Automated Analysis of Chest Radiographs for Cystic Fibrosis Scoring

  • Zhaowei HuangEmail author
  • Chen Ding
  • Lei Zhang
  • Min-Zhao Lee
  • Yang Song
  • Hiran Selvadurai
  • Dagan Feng
  • Yanning Zhang
  • Weidong Cai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10989)


We present a framework to analyze chest radiographs for cystic fibrosis using machine learning methods. We compare the representational power of deep learning features with traditional texture features. Specifically, we respectively employ VGG-16 based deep learning features, Tamura and Gabor filter based textural features to represent the cystic fibrosis images. We demonstrate that VGG-16 features perform best, with a maximum agreement of 82%. In addition, due to limited dimensionality, Tamura features for unsegmented images achieve no more than 50% agreement; however, after segmentation, the accuracy of Tamura can reach 78%. In combination with using the deep learning features, we also compare back propagation neural network and sparse coding classifiers to the typical SVM classifier with polynomial kernel function. The result shows that neural network and sparse coding classifiers outperform SVM in most cases. Only with insufficient training samples does SVM demonstrate higher accuracy.


Cystic fibrosis Computer-assisted score Deep learning feature VGG-16 


  1. 1.
    Ratjen, F., Döring, G.: Cystic fibrosis. In: Lancet, vol. 361, pp. 681–689 (2003)Google Scholar
  2. 2.
    Yankaskas, J.R., Marshall, B.C., Sufian, B., Simon, R.H., Rodman, D.: Cystic fibrosis adult care: consensus conference report. Chest 125(1 Suppl), 1S–39S (2004)CrossRefGoogle Scholar
  3. 3.
    Cleveland, R.H., Zurakowski, D., Slattery, D.M., Colin, A.A.: Chest radiographs for outcome assessment in cystic fibrosis. Proc. Am. Thorac. Soc. 4, 302–305 (2007)CrossRefGoogle Scholar
  4. 4.
    Shwachman, H., Kulczycki, L.L.: Long-term study of one hundred five patients with cystic fibrosis. AMA J. Dis. Child. 96, 6–15 (1958)CrossRefGoogle Scholar
  5. 5.
    Lee, M.Z., Cai, W., Song, Y., Selvadurai, H., Feng, D.D.: Fully automated scoring of chest radiographs in cystic fibrosis. In: 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, pp. 3965–3968 (2013)Google Scholar
  6. 6.
    Li, Q., Cai, W., Wang, X., Zhou, Y., Feng, D.D., Chen, M.: Medical image classification with convolutional neural network. In: 13th International Conference on Control Automation Robotics & Vision (ICARCV), Singapore, pp. 844–848 (2014)Google Scholar
  7. 7.
    Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., et al.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Image 35(5), 1299–1312 (2016)CrossRefGoogle Scholar
  8. 8.
    Song, Y., Li, Q., Huang, H., Feng, D., Chen, M., Cai, W.: Low dimensional representation of fisher vectors for microscopy image classification. IEEE Trans. Med. Imaging 36(8), 1636–1649 (2017)CrossRefGoogle Scholar
  9. 9.
    Orlando, J.I., Prokofyeva, E., Fresno, M.D., et al.: Convolutional neural network transfer for automated glaucoma identification. (2017)
  10. 10.
    Tamura, H., Mori, S., Yamawaki, T.: Textural features corresponding to visual perception. In: IEEE Transactions on Systems, Man, and Cybernetics, SMC-8, pp. 460–472 (1978)CrossRefGoogle Scholar
  11. 11.
    Niblack, C.W., et al.: The QBIC project: querying images by content using color, texture, and shape. In: Proceedings of SPIE, Storage and Retrieval for Image and Video Databases, vol. 1908, San Jose, pp. 173–187 (1993)Google Scholar
  12. 12.
    Castelli, V., Bergman, L.D.: Image Databases: Search and Retrieval of Digital Imagery. Wiley, New York (2002)Google Scholar
  13. 13.
    Fogel, I., Sagi, D.: Gabor filters as texture discriminator. Biol. Cybern. 61, 103–113 (1989)CrossRefGoogle Scholar
  14. 14.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, pp. 248–255 (2009)Google Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (2014)
  16. 16.
    Ding, C., Xia, Y., Li, Y.: Supervised segmentation of vasculature in retinal images using neural networks. In: International Conference on Orange Technologies, Xian, pp. 49–52 (2014).
  17. 17.
    Schölkopf, B., Platt, J., Hofmann, T.: Sparse representation for signal classification. In: 19th Proceedings of the 2006 Conference on Advances in Neural Information Processing Systems, edn. 1, pp. 609–616. MIT Press (2007)Google Scholar
  18. 18.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273–297 (1995)zbMATHGoogle Scholar
  19. 19.
    Noor, S.S.M., et al.: Hyperspectral image enhancement and mixture deep-learning classification of corneal epithelium injuries. Sensors 17(11), 2644 (2017)CrossRefGoogle Scholar
  20. 20.
    Ren, J.: ANN vs. SVM: which one performs better in classification of MCCs in mammogram imaging. Knowl. Based Syst. 26, 144–153 (2012)CrossRefGoogle Scholar
  21. 21.
    Wang, X., et al.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: CVPR, pp. 3462–3471 (2017)Google Scholar
  22. 22.
    Zabalza, J., et al.: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging. Neurocomputing 185, 1–10 (2016)CrossRefGoogle Scholar
  23. 23.
    Wang, Z., et al.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018)CrossRefGoogle Scholar
  24. 24.
    Noor, S.S.M., et al.: The properties of the cornea based on hyperspectral imaging: optical biomedical engineering perspective. In: Systems, Signals and Image Processing, IWSSIP (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Zhaowei Huang
    • 1
    Email author
  • Chen Ding
    • 2
  • Lei Zhang
    • 2
  • Min-Zhao Lee
    • 1
  • Yang Song
    • 1
  • Hiran Selvadurai
    • 3
  • Dagan Feng
    • 1
  • Yanning Zhang
    • 2
  • Weidong Cai
    • 1
  1. 1.Biomedical and Multimedia Information Technology (BMIT) Research Group, School of ITUniversity of SydneySydneyAustralia
  2. 2.Shaanxi Key Lab of Speech and Image Information Processing (SAIIP), School of Computer ScienceNorthwestern Polytechnical UniversityXi’anChina
  3. 3.Children’s Hospital at Westmead, Sydney Children’s Hospitals NetworkSydneyAustralia

Personalised recommendations