Advertisement

Multi-scale Deep Convolutional Neural Networks for Emphysema Classification and Quantification

  • Liying Peng
  • Lanfen LinEmail author
  • Hongjie Hu
  • Qiaowei Zhang
  • Huali Li
  • Qingqing Chen
  • Dan Wang
  • Xian-Hua Han
  • Yutaro Iwamoto
  • Yen-Wei Chen
  • Ruofeng Tong
  • Jian Wu
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 171)

Abstract

In this work, we aim at classification and quantification of emphysema in computed tomography (CT) images of lungs. Most previous works are limited to extracting low-level features or mid-level features without enough high-level information. Moreover, these approaches do not take the characteristics (scales) of different emphysema into account, which are crucial for feature extraction. In contrast to previous works, we propose a novel deep learning method based on multi-scale deep convolutional neural networks. There are three contributions for this paper. First, we propose to use a base residual network with 20 layers to extract more high-level information. Second, we incorporate multi-scale information into our deep neural networks so as to take full consideration of the characteristics of different emphysema. A 92.68% classification accuracy is achieved on our original dataset. Finally, based on the classification results, we also perform the quantitative analysis of emphysema in 50 subjects by correlating the quantitative results (the area percentage of each class) with pulmonary functions. We show that centrilobular emphysema (CLE) and panlobular emphysema (PLE) have strong correlation with the pulmonary functions and the sum of CLE and PLE can be used as a new and accurate measure of emphysema severity instead of the conventional measure (sum of all subtypes of emphysema). The correlations between the new measure and various pulmonary functions are up to |r| \(= 0.922\) (r is correlation coefficient).

Notes

Acknowledgements

This work was supported in part by Zhejiang Lab Program under the Grant No.2018DG0ZX01, in part by the Key Science and Technology Innovation Support Program of Hangzhou under the Grant No.20172011A038, and in part by the Grant-in Aid for Scientific Research from the Japanese Ministry for Education, Science, Culture and Sports (MEXT) under the Grant No.18H03267 and No.17H00754.

