Quantitative Analysis of Pulmonary Emphysema using Isotropic Gaussian Markov Random Fields

Chathurika Dharmagunawardhana, Sasan Mahmoodi, Michael Bennett, Mahesan Niranjan

2014

Abstract

A novel texture feature based on isotropic Gaussian Markov random fields is proposed for diagnosis and quantification of emphysema and its subtypes. Spatially varying parameters of isotropic Gaussian Markov random fields are estimated and their local distributions constructed using normalized histograms are used as effective texture features. These features integrate the essence of both statistical and structural properties of the texture. Isotropic Gaussian Markov Random Field parameter estimation is computationally efficient than the methods using other MRF models and is suitable for classification of emphysema and its subtypes. Results show that the novel texture features can perform well in discriminating different lung tissues, giving comparative results with the current state of the art texture based emphysema quantification. Furthermore supervised lung parenchyma tissue segmentation is carried out and the effective pathology extents and successful tissue quantification are achieved.

References

  1. Coxson, H. O., Rogers, R. M., Whittall, K. P., Yachkova, Y. D., Par, P. D., Sciurba, F. C., and Hogg, J. C. (1999). A quantification of the lung surface area in emphysema using computed tomography. 159 (3):851-6.
  2. Depeursinge, A., Iavindrasana, J., Hidki, A., Cohen, G., Geissbuhler, A., Platon, A., Poletti, P., and Müller, H. (2010). Comparative performance analysis of state-ofthe-art classification algorithms applied to lung tissue categorization. Journal of digital imaging, 23(1):18- 30.
  3. Depeursinge, A., Sage, D., Hidki, A., Platon, A., Poletti, P. A., Unser, M., and Muller, H. (2007). Lung tissue classification using wavelet frames. In Proc. IEEE Int'l conf. of the Engineering in Medicine and Biology Society, pages 6259-6262. IEEE.
  4. Dharmagunawardhana, C., Mahmoodi, S., Bennett, M., and Mahesan, N. (2012). Unsupervised texture segmentation using active contours and local distributions of Gaussian Markov random field parameters. In Proc. British Machine Vision Conference, pages 88.1- 88.11.
  5. Gangeh, M. J., Sørensen, L., Shaker, S. B., Kamel, M. S., Bruijne, M., and Loog, M. (2010). A texton-based approach for the classification of lung parenchyma in CT images. 13:595-602.
  6. Häme, Y., Angelini, E. D., Hoffman, E. A., Barr, R. G., and Laine, A. F. (2013). Robust quantification of pulmonary emphysema with a hidden Markov measure field model. In Proc. 10th IEEE Int'l Symposium on Biomedical Imaging, pages 382-385. IEEE.
  7. Hara, T., Yamamoto, A., Zhou, X., Iwano, S., Itoh, S., Fujita, H., and Ishigaki, T. (2004). Automated detection system for pulmonary emphysema on 3D chest CT images. In Proc. of SPIE, pages 915-919.
  8. Kashyap, R. L. and Khotanzad, A. (1986). A model-based method for rotation invariant texture classification. IEEE Trans. on Pattern Analysis and Machine Intelligence, (4):472-481.
  9. Kim, N., Seo, J. B., Lee, Y., Lee, J. G., Kim, S. S., , and Kang, S. (2009). Development of an automatic classification system for differentiation of obstructive lung disease using hrct. Journal of digital imaging, 22(2):136-148.
  10. Li, S. Z. (2009). Markov Random Field Modeling in Image Analysis. Springer-Verlag London Ltd, 3rd edn edition.
  11. Litmanovich, D., Boiselle, P. M., and Bankier, A. (2009). CT of pulmonary emphysema - current status, challenges, and future directions. 19:537-51.
  12. Madani, A., Keyzer, C., and AGevenois, P. (2001). Quantitative computed tomography assessment of lung structure and function in pulmonary emphysema. 18 (4):720-30.
