Journal of Digital Imaging

, Volume 24, Issue 3, pp 382–393 | Cite as

An Automatic Computer-Aided Detection Scheme for Pneumoconiosis on Digital Chest Radiographs

  • Peichun Yu
  • Hao Xu
  • Ying Zhu
  • Chao Yang
  • Xiwen Sun
  • Jun Zhao
Article

Abstract

This paper presents an automatic computer-aided detection scheme on digital chest radiographs to detect pneumoconiosis. Firstly, the lung fields are segmented from a digital chest X-ray image by using the active shape model method. Then, the lung fields are subdivided into six non-overlapping regions, according to Chinese diagnosis criteria of pneumoconiosis. The multi-scale difference filter bank is applied to the chest image to enhance the details of the small opacities, and the texture features are calculated from each region of the original and the processed images, respectively. After extracting the most relevant ones from the feature sets, support vector machine classifiers are utilized to separate the samples into the normal and the abnormal sets. Finally, the final classification is performed by the chest-based report-out and the classification probability values of six regions. Experiments are conducted on randomly selected images from our chest database. Both the training and the testing sets have 300 normal and 125 pneumoconiosis cases. In the training phase, training models and weighting factors for each region are derived. We evaluate the scheme using the full feature vectors or the selected feature vectors of the testing set. The results show that the classification performances are high. Compared with the previous methods, our fully automated scheme has a higher accuracy and a more convenient interaction. The scheme is very helpful to mass screening of pneumoconiosis in clinic.

Key words

Pneumoconiosis digital radiography computer-aided detection (CAD) active shape model (ASM) texture analysis support vector machine (SVM) 