References

  1. 1.
    Mannino, D.M., Kiri, V.A.: Changing the burden of COPD mortality. Int. J. Chron. Obstruct. Pulmon. Dis. 1, 219–233 (2006)Google Scholar
  2. 2.
    Takahashi, M., Fukuoka, J., Nitta, N., Takazakura, R., Nagatani, Y., Murakami, Y., Murata, K.: Imaging of pulmonary emphysema: a pictorial review. Int. J. Chron. Obstruct. Pulmon. Dis. 3, 193–204 (2008)CrossRefGoogle Scholar
  3. 3.
    Lynch, D.A., Austin, J.H., Hogg, J.C., Grenier, P.A., Kauczor, H.U., Bankier, A.A., Coxson, H.O.: CT-definable subtypes of chronic obstructive pulmonary disease: a statement of the Fleischner Society. Radiology 277, 192–205 (2015)CrossRefGoogle Scholar
  4. 4.
    Smith, B.M., Austin, J.H., Newell Jr., J.D., D’Souza, B.M., Rozenshtein, A., Hoffman, E.A., Barr, R.G.: Pulmonary emphysema subtypes on computed tomography: the MESA COPD study. Am. J. Med. 127, 94–e7 (2014)CrossRefGoogle Scholar
  5. 5.
    Shaker, S.B., von Wachenfeldt, K.A., Larsson, S., Mile, I., Persdotter, S., Dahlbäck, M., Fehniger, T.E.: Identification of patients with chronic obstructive pulmonary disease (COPD) by measurement of plasma biomarkers. Clin. Respir. J. 2, 17–25 (2008)CrossRefGoogle Scholar
  6. 6.
    Yang, J., Angelini, E.D., Smith, B.M., Austin, J.H., Hoffman, E.A., Bluemke, D.A., Laine, A.F.: Explaining radiological emphysema subtypes with unsupervised texture prototypes: MESA COPD study. In: Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging, pp. 69–80. Springer, Cham (2016)CrossRefGoogle Scholar
  7. 7.
    Sorensen, L., Shaker, S.B., De Bruijne, M.: Quantitative analysis of pulmonary emphysema using local binary patterns. IEEE Trans. Med. Imaging 29, 559–569 (2010)CrossRefGoogle Scholar
  8. 8.
    Binder, P., Batmanghelich, N.K., Estépar, R.S.J., Golland, P.: Unsupervised discovery of emphysema subtypes in a large clinical cohort. In: International Workshop on Machine Learning in Medical Imaging, pp. 180–187. Springer, Cham (2016)CrossRefGoogle Scholar
  9. 9.
    Häme, Y., Angelini, E.D., Parikh, M.A., Smith, B.M., Hoffman, E.A., Barr, R.G., Laine, A.F.: Sparse sampling and unsupervised learning of lung texture patterns in pulmonary emphysema: MESA COPD study. In: Proceedings of the IEEE International Symposium on Biomedical Imaging, pp. 109–113 (2015)Google Scholar
  10. 10.
    Song, J., Yang, J., Smith, B., Balte, P., Hoffman, E.A., Barr, R.G., Angelini, E.D.: Generative method to discover emphysema subtypes with unsupervised learning using lung macroscopic patterns (LMPS): the MESA COPD study. In: Proceedings of the IEEE International Symposium on Biomedical Imaging. pp. 375–378 (2017)Google Scholar
  11. 11.
    Yang, J., Angelini, E.D., Balte, P.P., Hoffman, E.A., Austin, J.H., Smith, B.M., Laine, A.F.: Unsupervised discovery of spatially-informed lung texture patterns for pulmonary emphysema: the MESA COPD study. In: Proceedings of the MICCAI, pp. 116–124 (2017)CrossRefGoogle Scholar
  12. 12.
    Mendoza, C.S., Washko, G.R., Ross, J.C., Diaz, A.A., Lynch, D.A., Crapo, J.D., Estépar, R.S.J.: Emphysema quantification in a multi-scanner HRCT cohort using local intensity distributions. In: Proceedings of the IEEE International Symposium on Biomedical Imaging, pp. 474–477 (2012)Google Scholar
  13. 13.
    Uppaluri, R., Mitsa, T., Sonka, M., Hoffman, E.A., McLennan, G.: Quantification of pulmonary emphysema from lung computed tomography images. Amer. J. Respir. Crit. Care Med. 156, 248–254 (1997)CrossRefGoogle Scholar
  14. 14.
    Xu, Y., Sonka, M., McLennan, G., Guo, J., Hoffman, E.A.: MDCT-based 3D texture classification of emphysema and early smoking related lung pathologies. IEEE Trans. Med. Imaging 25, 464–475 (2006)CrossRefGoogle Scholar
  15. 15.
    Park, Y.S., Seo, J.B., Kim, N., Chae, E.J., Oh, Y.M., Do Lee, S., Kang, S.H.: Texture-based quantification of pulmonary emphysema on high-resolution computed tomography: comparison with density-based quantification and correlation with pulmonary function. Invest. Radiol. 43, 395–402 (2008)CrossRefGoogle Scholar
  16. 16.
    Prasad, M., Sowmya, A., Wilson, P.: Multi-level classification of emphysema in HRCT lung images. Pattern Anal. Appl. 12, 9–20 (2009)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Peng, L., Lin, L., Hu, H., Ling, X., Wang, D., Han, X., Chen, Y.W.: Joint weber-based rotation invariant uniform local ternary pattern for classification of pulmonary emphysema in CT images. In: Proceedigs of the International Conference on Image Processing, pp. 2050–2054 (2017)Google Scholar
  18. 18.
