Advertisement

Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio

  • Nanqing DongEmail author
  • Michael Kampffmeyer
  • Xiaodan Liang
  • Zeya Wang
  • Wei Dai
  • Eric Xing
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

The cardiothoracic ratio (CTR), a clinical metric of heart size in chest X-rays (CXRs), is a key indicator of cardiomegaly. Manual measurement of CTR is time-consuming and can be affected by human subjectivity, making it desirable to design computer-aided systems that assist clinicians in the diagnosis process. Automatic CTR estimation through chest organ segmentation, however, requires large amounts of pixel-level annotated data, which is often unavailable. To alleviate this problem, we propose an unsupervised domain adaptation framework based on adversarial networks. The framework learns domain invariant feature representations from openly available data sources to produce accurate chest organ segmentation for unlabeled datasets. Specifically, we propose a model that enforces our intuition that prediction masks should be domain independent. Hence, we introduce a discriminator that distinguishes segmentation predictions from ground truth masks. We evaluate our system’s prediction based on the assessment of radiologists and demonstrate the clinical practicability for the diagnosis of cardiomegaly. We finally illustrate on the JSRT dataset that the semi-supervised performance of our model is also very promising.

Notes

Acknowledgements

We thank Wingspan Technology for collecting and annotating the data for this study.

References

  1. 1.
    Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. In: IEEE TPAMI (2017)Google Scholar
  2. 2.
    Dallal, A.H., Agarwal, C., Arbabshirani, M.R., Patel, A., Moore, G.: Automatic estimation of heart boundaries and cardiothoracic ratio from chest x-ray images. In: Proceedings of the SPIE, vol. 10134, id. 101340K 10, p. 134 (2017)Google Scholar
  3. 3.
    Danzer, C.S.: The cardiothoracic ratio. Am. J. Med. Sci. 157, 513–554 (1919)CrossRefGoogle Scholar
  4. 4.
    Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. JAMIA 23(2), 304–10 (2016)Google Scholar
  5. 5.
    Dimopoulos, K., et al.: Cardiothoracic ratio from postero-anterior chest radiographs: a simple, reproducible and independent marker of disease severity and outcome in adults with congenital heart disease. Int. J. Cardiol. 166 (2011)CrossRefGoogle Scholar
  6. 6.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)Google Scholar
  7. 7.
    Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., Schölkopf, B.: Covariate shift and local learning by distribution matching, pp. 131–160. MIT Press, Cambridge (2009)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  9. 9.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)Google Scholar
  10. 10.
    Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. In: NIPS Workshop on Adversarial Training (2016)Google Scholar
  11. 11.
    Shiraishi, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am. J. Roentgenol. 174(1), 71–74 (2000)CrossRefGoogle Scholar
  12. 12.
    Shu, R., Bui, H., Narui, H., Ermon, S.: A DIRT-T approach to unsupervised domain adaptation. In: ICLR (2018)Google Scholar
  13. 13.
    Tavora, F., et al.: Cardiomegaly is a common arrhythmogenic substrate in adult sudden cardiac deaths, and is associated with obesity. Pathology 44, 187–91 (2012)CrossRefGoogle Scholar
  14. 14.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 2962–2971. IEEE (2017)Google Scholar
  15. 15.
    Van Ginneken, B., Stegmann, M.B., Loog, M.: Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med. Image Anal. 10(1), 19–40 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Nanqing Dong
    • 1
    • 2
    Email author
  • Michael Kampffmeyer
    • 3
  • Xiaodan Liang
    • 4
  • Zeya Wang
    • 1
  • Wei Dai
    • 1
  • Eric Xing
    • 1
  1. 1.Petuum, Inc.PittsburghUSA
  2. 2.Cornell UniversityIthacaUSA
  3. 3.UiT The Arctic University of NorwayTromsøNorway
  4. 4.Carnegie Mellon UniversityPittsburghUSA

Personalised recommendations