References

  1. 1.
    International Labor Organization (ILO): Guidelines for the use of the ILO international classification of radiographs of pneumoconioses. Occupational Safety and Health Series, No. 22 (Rev.). International Labor Office, Geneva Switzerland, 1980Google Scholar
  2. 2.
    Hering KG, Jacobsen M, Bosch-Galetke E: Further development of the International Pneumoconiosis Classification—from ILO 1980 to ILO 2000 and to ILO 2000/German Federal Republic version. Pneumologie 57(10):576–584, 2003PubMedCrossRefGoogle Scholar
  3. 3.
    Hodous TK, Chen RA, Kinsley KB: A comparison of pneumoconiosis interpretation between Chinese and American reader and classifications. J Tongji Med Univ 11(4):225–229, 1991PubMedCrossRefGoogle Scholar
  4. 4.
    Ginneken BV, Romeny BM, Viergever MA: Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imag 20(12):1228–1241, 2001CrossRefGoogle Scholar
  5. 5.
    Elter M, Horsch A: CADx of mammographic masses and lustered microcalcifications: a review. Med Phys 36(6):2052–2068, 2009PubMedCrossRefGoogle Scholar
  6. 6.
    Giger ML, Chan HP, Boone J: Anniversary paper: history and status of CAD and quantitative image analysis: the role of medical physics and AAPM. Med Phys 35(12):5799–5820, 2008PubMedCrossRefGoogle Scholar
  7. 7.
    Doi K: Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31:198–211, 2007PubMedCrossRefGoogle Scholar
  8. 8.
    Kruger RP, Thompson WB, Turner AF: Computer diagnosis of pneumoconiosis. IEEE Trans Syst Man Cybern 4(1):40–49, 1974Google Scholar
  9. 9.
    Ledley RS, Huang HK, Rotolo LS: A texture analysis method in classification of coal workers’ pneumoconiosis. Comput Biol Med 5(1–2):53–67, 1974Google Scholar
  10. 10.
    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(5):479–482, 1980Google Scholar
  11. 11.
    Hall EL, Crawford WO, Roberts FE: Computer classification of pneumoconiosis from radiographs of coal workers. IEEE Trans Biomed Eng 22(6):518–527, 1975PubMedCrossRefGoogle Scholar
  12. 12.
    Kobatake H, Ohishi K, Miyamichi J: Automatic diagnosis of pneumoconiosis by texture analysis of chest X-ray images. IEEE ICASSP 12:610–613, 1987Google Scholar
  13. 13.
    Ugurlu Y, Ohkura K, Obi T: Detection of increasing profusion of opacities from a sequence of personal chest radiographs. IEEE Int Conf Image Proc 3:402–406, 1999Google Scholar
  14. 14.
    Huang Z, Yu D, Zhao J: Application of neural networks with linear and nonlinear weights in occupational disease incidence forecast. IEEE Asia-Pacific Conference on Circuits and Systems 383–386, 2000Google Scholar
  15. 15.
    Kondo H, Kouda T: Detection of pneumoconiosis rounded opacities using neural network. Joint 9th IFSA World Congress and 20th NAFIPS International Conference 3: 1581–1585, 2001Google Scholar
  16. 16.
    Kondo H, Kouda T: Computer-aided diagnosis for pneumoconiosis using neural network. IEEE Symposium on Computer-Based Systems 467–472, 2001Google Scholar
  17. 17.
    Soliz P, Pattichis MS, Ramachandran J. Computer-assisted diagnosis of chest radiographs for pneumoconioses. Proceedings of SPIE 667–675, 2001Google Scholar
  18. 18.
    Pattichis MS, Pattichis CS, Christodoulou CI: A screening system for the assessment of opacity profusion in chest radiographs of miners with pneumoconiosis. Fifth IEEE Southwest Symposium on Image Analysis and Interpretation 130–133, 2002Google Scholar
  19. 19.
    Ginneken BV: Computer-aided diagnosis in chest radiography. Med Phys 28(6):1144–1150, 2001CrossRefGoogle Scholar
  20. 20.
    Li L: Improved method for automatic identification of lung regions on chest radiographs. Acad Radiol 8(7):629–638, 2001PubMedCrossRefGoogle Scholar
  21. 21.
    Vittitoe NF, Vargas-Voracek R, Floyd CE: Identification of lung regions in chest radiographs using Markov random field modeling. Med Phys 25(6):976–985, 1998PubMedCrossRefGoogle Scholar
  22. 22.
    Ginneken BV, Frangi AF, Staal JJ: Active shape model segmentation with optimal features. IEEE Trans Med Imag 21(8):924–933, 2002CrossRefGoogle Scholar
  23. 23.
    Iglesias I, Souto M, Alegria AM: Lung segmentation on postero-anterior digital chest radiographs using active contours. Lect Notes Comput Sci 3138:538–546, 2004CrossRefGoogle Scholar
  24. 24.
    Cootes TF, Taylor CJ, Cooper DH: Active shape models-their training and application. Comput Vis Image Underst 61(1):38–59, 1995CrossRefGoogle Scholar
  25. 25.
    Cootes TF, Taylor CJ: Statistical models of appearance for computer vision. Wolfson Image Analysis Unit. University of Manchester, Manchester, UK, 1999. Tech. RepGoogle Scholar
  26. 26.
    Katsuragawa S, Doi K: Computer-aided diagnosis in chest radiography. Comput Med Imaging Graph 31:212–222, 2007PubMedCrossRefGoogle Scholar
  27. 27.
    Ginneken BV, Katsuragawa S, Romeny BM: Automatic detection of abnormalities in chest radiographs using local texture analysis. IEEE Trans Med Imag 21(2):139–148, 2002CrossRefGoogle Scholar
  28. 28.
    Sutton RN, Hall EL: Texture measures for automatic classification of pulmonary disease. IEEE Trans Comput 21:667–676, 1972CrossRefGoogle Scholar
  29. 29.
    Jagoe JR, Paton KA: Reading chest radiographs for pneumoconiosis by computer. Br J Ind Med 32:367–372, 1975Google Scholar
  30. 30.
    Tully RJ, Connors RW, Harlow CA: Toward computer analysis of pulmonary infiltration. Investigat Radiol 13:198–305, 1978CrossRefGoogle Scholar
  31. 31.
    Jagoe JR: Gradient pattern coding-an application to the measurement of pneumoconiosis in chest X-rays. Comput Biomed Res 12:1–15, 1979PubMedCrossRefGoogle Scholar
  32. 32.
    Witten IH: Data mining: practical machine learning tools and techniques. Morgan Kaufmann, San Francisco, 2005, pp 369–424Google Scholar
  33. 33.
    Arya S, Mount DM: Approximate nearest neighbor queries in fixed dimensions. Proc. 4th ACM-ALAM Symp. Discrete Algorithms 271–280, 1993Google Scholar
  34. 34.
    Vapnik VN: The nature of statistical learning theory. Springer, New York, 199, pp 4–80Google Scholar
  35. 35.
    Burges JC: A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2:121–167, 1998CrossRefGoogle Scholar
  36. 36.
    Breiman L: Random forests. Mach Learn 45:5–32, 2001CrossRefGoogle Scholar
  37. 37.
    Breiman L, Friedman J, Olshen R: Classification and regression trees. Chapman & Hall, New York, 1984Google Scholar
  38. 38.
    Ripley BD: Pattern recognition and neural networks. Cambridge University Press, Cambridge, 1996Google Scholar
  39. 39.
    Hastie T, Tibshirani R, Friedman J: The elements of statistical learning. Springer, New York, 2001Google Scholar
  40. 40.
    Park SH, Goo JM, Jo CH: Receiver operating characteristic (ROC) curve: practical review for radiologitst. Korean J Radiol 5(1):11–18, 2004PubMedCrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2010

Authors and Affiliations

  • Peichun Yu
    • 1
  • Hao Xu
    • 2
  • Ying Zhu
    • 1
  • Chao Yang
    • 2
  • Xiwen Sun
    • 3
  • Jun Zhao
    • 1
  1. 1.Department of Biomedical EngineeringSchool of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityShanghaiChina
  2. 2.Imaging Technologies LabGE Global ResearchShanghaiChina
  3. 3.Shanghai Pulmonary HospitalShanghaiChina

Personalised recommendations