Academic Radiology
Volume 17, Issue 5 , Pages 595-602 , May 2010

Neural Network Ensemble-Based Computer-Aided Diagnosis for Differentiation of Lung Nodules on CT Images: Clinical Evaluation

  • Hui Chen, PhD

      Affiliations

    • Institute of Biomedical Engineering, Capital Medical University, No.10 Xitoutiao, You An Men, Fengtai District, Beijing, P.R. China, 100069
    • ,
  • Yan Xu, MM

      Affiliations

    • Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No.10 Xitoutiao, You An Men, Fengtai District, Beijing, P.R. China, 100069
    • ,
  • Yujing Ma, BE

      Affiliations

    • Institute of Biomedical Engineering, Capital Medical University, No.10 Xitoutiao, You An Men, Fengtai District, Beijing, P.R. China, 100069
    • ,
  • Binrong Ma, MM

      Affiliations

    • Institute of Biomedical Engineering, Capital Medical University, No.10 Xitoutiao, You An Men, Fengtai District, Beijing, P.R. China, 100069
    • Corresponding Author InformationAddress correspondence to: B.M.

Received 8 July 2009 ,Accepted 9 December 2009.

References 

  1. Flehinger BJ, Kimmel M, Melamed MR. The effect of surgical treatment on survival from early lung cancer: implication for screening. Chest. 1992;101:1013–1018
  2. Sobue T, Suzuki R, Matsuda M, et al. Survival for clinical stage I lung cancer not surgically treated. Cancer. 1992;69:685–692
  3. Mittinen OS. Screening for lung cancer. Radiol Clin N Am. 2000;38:479–496
  4. Matsuki Y, Nakamura K, Watanabe H, et al. Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high resolution CT: evaluation with receiver operating characteristic analysis. Am J Roentgenol. 2002;178:657–663
  5. Shiraishi J, Abe H, Engelmann R, et al. Computer-aided diagnosis to distinguish benign from malignant solitary pulmonary nodules on radiographs: ROC analysis of radiologists' performance—initial experience. Radiology. 2003;227:469–474
  6. Sluimer IC, van Waes PF, Viergever MA, et al. Computer-aided diagnosis in high resolution CT of the lungs. Med Phys. 2003;30:3081–3090
  7. Aoyama M, Li Q, Katsuragawa S, et al. Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images. Med Phys. 2003;30:387–394
  8. Li F, Aoyama M, Shiraishi J, et al. Radiologists' performance for differentiating benign from malignant lung nodules on high-resolution CT using computer-estimated likelihood of malignancy. Am J Roentgenol. 2004;183:1209–1215
  9. Li Q, Li F, Suzuki K, et al. Computer-aided diagnosis in thoracic CT. Semin Ultrasound CT. 2005;26:357–363
  10. Shah SK, McNitt-Gray MF, Rogers SR, et al. Computer-aided diagnosis of the solitary pulmonary nodule. Acad Radiol. 2005;12:570–575
  11. Suzuki K, Li F, Sone S, et al. Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network. IEEE T Med Imaging. 2005;24:1138–1150
  12. Shiraishi J, Abe H, Li F, et al. Computer-aided diagnosis for the detection and classification of lung cancers on chest radiographs: ROC analysis of radiologists' performance. Acad Radiol. 2006;13:995–1003
  13. Awai K. Pulmonary Nodules: estimation of malignancy at thin-section helical CT—effect of computer-aided diagnosis on performance of radiologists. Radiology. 2006;239:276–284
  14. Chen H, Wang XH, Ma DQ, et al. Neural network-based computer-aided diagnosis in distinguishing malignant from benign solitary pulmonary nodules by computed tomography. Chinese Med J-Peking. 2007;120:1211–1215
  15. Silva EC, Silva AC, Paiva AC, et al. Diagnosis of lung nodule using Moran's index and Geary's coefficient in computerized tomography images. Pattern Anal Applic. 2008;11:89–99
  16. Yeh C, Lin CL, Wu MT, et al. A neural network-based diagnostic method for solitary pulmonary nodules. Neurocomputing. 2008;72:612–624
  17. Way TW. Computer-aided diagnosis of pulmonary nodules in thoracic computed tomography. Doctoral Dissertation, University of Michigan; 2008;138–165
