Journal of Digital Imaging

, Volume 27, Issue 1, pp 90–97 | Cite as

Support Vector Machine Model for Diagnosing Pneumoconiosis Based on Wavelet Texture Features of Digital Chest Radiographs

  • Biyun Zhu
  • Hui Chen
  • Budong Chen
  • Yan Xu
  • Kuan Zhang


This study aims to explore the classification ability of decision trees (DTs) and support vector machines (SVMs) to discriminate between the digital chest radiographs (DRs) of pneumoconiosis patients and control subjects. Twenty-eight wavelet-based energy texture features were calculated at the lung fields on DRs of 85 healthy controls and 40 patients with stage I and stage II pneumoconiosis. DTs with algorithm C5.0 and SVMs with four different kernels were trained by samples with two combinations of the texture features to classify a DR as of a healthy subject or of a patient with pneumoconiosis. All of the models were developed with fivefold cross-validation, and the final performances of each model were compared by the area under receiver operating characteristic (ROC) curve. For both SVM (with a radial basis function kernel) and DT (with algorithm C5.0), areas under ROC curves (AUCs) were 0.94 ± 0.02 and 0.86 ± 0.04 (P = 0.02) when using the full feature set and 0.95 ± 0.02 and 0.88 ± 0.04 (P = 0.05) when using the selected feature set, respectively. When built on the selected texture features, the SVM with a polynomial kernel showed a higher diagnostic performance with an AUC value of 0.97 ± 0.02 than SVMs with a linear kernel, a radial basis function kernel and a sigmoid kernel with AUC values of 0.96 ± 0.02 (P = 0.37), 0.95 ± 0.02 (P = 0.24), and 0.90 ± 0.03 (P = 0.01), respectively. The SVM model with a polynomial kernel built on the selected feature set showed the highest diagnostic performance among all tested models when using either all the wavelet texture features or the selected ones. The model has a good potential in diagnosing pneumoconiosis based on digital chest radiographs.


Pneumoconiosis Classification Wavelet transform Texture feature Decision tree Support vector machine 



This work was partially supported by the Science and Technology Project of Beijing Municipal Education Commission, China (No. KM201110025008). The authors are grateful to Dr. Haiying Quan for the helpful suggestions.


