Automatic Detection and Segmentation of Ground Glass Opacity Nodules

  • Jinghao Zhou
  • Sukmoon Chang
  • Dimitris N. Metaxas
  • Binsheng Zhao
  • Lawrence H. Schwartz
  • Michelle S. Ginsberg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4190)


Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (nonsolid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and inter- or intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting k-NN, whose distance measure is the Euclidean distance between the nonparametric density estimates of two examples. The detected GGO region is then automatically segmented by analyzing the texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO.


Automatic Detection Ground Glass Opacity Nonparametric Density Estimate Standard Euclidean Distance False Positive Nodule 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Austin, J., Muller, N., Friedman, P., et al.: Glossary of terms for CT of the lung: recommendations of the nomenclature committee of the fleischner society. Radiology 200, 327–331 (1996)Google Scholar
  2. 2.
    Henschke, C., Yankelevitz, D., Mirtcheva, R.: CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules. Am. J. Roentgenol. 178, 1053–1057 (2002)Google Scholar
  3. 3.
    Jang, H., Lee, K., Kwon, O., Rhee, C., Shim, Y., Han, J.: Bronchioloalveolar carcinoma: Focal area of ground-glass attenuation at thin-section CT as an early sign. Radiology 199, 485–488 (1996)Google Scholar
  4. 4.
    Kuriyama, K., Seto, M., Kasugai, T., Higashiyama, M., Kido, S., Sawai, Y., Kodama, K., Kuroda, D.: Ground-glass opacity on thin-section CT: Value in differentiating subtypes of adenocarcinoma of the lung. Am. J. Roentgenol. 173, 465–469 (1999)Google Scholar
  5. 5.
    Watanabe, S., Watanabe, T., Arai, K., Kasai, T., Haratake, J., Urayama, H.: Results of wedge resection for focal bronchioloalveolar carcinoma showing pure ground-glass attenuation on computed tomography. Ann. Thorac. Surg. 73, 1071–1075 (2002)CrossRefGoogle Scholar
  6. 6.
    Heitmann, K., Kauczor, H.U., Mildenberger, P., Uthmann, T., Perl, J., Thelen, M.: Automatic detection of ground glass opacities on lung HRCT using multiple neural networks. European Radiology 7, 1463–1472 (1997)CrossRefGoogle Scholar
  7. 7.
    Tanino, M., Takizawa, H., Yamamoto, S., Matsumoto, T., Tateno, Y., Iinuma, T.: A detection method of ground glass opacities in chest x-ray CT images using automatic clustering techniques. In: SPIE, vol. 5032, pp. 1728–1737 (2003)Google Scholar
  8. 8.
    Zhang, L., Fang, M., Naidich, D., Novak, C.: Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies. In: SPIE, vol. 5370, pp. 1709–1719 (2004)Google Scholar
  9. 9.
    Chang, S., Emoto, H., Metaxas, D., Axel, L.: Pulmonary micronodule detection from 3D chest CT. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 821–828. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: The 13th International Conference on Machine Learning, pp. 148–156 (1996)Google Scholar
  11. 11.
    Huang, X., Qian, Z., Huang, R., Metaxas, D.: Deformable-Model Based Textured Object Segmentation. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 119–135. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Lorenz, C., Carlsen, I.C., Buzug, T., Fassnacht, C., Weese, J.: Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. In: Troccaz, J., Mösges, R., Grimson, W.E.L. (eds.) CVRMed-MRCAS 1997, CVRMed 1997, and MRCAS 1997. LNCS, vol. 1205, pp. 233–242. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  13. 13.
    Ali, S., Silvey, S.: A general class of coefficients of divergence of one distribution from another. J. Roy. Stat. Soc. 28, 131–142 (1966)MATHMathSciNetGoogle Scholar
  14. 14.
    Chernoff, H.: Large-sample theory: Parametric case. Ann. Math. Stat. 27, 1–22 (1956)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Zhou, J., Chang, S., Metaxas, D., Axel, L.: Vessel boundary extraction using ridge scan-conversion and the deformable model. In: ISBI, pp. 189–192 (2006)Google Scholar
  16. 16.
    Efron, B.: Estimating the error rate of a prediction rule: Improvement on cross-validation. Journal of the American Statistical Association 78, 316–331 (1983)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jinghao Zhou
    • 1
  • Sukmoon Chang
    • 1
    • 2
  • Dimitris N. Metaxas
    • 1
  • Binsheng Zhao
    • 3
  • Lawrence H. Schwartz
    • 3
  • Michelle S. Ginsberg
    • 3
  1. 1.CBIM, RutgersThe State University of New JerseyUSA
  2. 2.Computer Science, Capital CollegePenn State UniversityMiddletownUSA
  3. 3.Department of RadiologyMemorial Sloan-Kettering Cancer CenterUSA

Personalised recommendations