    Gangeh, M.J., Sørensen, L., Shaker, S.B., Kamel, M.S., De Bruijne, M., Loog, M.: A texton-based approach for the classfication of lung parenchyma in CT images. In: Proceedings of the MICCAI, pp. 595–602 (2010)CrossRefGoogle Scholar
  19. 19.
    Asherov, M., Diamant, I., Greenspan, H.: Lung texture classification using bag of visual words. In: Proceedings of the SPIE Medical Imaging (2014)Google Scholar
  20. 20.
    Yang, J., Feng, X., Angelini, E.D., Laine, A.F.: Texton and sparse representation based texture classification of lung parenchyma in CT images. In: Proceedings of the EMBC, pp. 1276–1279 (2016)Google Scholar
  21. 21.
    Litjens, G., Kooi, T., Bejnordi, B.E., Setio, A.A.A., Ciompi, F., Ghafoorian, M., Sánchez, C.I.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  22. 22.
    Dou, Q., Chen, H., Yu, L., Qin, J., Heng, P.A.: Multilevel contextual 3-d cnns for false positive reduction in pulmonary nodule detection. IEEE Trans. Biomed. Eng. 64, 1558–1567 (2017)CrossRefGoogle Scholar
  23. 23.
    Setio, A.A.A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., Van Riel, S.J., Van, G.: Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging 35, 1160–1169 (2016)CrossRefGoogle Scholar
  24. 24.
    Anthimopoulos, M., Christodoulidis, S., Ebner, L., Christe, A., Mougiakakou, S.: Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans. Med. Imaging 35, 1207–1216 (2016)CrossRefGoogle Scholar
  25. 25.
    Wang, Q., Zheng, Y., Yang, G., Jin, W., Chen, X., Yin, Y.: Multiscale rotation-invariant convolutional neural networks for lung texture classification. IEEE J. Biomed. Health Inform. 1–1 (2017)Google Scholar
  26. 26.
    Hoo-Chang, S., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., Summers, R.M.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35, 1285–1298 (2016)CrossRefGoogle Scholar
  27. 27.
    Gao, M., Xu, Z., Lu, L., Harrison, A.P., Summers, R.M., Mollura, D.J.: Holistic interstitial lung disease detection using deep convolutional neural networks: multi-label learning and unordered pooling. arXiv preprint arXiv:1701.05616 (2017)
  28. 28.
    Karabulut, E.M., Ibrikci, T.: Emphysema discrimination from raw HRCT images by convolutional neural networks. In: Proceedings of the ELECO, pp. 705–708 (2015)Google Scholar
  29. 29.
    Pei, X: Emphysema classification using convolutional neural networks. In: Proceedings of the ICIRA, pp. 455–461 (2015)CrossRefGoogle Scholar
  30. 30.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770–778 (2016)Google Scholar
  31. 31.
    Heaton, J.: Ian Goodfellow, Yoshua Bengio, and Aaron Courville: deep learning. In: Genetic Programming and Evolvable Machines, pp. 305–307 (2017)CrossRefGoogle Scholar
  32. 32.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Represents, pp. 1–13 (2015)Google Scholar
  33. 33.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)Google Scholar
  34. 34.
    Crapo, R.O. et al.: American thoracic society. Standardization of spirometry 1994 update. Am. J. Respir. Crit. Care Med. 152, 1107–1136 (1995)Google Scholar
  35. 35.
    Sverzellati, N., Cademartiri, F., Bravi, F., Martini, C., Gira, F.A., Maffei, E., Rossi, C.: Relationship and prognostic value of modified coronary artery calcium score, FEV1, and emphysema in lung cancer screening population: the MILD trial. Radiology 262, 460–467 (2012)CrossRefGoogle Scholar
  36. 36.
    Ceresa, M., Bastarrika, G., de Torres, J.P., Montuenga, L.M., Zulueta, J.J., Ortiz-de-Solorzano, C., Muñoz-Barrutia, A.: Robust, standardized quantification of pulmonary emphysema in low dose CT exams. Acad. Radiol. 18, 1382–1390 (2011)CrossRefGoogle Scholar
  37. 37.
    Hame, Y.T., Angelini, E.D., Hoffman, E.A., Barr, R.G., Laine, A.F.: Adaptive quantification and longitudinal analysis of pulmonary emphysema with a hidden markov measure field model. IEEE Trans. Med. Imaging 33, 1527–1540 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Liying Peng
    • 1
  • Lanfen Lin
    • 1
    Email author
  • Hongjie Hu
    • 2
  • Qiaowei Zhang
    • 2
  • Huali Li
    • 2
  • Qingqing Chen
    • 2
  • Dan Wang
    • 2
  • Xian-Hua Han
    • 3
  • Yutaro Iwamoto
    • 4
  • Yen-Wei Chen
    • 5
  • Ruofeng Tong
    • 1
  • Jian Wu
    • 1
  1. 1.College of Computer Science and Technology, Zhejiang UniversityHangzhouChina
  2. 2.Department of Radiology, Sir Run Run Shaw HospitalZhejiang UniversityHangzhouChina
  3. 3.Yamaguchi UniversityYamaguchiJapan
  4. 4.Graduate School of Information Science and EngineeringRitsumeikan UniversityKyotoJapan
  5. 5.Zhejiang LabHangzhou CityChina

Personalised recommendations