Skip to main content

An Ensemble Method for Classifying Regional Disease Patterns of Diffuse Interstitial Lung Disease Using HRCT Images from Different Vendors

Journal of Digital Imaging volume 30, pages 761–771 (2017)Cite this article

Abstract

We propose the use of ensemble classifiers to overcome inter-scanner variations in the differentiation of regional disease patterns in high-resolution computed tomography (HRCT) images of diffuse interstitial lung disease patients obtained from different scanners. A total of 600 rectangular 20 × 20-pixel regions of interest (ROIs) on HRCT images obtained from two different scanners (GE and Siemens) and the whole lung area of 92 HRCT images were classified as one of six regional pulmonary disease patterns by two expert radiologists. Textual and shape features were extracted from each ROI and the whole lung parenchyma. For automatic classification, individual and ensemble classifiers were trained and tested with the ROI dataset. We designed the following three experimental sets: an intra-scanner study in which the training and test sets were from the same scanner, an integrated scanner study in which the data from the two scanners were merged, and an inter-scanner study in which the training and test sets were acquired from different scanners. In the ROI-based classification, the ensemble classifiers showed better (p < 0.001) accuracy (89.73%, SD = 0.43) than the individual classifiers (88.38%, SD = 0.31) in the integrated scanner test. The ensemble classifiers also showed partial improvements in the intra- and inter-scanner tests. In the whole lung classification experiment, the quantification accuracies of the ensemble classifiers with integrated training (49.57%) were higher (p < 0.001) than the individual classifiers (48.19%). Furthermore, the ensemble classifiers also showed better performance in both the intra- and inter-scanner experiments. We concluded that the ensemble classifiers provide better performance when using integrated scanner images.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3

References

  1. Hoffman EA, et al.: Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function 1. Academic Radiology 10:1104–1118, 2003

    Article  PubMed  Google Scholar 

  2. Scatarige JC, Diette GB, Haponik EF, Merriman B, Fishman EK: Utility of high-resolution CT for management of diffuse lung disease: results of a survey of US pulmonary physicians. Academic Radiology 10:167–175, 2003

    Article  PubMed  Google Scholar 

  3. Grenier P, Valeyre D, Cluzel P, Brauner MW, Lenoir S, Chastang C: Chronic diffuse interstitial lung-disease—diagnostic-value of chest radiography and high-resolution Ct. Radiology 179:123–132, 1991

    CAS  Article  PubMed  Google Scholar 

  4. Coxson HO, et al.: A quantification of the lung surface area in emphysema using computed tomography. American Journal of Respiratory and Critical Care Medicine 159:851–856, 1999

    CAS  Article  PubMed  Google Scholar 

  5. Kalender WA, Rienmuller R, Seissler W, Behr J, Welke M, Fichte H: Measurement of pulmonary parenchymal attenuation—use of Spirometric gating with quantitative Ct. Radiology 175:265–268, 1990

    CAS  Article  PubMed  Google Scholar 

  6. Kim N, Seo JB, Lee Y, Lee JG, Kim SS, Kang S-H: Development of an automatic classification system for differentiation of obstructive lung disease using HRCT. Journal of Digital Imaging 22:136–148, 2008

    Article  PubMed  PubMed Central  Google Scholar 

  7. Xu Y, Sonka M, McLennan G, Guo JF, Hoffman EA: MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies. IEEE Transactions on Medical Imaging 25:464–475, 2006

    CAS  Article  PubMed  Google Scholar 

  8. Fujisaki T, et al.: Effects of density changes in the chest on lung stereotactic radiotherapy. Radiat Med 22:233–238, 2004

    PubMed  Google Scholar 

  9. Chabat F, Yang GZ, Hansell DM: Obstructive lung diseases: texture classification for differentiation at CT. Radiology 228:871–877, 2003

    Article  PubMed  Google Scholar 

  10. Lim J, Kim N, Seo JB, Lee YK, Lee Y, Kang S-H: Regional context-sensitive support vector machine classifier to improve automated identification of regional patterns of diffuse interstitial lung disease. Journal of Digital Imaging 24:1133–1140, 2011

    Article  PubMed  PubMed Central  Google Scholar 

  11. Moon JW, et al.: Perfusion-and pattern-based quantitative CT indexes using contrast-enhanced dual-energy computed tomography in diffuse interstitial lung disease: relationships with physiologic impairment and prediction of prognosis. European Radiology:1–10, 2015

  12. Xu Y, van Beek EJ, Hwanjo Y, Guo J, McLennan G, Hoffman EA: Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). Academic Radiology 13:969–978, 2006

    Article  PubMed  Google Scholar 

  13. Delorme S, Keller-Reichenbecher M-A, Zuna I, Schlegel W, Van Kaick G: Usual interstitial pneumonia: quantitative assessment of high-resolution computed tomography findings by computer-assisted texture-based image analysis. Investigative Radiology 32:566–574, 1997

    CAS  Article  PubMed  Google Scholar 

  14. Uppaluri R, Hoffman EA, Sonka M, Hartley PG, Hunninghake GW, Mclennan G: Computer recognition of regional lung disease patterns. American Journal of Respiratory and Critical Care Medicine 160:648–654, 1999

    CAS  Article  PubMed  Google Scholar 

  15. Gangeh MJ, Sorensen L, Shaker SB, Kamel MS, Bruijne Md, Loog M: A texton-based approach for the classification of lung parenchyma in CT images. Proc. Proceedings of the 13th International Conference on Medical Image Computing and Computer-assisted Intervention: Part III