  18. Way TW, Sahiner B, Chan HP, et al. Computer-aided diagnosis of pulmonary nodules on CT scans: improvement of classification performance with nodule surface features. Med Phys. 2009;36:3086–3098
  19. Doi K. Current status and future potential of computer-aided diagnosis in medical imaging. Br J Radiol. 2005;78:S3–S19
  20. Armato SG, McLennan G, McNitt-Gray MF, et al. Lung image database consortium: developing a resource for the medical imaging research community. Radiology. 2004;232:739–748
  21. National Biomedical Imaging Archive. Available at: https://imaging.nci.nih.gov/nciaAccessed May 21, 2009
  22. Canny J. A computational approach to edge detection. IEEE T Pattern Anal. 1986;8:679–698
  23. Giorgio G, Fabio R. Design of effective neural network ensembles for image classification purposes. Image Vision Comput. 2001;19:699–707
  24. Lam L, Suen CY. Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE T Syst Man Cy A. 1997;27:553–568
  25. Partridge D. Network generalization differences quantified. Neural Networks. 1996;9:263–271
  26. Asuncion A, Newman DJ. UCI Machine Learning Repository. Available at: http://www.ics.uci.edu/∼mlearn/MLRepository.htmlAccessed July 21, 2008
  27. Metz CE, Herman BA, Shen JH. Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. Stat Med. 1998;17:1033–1053
  28. Pan X, Metz CE. The “proper” binormal model: parametric ROC curve estimation with degenerate data. Acad Radiol. 1997;4:380–389
  29. McClish DK. Analyzing a portion of the ROC curve. Med Decis Making. 1989;9:190–195
  30. Obuchowski NA. Receiver operating characteristic curves and their use in radiology. Radiology. 2003;229:3–8
  31. Jiang Y, Metz CE, Nishikawa RM. A receiver operating characteristic partial area index for highly sensitive diagnostic tests. Radiology. 1996;201:745–750
  32. Daly L, Bourke GJ. Interpretation and uses of medical statistics. 5th ed.. Hoboken, NJ: Wiley-Blackwell; 2000;410
  33. Das R, Turkoglu I, Sengur A. Diagnosis of valvular heart disease through neural networks ensembles. Comput Meth Prog Bio. 2009;39:185–191
  34. Osowski S, Markiewicz T, Hoai LT. Recognition and classification system of arrhythmia using ensemble of neural networks. Measurement. 2008;41:610–617
  35. Daskalakis A, Kostopoulos S, Spyridonos P, et al. Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images. Comput Biol Med. 2008;38:196–203
  36. Zhou ZH, Jiang Y, Yang YB, et al. Lung cancer cell identification based on artificial neural network ensembles. Artif Intell Med. 2002;24:25–36
  37. Shah SK, McNitt-Gray MF, De Zoysa KR, et al. Solitary pulmonary nodule diagnosis on CT: results of an observer study. Acad Radiol. 2005;12:496–501
  38. Erasmus JJ, McAdams HP, Connolly JE. Solitary pulmonary nodules. Part II. Evaluation of the indeterminate nodule. Radio Graphics. 2000;20:59–66
  39. Swensen SJ, Viggiano RW, Midthun DE, et al. Lung nodule enhancement at CT: multicenter study. Radiology. 2000;214:73–80
  40. Yi CA, Lee KS, Kim EA, et al. Solitary pulmonary nodules: dynamic enhanced multi-detector row CT study and comparison with vascular endothelial growth factor and microvessel density. Radiology. 2004;233:191–199
  41. Jeong YJ, Lee KS, Jeong SY, et al. Solitary pulmonary nodule: characterization with combined washin and washout features at dynamic multi-detector row CT. Radiology. 2005;237:675–683
  42. Lowe VJ, Fletcher JW, Gobar L, et al. Prospective investigation of positron emission tomography in lung nodules. J Clin Oncol. 1998;16:1075–1084

 Supported by The Basic & Clinical Cooperative Research Foundation of Capital Medical University (No. 2007JL07) and Beijing Training Program Foundation for the Excellent Talents (No. 20061D0501800251).

PII: S1076-6332(09)00685-0

doi: 10.1016/j.acra.2009.12.009

Academic Radiology
Volume 17, Issue 5 , Pages 595-602 , May 2010

Article Tools

* Image Usage & Resolution