Advertisement

Journal of Digital Imaging

, Volume 31, Issue 2, pp 235–244 | Cite as

Development of a Computer-Aided Differential Diagnosis System to Distinguish Between Usual Interstitial Pneumonia and Non-specific Interstitial Pneumonia Using Texture- and Shape-Based Hierarchical Classifiers on HRCT Images

  • SangHoon Jun
  • BeomHee Park
  • Joon Beom Seo
  • SangMin Lee
  • Namkug Kim
Article

Abstract

A computer-aided differential diagnosis (CADD) system that distinguishes between usual interstitial pneumonia (UIP) and non-specific interstitial pneumonia (NSIP) using high-resolution computed tomography (HRCT) images was developed, and its results compared against the decision of a radiologist. Six local interstitial lung disease patterns in the images were determined, and 900 typical regions of interest were marked by an experienced radiologist. A support vector machine classifier was used to train and label the regions of interest of the lung parenchyma based on the texture and shape characteristics. Based on the regional classifications of the entire lung using HRCT, the distributions and extents of the six regional patterns were characterized through their CADD features. The disease division index of every area fraction combination and the asymmetric index between the left and right lungs were also evaluated. A second SVM classifier was employed to classify the UIP and NSIP, and features were selected through sequential-forward floating feature selection. For the evaluation, 54 HRCT images of UIP (n = 26) and NSIP (n = 28) patients clinically diagnosed by a pulmonologist were included and evaluated. The classification accuracy was measured based on a fivefold cross-validation with 20 repetitions using random shuffling. For comparison, thoracic radiologists assessed each case using HRCT images without clinical information or diagnosis. The accuracies of the radiologists’ decisions were 75 and 87%. The accuracies of the CADD system using different features ranged from 70 to 81%. Finally, the accuracy of the proposed CADD system after sequential-forward feature selection was 91%.

Keywords

Computer-aided differential diagnosis Usual interstitial pneumonia Non-specific interstitial pneumonia Regional lung disease patterns SVM classifier 

Notes

Acknowledgments

This work was supported by the Industrial Strategic technology development program (10072064) funded by the Ministry of Trade, Industry and Energy (MI, Korea).

Compliance with Ethical Standards

Conflict of Interest

Namkug Kim and Joon Beom Seo have conflicts of interest regarding royalties received for a patent on classifying regional diseased patterns of diffuse interstitial lung disease, and as stockholders of Coreline Soft, Inc. The other authors have no relevant conflicts of interest to disclose.