  13. Mahmoodi, S. and Gunn, S. (2011). Snake based unsupervised texture segmentation using Gaussian Markov random field models. In Proc. 18th IEEE Int'l Conf. Image Processing, pages 1-4.
  14. Manjunath, B. S. and Chellappa, R. (1991). Unsupervised texture segmentation using Markov random field models. IEEE Trans. on pattern analysis and machine intelligence, 13(5):478-482.
  15. Mishima, M., T. Hirai, H. I., Nakano, Y., Sakai, H., Muro, S., Nishimura, K., Oku, Y., Chin, K., Ohi, M., Nakamura, T., Bates, J. H. T., Alencar, A. M., and Suki, B. L. (1999). Complexity of terminal airspace geometry assessed by lung computed tomography in normal subjects and patients with chronic obstructive pulmonary disease. In Proceedings of the National Academy of Sciences, volume 96, pages 8829-8834.
  16. Muller, N., Staples, C., and R. Miller, R. A. (1988). Density mask, an objective method to quantitate emphysema using computed tomography. 94:782-787.
  17. Ojala, T., Pietikainen, M., and Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. on pattern analysis and machine intelligence, 24:971- 987.
  18. Petrou, M. and Sevilla, P. G. (2006). Image Processing, Dealing with Texture. John Wiley & Sons Ltd.
  19. Rue, H. and Held, L. (2005). Gaussian Markov Random Fields; Theory and Applications. Chapman & Hall/CRC.
  20. Sluimer, I. C., Waes, P. F., Viergever, M., and Ginneken, B. (2003). Computer-aided diagnosis in high resolution CT of the lungs. 30:3081.
  21. Sørensen, L., Shaker, S. B., and de Bruijne, M. (2010). Quantitative analysis of pulmonary emphysema using local binary patterns. IEEE Transactions on Medical Imaging, 29(2):559-569.
  22. Sørensen, L., Shaker, S. B., and de Bruijne, M. (2013). Computed Tomography Emphysema Database. http://image.diku.dk/emphysema database/.
  23. Sprawls, P. (1995). The Physical Principles of Medical Imaging. Medical Physics Publishing, USA, 2nd edition.
  24. Uppaluri, R., Hoffman, E., M.Sonka, Hartley, P. G., W.Hunninghake, G., and McLennan, G. (1999). Computer recognition of regional lung disease patterns. 160 (2):648-54.
  25. Vasconcelos, V., Silva, J. S., Marques, L., and Barroso, J. (2010). Statistical textural features for classification of lung emphysema in CT images: A comparative study. In Information Systems and Technologies (CISTI), pages 1-5. IEEE.
  26. Xu, Y., Sonka, M., McLennan, G., Guo, J., and Hoffman, E. A. (2006). MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies. 156 (1):25.
  27. Zhao, Y., Zhang, L., Li, P., and Huang, B. (2007). Classification of high spatial resolution imagery using improved Gaussian Markov random-field-based texture features. IEEE Trans. on Geoscience and Remote Sensing, 45(5):1458-1468.
Download


Paper Citation


in Harvard Style

Dharmagunawardhana C., Mahmoodi S., Bennett M. and Niranjan M. (2014). Quantitative Analysis of Pulmonary Emphysema using Isotropic Gaussian Markov Random Fields . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 44-53. DOI: 10.5220/0004728900440053


in Bibtex Style

@conference{visapp14,
author={Chathurika Dharmagunawardhana and Sasan Mahmoodi and Michael Bennett and Mahesan Niranjan},
title={Quantitative Analysis of Pulmonary Emphysema using Isotropic Gaussian Markov Random Fields},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={44-53},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004728900440053},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Quantitative Analysis of Pulmonary Emphysema using Isotropic Gaussian Markov Random Fields
SN - 978-989-758-009-3
AU - Dharmagunawardhana C.
AU - Mahmoodi S.
AU - Bennett M.
AU - Niranjan M.
PY - 2014
SP - 44
EP - 53
DO - 10.5220/0004728900440053