  1. 1.
    International Labor Organization (ILO): Guidelines for the use of the ILO international classification of radiographs of pneumoconiosis. Occupational Safety and Health Series, No. 22 (Rev.). International Labor Office, Geneva Switzerland, 1980.Google Scholar
  2. 2.
    Savol AM, Li CC, Hoy RJ: Computer-aided recognition of small rounded pneumoconiosis opacities in chest X-rays. IEEE Trans Pattern Anal Mach Intell 2:479–482, 1980CrossRefGoogle Scholar
  3. 3.
    Hall EL, Crawford WO, Roberts FE: Computer classification of pneumoconiosis from radiographs of coal workers. IEEE Trans Biomed Eng 22:518–527, 1975PubMedCrossRefGoogle Scholar
  4. 4.
    Yu P, Xu H, Zhu Y, Yang C, Sun X, Zhao J, et al: An automatic computer-aided detection scheme for pneumoconiosis on digital chest radiographs. J Digit Imaging 24:382–393, 2011PubMedCentralPubMedCrossRefGoogle Scholar
  5. 5.
    Xu H, Tao X, Sundararajan R, et al.: Computer aided detection for pneumoconiosis screening on digital chest radiographs. Proc. Third International Workshop on Pulmonary Image Analysis, 129–138, 2010.Google Scholar
  6. 6.
    Okumura E, Kawashita I, Ishida T: Computerized analysis of pneumoconiosis in digital chest radiography: effect of artificial neural network trained with power spectra. J Digit Imaging 24:1126–1132, 2011PubMedCentralPubMedCrossRefGoogle Scholar
  7. 7.
    Cai C, Zhu B, Chen H: Computer-aided diagnosis for pneumoconiosis based on texture analysis on digital chest radiographs. Proceedings of International Conference on Electronic, Communication and Computer Science. Guilin, China, 2012 June 15–17.Google Scholar
  8. 8.
    Chen H, Zhang J, Xu Y, Chen B, Zhang K: Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans. Expert Syst Appl 39:11503–11509, 2012CrossRefGoogle Scholar
  9. 9.
    Zhu B, Chen H: Morphological reconstruction based segmentation of lung fields on digital radiographs. Proceedings of International Conference on Electronic, Communication and Computer Science. Guilin, China, 2012 June 15–17.Google Scholar
  10. 10.
    Arivazhagan S, Ganesan L: Texture segmentation using wavelet transform. Pattern Recogn Lett 24:3197–3203, 2003CrossRefGoogle Scholar
  11. 11.
    Kociołek M, Materka A, Strzelecki M, Szczypiński P: Discrete wavelet transform-derived features for digital image texture analysis. Proceedings of International Conference on Signals and Electronic Systems. Lodz, Poland, 2001 September 18–21.Google Scholar
  12. 12.
    Quinlan JR: Induction decision tree. Mach Learn 1:81–106, 1986Google Scholar
  13. 13.
    Li C, Zhi X, Ma J, Cui Z, Zhu Z, Zhang C, et al: Performance comparison between logistic regression, decision trees, and multilayer perceptron in predicting peripheral neuropathy in type 2 diabetes mellitus. Chin Med J (Engl) 125:851–857, 2012Google Scholar
  14. 14.
    Maimon O, Rokach L: Data Mining and Knowledge Discovery Handbook, 2nd edition. Springer, New York, 2010CrossRefGoogle Scholar
  15. 15.
    Zhu Y, Tan Y, Hua Y, Wang M, Zhang G, Zhang J: Feature selection and performance evaluation of support vector machine (SVM)-based classifier for differentiating benign and malignant pulmonary nodules by computed tomography. J Digit Imaging 23:51–65, 2010PubMedCentralPubMedCrossRefGoogle Scholar
  16. 16.
    Shawe-Taylor J, Cristianini N: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge, 2004CrossRefGoogle Scholar
  17. 17.
    Olson DL, Delen D: Advanced Data Mining Techniques. Springer, LLC, Berlin, 2008Google Scholar
  18. 18.
    Kondo H, Zhao B, Mino M: Automated quantitative analysis for pneumoconiosis. Proceedings of International Symposium on Multispectral Image Processing. Wuhan, China, 1998 Oct 21–23.Google Scholar
  19. 19.
    Chen X, Toriwaki J, Hasegawa J: Automated classification of pneumoconiosis radiographs based on recognition of small rounded opacities. Syst Comput Jpn 21:33–44, 1990CrossRefGoogle Scholar
  20. 20.
    Murray V, Pattichis MS, Davis H, Barriga ES, Soliz P: Multiscale AM-FM analysis of pneumoconiosis x-ray images. Proceedings of IEEE International Conference on Image Processing. Kochi, India, 2009 Nov 7–10.Google Scholar
  21. 21.
    Delen D, Walker G, Kadam A: Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med 34:113–127, 2005PubMedCrossRefGoogle Scholar
  22. 22.
    McLaren CE, Chen WP, Nie K, Su MY: Prediction of malignant breast lesions from MRI features: a comparison of artificial neural network and logistic regression techniques. Acad Radiol 16:842–851, 2009PubMedCentralPubMedCrossRefGoogle Scholar
  23. 23.
    Mohamed MM, Abdel-Galil TK, Salama MA, EI-Saadany EF, Kamel M, Fenster A, Downey DB, Rizkalla K: Prostate cancer diagnosis based on Gabor filter texture segmentation of ultrasound image. Proc IEEE Can Conf Electr Comput Eng 3:1485–1488, 2003Google Scholar
  24. 24.
    Bárbara B, Pineda-Bautista JA, Carrasco-Ochoa J: Fco Martínez-Trinidad: General framework for class-specific feature selection. Expert Syst Appl 38:10018–10024, 2011CrossRefGoogle Scholar
  25. 25.
    Hastie T, Tibshirani R, Friedman J: The Elements of Statistical Learning, 2nd edition. Springer, New York, 2009CrossRefGoogle Scholar
  26. 26.
    Lim T, Loh W, Shih Y: A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms. Mach Learn 40:203–228, 2000CrossRefGoogle Scholar
  27. 27.
    Elangovan M, Sugumaran V, Ramachandran KI, Ravikumar S: Effect of SVM kernel functions on classification of vibration signals of a single point cutting tool. Expert Syst Appl 38:15202–15207, 2011CrossRefGoogle Scholar
  28. 28.
    Islam T, Rico-Ramirez MA, Han D, Srivastava PK: Artificial intelligence techniques for clutter identification with polarimetric radar signatures. Atmos Res 109:95–113, 2012CrossRefGoogle Scholar
  29. 29.
    Marjanovic M, Kovacevic M, Bajat B, Vozenilek V: Landslide susceptibility assessment using SVM machine learning algorithm. Eng Geol 123:225–234, 2011CrossRefGoogle Scholar
  30. 30.
    Han J, Kamber M: Data Mining: Concepts and Techniques, 2nd edition. Elsevier, Maryland Heights, 2006Google Scholar
  31. 31.
    Way TW, Sahiner B, Hadjiiski LM, Chan HP: Effect of finite sample size on feature selection and classification: a simulation study. Med Phys 37:907–920, 2010PubMedCrossRefGoogle Scholar
  32. 32.
    Sahiner B, Chan HP, Hadjiiski L: Classifier performance prediction for computer-aided diagnosis using a limited dataset. Med Phys 35:1559–1570, 2008PubMedCrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2013

Authors and Affiliations

  • Biyun Zhu
    • 1
  • Hui Chen
    • 1
  • Budong Chen
    • 2
  • Yan Xu
    • 2
  • Kuan Zhang
    • 1
  1. 1.School of Biomedical EngineeringCapital Medical UniversityBeijingChina
  2. 2.Department of Radiology, Beijing Friendship HospitalCapital Medical UniversityBeijingChina

Personalised recommendations