  16. Sorensen L, Shaker SB, de Bruijne M: Quantitative analysis of pulmonary emphysema using local binary patterns. IEEE Transaction on Medical Imaging 29:559–569, 2010

    Article  Google Scholar 

  17. Vo KT, Sowmya A: Multiple kernel learning for classification of diffuse lung disease using HRCT lung images. Proc. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology

  18. Xu R, Hirano Y, Tachibana R, Kido S: Classification of diffuse lung disease patterns on high-resolution computed tomography by a bag of words approach. Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention

  19. Depeursinge A, et al.: Optimized steerable wavelets for texture analysis of lung tissue in 3-D CT: classification of usual interstitial pneumonia. Proc. 2015 I.E. 12th International Symposium on Biomedical Imaging (ISBI)

  20. Zhao W, Xu R, Hirano Y, Tachibana R, Kido S: Classification of diffuse lung diseases patterns by a sparse representation based method on HRCT images. Proc. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

  21. Yuan R, et al.: The effects of radiation dose and CT manufacturer on measurements of lung densitometry. Chest Journal 132:617–623, 2007

    Article  Google Scholar 

  22. Park SO, et al.: Feasibility of automated quantification of regional disease patterns depicted on high-resolution computed tomography in patients with various diffuse lung diseases. Korean Journal of Radiology 10:455, 2009

    Article  PubMed  PubMed Central  Google Scholar 

  23. Chang Y, Lim J, Kim N, Seo JB, Lynch DA: A support vector machine classifier reduces interscanner variation in the HRCT classification of regional disease pattern in diffuse lung disease: comparison to a Bayesian classifier. Medical Physics 40:051912, 2013

    Article  PubMed  Google Scholar 

  24. Kim N, et al.: Effect of various binning methods and ROI sizes on the accuracy of the automatic classification system for differentiation between diffuse infiltrative lung diseases on the basis of texture features at HRCT. Proc. Medical Imaging, 2008

  25. Haralick RM: Statistical and structural approaches to texture. Proceedings of the IEEE 67:786–804, 1979

    Article  Google Scholar 

  26. Carr JR, de Miranda FP: The semivariogram in comparison to the co-occurrence matrix for classification of image texture. IEEE Transactions on Geoscience and Remote Sensing 36:1945–1952, 1998

    Article  Google Scholar 

  27. Kim N, Seo JB, Lee YK, Kim SS, Kang SH: Optimal binning and ROI size of the automatic classification system for differentiation between obstructive lung diseases on the basis of texture features at HRCT. IEICE technical report 106:95–97, 2007

    Google Scholar 

  28. Gevenois PA, de Maertelaer V, De Vuyst P, Zanen J, Yernault JC: Comparison of computed density and macroscopic morphometry in pulmonary emphysema. American Journal of Respiratory and Critical Care Medicine 152:653–657, 1995

    CAS  Article  PubMed  Google Scholar 

  29. Sonka M, Hlavac V, Boyle R: Image processing, analysis, and machine vision, Pacific Grove, CA: PWS Pub., 1999

    Google Scholar 

  30. Yoo TS, et al.: Engineering and algorithm design for an image processing API: a technical report on ITK—the insight toolkit. Studies in Health Technology and Informatics:586–592, 2002

  31. Pedregosa F, et al.: Scikit-learn: machine learning in python. Journal of Machine Learning Research 12:2825–2830, 2011

    Google Scholar 

  32. Cortes C, Vapnik V: Support-vector networks. Machine Learning 20:273–297, 1995

    Google Scholar 

  33. Dietterich TG: Ensemble methods in machine learning: Springer, 2000

  34. Breiman L: Random forests. Machine Learning 45:5–32, 2001

    Article  Google Scholar 

  35. Wolpert DH: Stacked generalization. Neural Networks 5:241–259, 1992

    Article  Google Scholar 

Download references

Acknowledgements

This work was partially supported by the Technological Innovation R&D Program (S2259881) funded by the Small and Medium Business Administration (SMBA, Korea); and by Institute for Information and Communications Technology Promotion (IITP) grant funded by the Korean Government (MSIP) (No. R6910-15-1023).

Author information

Affiliations

  1. Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil, Songpa-Gu, Seoul, South Korea

    Sanghoon Jun & Namkug Kim

  2. Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil, Songpa-Gu, Seoul, South Korea

    Namkug Kim & Joon Beom Seo

  3. Department of Laboratory Medicine, Hallym University College of Medicine, Anyang, South Korea

    Young Kyung Lee

  4. Department of Radiology, National Jewish Medical and Research Center, Denver, CO, USA

    David A. Lynch

Authors
  1. Sanghoon Jun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Namkug Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Joon Beom Seo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Young Kyung Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. David A. Lynch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Namkug Kim.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Jun, S., Kim, N., Seo, J.B. et al. An Ensemble Method for Classifying Regional Disease Patterns of Diffuse Interstitial Lung Disease Using HRCT Images from Different Vendors. J Digit Imaging 30, 761–771 (2017). https://doi.org/10.1007/s10278-017-9957-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-017-9957-6

Keywords

  • Interstitial lung disease (ILD)
  • Ensemble learning
  • Support vector machine (SVM)
  • Inter-scanner variation
  • Multi-center trial