning in cystic fibrosis. J Thorac Imaging 21:14–21PubMedCrossRefGoogle Scholar
  8. 8.
    Biernacki W, Redpath AT, Best JJ et al (1997) Measurement of CT lung density in patients with chronic asthma 2. Eur Respir J 10:2455–2459PubMedCrossRefGoogle Scholar
  9. 9.
    Gould GA, MacNee W, McLean A et al (1988) CT measurements of lung density in life can quantitate distal airspace enlargement–an essential defining feature of human emphysema. Am Rev Respir Dis 137:380–392PubMedGoogle Scholar
  10. 10.
    Uppaluri R, Mitsa T, Sonka M et al (1997) Quantification of pulmonary emphysema from lung computed tomography images. Am J Respir Crit Care Med 156:248–254PubMedGoogle Scholar
  11. 11.
    Hoffman EA, Reinhardt JM, Sonka M et al (2003) Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function. Acad Radiol 10:1104–1118PubMedCrossRefGoogle Scholar
  12. 12.
    Blechschmidt RA, Werthschuetzky R, Loercher U (2001) Automated CT image evaluation of the lung: a morphology-based concept. IEEE Trans Med Imaging 20:434–442PubMedCrossRefGoogle Scholar
  13. 13.
    Gilman MJ, Laurens RG Jr, Somogyi JW et al (1983) CT attenuation values of lung density in sarcoidosis. J Comput Assist Tomogr 7:407–410PubMedCrossRefGoogle Scholar
  14. 14.
    Goddard PR, Nicholson EM, Laszlo G et al (1982) Computed tomography in pulmonary emphysema. Clin Radiol 33:379–387PubMedCrossRefGoogle Scholar
  15. 15.
    Hayhurst MD, MacNee W, Flenley DC et al (1984) Diagnosis of pulmonary emphysema by computerised tomography. Lancet 2:320–322PubMedCrossRefGoogle Scholar
  16. 16.
    Best AC, Lynch AM, Bozic CM et al (2003) Quantitative CT indexes in idiopathic pulmonary fibrosis: relationship with physiologic impairment. Radiology 228:407–414PubMedCrossRefGoogle Scholar
  17. 17.
    Delorme S, Keller-Reichenbecher MA, Zuna I et al (1997) Usual interstitial pneumonia. Quantitative assessment of high-resolution computed tomography findings by computer-assisted texture-based image analysis. Invest Radiol 32:566–574PubMedCrossRefGoogle Scholar
  18. 18.
    Perez A, Coxson HO, Hogg JC et al (2005) Use of CT morphometry to detect changes in lung weight and gas volume. Chest 128:2471–2477PubMedCrossRefGoogle Scholar
  19. 19.
    Uppaluri R, Hoffman EA, Sonka M et al (1999) Interstitial lung disease: a quantitative study using the adaptive multiple feature method. Am J Respir Crit Care Med 159:519–525PubMedGoogle Scholar
  20. 20.
    Blechschmidt RA, Werthschutzky R, Lorcher U (2001) Automated CT image evaluation of the lung: a morphology-based concept. IEEE Trans Med Imaging 20:434–442PubMedCrossRefGoogle Scholar
  21. 21.
  22. 22.
    Quarnier PH, Tammeling GJ, Cotes JE et al (1993) Lung volumes and forced ventilatory flows: report working party standardization of lung function tests, European community for steel and coal. Official statement of the European Respiratory Society. Eur Respir J 16:5–40Google Scholar
  23. 23.
    Michielsen K, De Raedt H, Kawakatsu T (2001) Integral-geometry morphological image analysis. Phys Rep 347:461–538CrossRefGoogle Scholar
  24. 24.
    Berg BA (2004) Markov chain Monte Carlo Simulations and their statistical analysis. World Scientific, SingaporeGoogle Scholar
  25. 25.
    Robert CP, Casella G (2004) Monte Carlo Statistical Methods. Springer, New YorkGoogle Scholar
  26. 26.
    Metz CE (1978) Basic principles of ROC analysis. Semin Nucl Med 8:283–298PubMedCrossRefGoogle Scholar
  27. 27.
    Stone M (1977) An asymptotic equivalence of choice of model by cross-validation and Akaike’s criterion. J R Stat Soc 38:44–47Google Scholar
  28. 28.
    Long FR, Williams RS, Castile RG (2005) Inspiratory and expiratory CT lung density in infants and young children. Pediatr Radiol 35:677–683PubMedCrossRefGoogle Scholar
  29. 29.
    Long FR, Castile RG (2001) Technique and clinical applications of full-inflation and end-exhalation controlled-ventilation chest CT in infants and young children. Pediatr Radiol 31:413–422PubMedCrossRefGoogle Scholar
  30. 30.
    Zompatori M, Battaglia M, Rimondi MR et al (1997) Quantitative assessment of pulmonary emphysema with computerized tomography. Comparison of the visual score and high resolution computerized tomography, expiratory density mask with spiral computerized tomography and respiratory function tests. Radiol Med (Torino) 93:374–381Google Scholar
  31. 31.
    Bankier AA, De Maertelaer V, Keyzer C et al (1999) Pulmonary emphysema: subjective visual grading versus objective quantification with macroscopic morphometry and thin-section CT densitometry. Radiology 211:851–858PubMedGoogle Scholar
  32. 32.
    Xu Y, van Beek EJ, Hwanjo Y et al (2006) Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). Acad Radiol 13:969–978PubMedCrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2008

Authors and Affiliations

  • H. F. Boehm
    • 1
    • 4
    Email author
  • C. Fink
    • 2
  • U. Attenberger
    • 1
  • C. Becker
    • 1
  • J. Behr
    • 3
  • M. Reiser
    • 1
  1. 1.Department of RadiologyLudwig-Maximilians-UniversitaetMunichGermany
  2. 2.Department of RadiologyUniversitaetsklinikum MannheimMannheimGermany
  3. 3.Department of PneumologyLudwig-Maximilians-UniversitaetMunichGermany
  4. 4.Department of RadiologyUniversity of MunichMunichGermany

Personalised recommendations