References

  1. 1.
    Travis WD, King TE, Bateman ED, Lynch DA, Capron F, Center D, Colby TV, Cordier JF, DuBois RM, Galvin J: American Thoracic Society/European Respiratory Society international multidisciplinary consensus classification of the idiopathic interstitial pneumonias. American journal of respiratory and critical care medicine 165(2):277–304, 2002CrossRefGoogle Scholar
  2. 2.
    du Bois R, King TE: Challenges in pulmonary fibrosis · 5: The NSIP/UIP debate. Thorax 62(11):1008–1012, 2007CrossRefPubMedPubMedCentralGoogle Scholar
  3. 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(1):123–132, 1991CrossRefPubMedGoogle Scholar
  4. 4.
    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(2):167–175, 2003CrossRefPubMedGoogle Scholar
  5. 5.
    Copley SJ, Wells AU, Muller NL, Rubens MB, Hollings NP, Cleverley JR, Milne DG, Hansell DM: Thin-Section CT in Obstructive Pulmonary Disease: Discriminatory Value 1. Radiology 223(3):812–819, 2002CrossRefPubMedGoogle Scholar
  6. 6.
    Ge Z, Sahiner B, Chan H-P, Hadjiiski LM, Cascade PN, Bogot N, Kazerooni EA, Wei J, Zhou C: Computer-aided detection of lung nodules: false positive reduction using a 3D gradient field method and 3D ellipsoid fitting. Medical physics 32(8):2443–2454, 2005CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Yamagishi M, Koba H, Nakagawa A, Honma A, Yokokawa K, Saitoh T, Harada H, Watanabe H, Mori Y, Katoh S: Qualitative assessment of centrilobular emphysema using computed tomography. Nihon Igaku Hoshasen Gakkai zasshi. Nippon acta radiologica 51(3):203–212, 1991PubMedGoogle Scholar
  8. 8.
    Uppaluri R, Mitsa T, Sonka M, Hoffman EA, McLennan G: Quantification of pulmonary emphysema from lung computed tomography images. American journal of respiratory and critical care medicine 156(1):248–254, 1997CrossRefPubMedGoogle Scholar
  9. 9.
    Chabat F, Yang G-Z, Hansell DM: Obstructive Lung Diseases: Texture Classification for Differentiation at CT 1. Radiology 228(3):871–877, 2003CrossRefPubMedGoogle Scholar
  10. 10.
    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(8):969–978, 2006CrossRefPubMedGoogle Scholar
  11. 11.
    N. Kim, J. B. Seo, Y. S. Sung, B.-W. Park, Y. Lee, S. H. Park, Y. K. Lee, S.-H. Kang: 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, presented at the Medical Imaging, 2008 (unpublished).Google Scholar
  12. 12.
    Raqhu G, Collard HR, Eqan JJ, Martinez FJ, Behr J, Brown KK, Colby TV, Cordier JF, Flaherty KR, Lasky JA, Lynch DA, Ryu JH, Swiqris JJ, Wells AU, Ancochea J, Bouros D, Carvalho C, Costabel U, Ebina M, Hansell DM, Johkoh T, Kim DS, King, Jr TE, Kondoh Y, Myers J, Muller NL, Nicholson AG, Richeldi L, Selman M, Dudden RF, Griss BS, Protzko SL, Schunemann HJ: An official ATS/ERS/JRS/ALAT statement: Idiopathic pulmonary fibrosis: evidence-based guidelines for diagnosis and management. American Journal of Respiratory and Critical Care Medicine 183(6):788–824, 2011CrossRefGoogle Scholar
  13. 13.
    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(5):051912, 2013CrossRefPubMedGoogle Scholar
  14. 14.
    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(2):136–148, 2008CrossRefPubMedPubMedCentralGoogle Scholar
  15. 15.
    Lynch DA, Travis WD, Muller NL, Galvin JR, Hansell DM, Grenier PA, King J, Talmadge E: Idiopathic Interstitial Pneumonias: CT Features 1. Radiology 236(1):10–21, 2005CrossRefPubMedGoogle Scholar
  16. 16.
    Mueller-Mang C, Grosse C, Schmid K, Stiebellehner L, Bankier AA: What Every Radiologist Should Know about Idiopathic Interstitial Pneumonias 1. Radiographics 27(3):595–615, 2007CrossRefPubMedGoogle Scholar
  17. 17.
    Akira M, Inoue Y, Kitaichi M, Yamamoto S, Arai T, Toyokawa K: Usual Interstitial Pneumonia and Nonspecific Interstitial Pneumonia with and without Concurrent Emphysema: Thin-Section CT Findings 1. Radiology 251(1):271–279, 2009CrossRefPubMedGoogle Scholar
  18. 18.
    Silva CIS, Muller NL, Hansell DM, Lee KS, Nicholson AG, Wells AU: Nonspecific Interstitial Pneumonia and Idiopathic Pulmonary Fibrosis: Changes in Pattern and Distribution of Disease over Time 1. Radiology 247(1):251–259, 2008CrossRefPubMedGoogle Scholar
  19. 19.
    Pudil P, Novovičová J, Kittler J: Floating search methods in feature selection. Pattern recognition letters 15(11):1119–1125, 1994CrossRefGoogle Scholar
  20. 20.
    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(6):1133–1140, 2011CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2017

Authors and Affiliations

  1. 1.Biomedical Engineering Research Center, Asan Institute of Life ScienceUniversity of Ulsan College of Medicine, Asan Medical CenterSeoulRepublic of Korea
  2. 2.Department of RadiologyUniversity of Ulsan College of Medicine, Asan Medical CenterSeoulRepublic of Korea
  3. 3.Department of Convergence MedicineUniversity of Ulsan College of Medicine, Asan Medical CenterSeoulRepublic of Korea

Personalised recommendations