Advertisement

Weakly Supervised Segmentation Framework with Uncertainty: A Study on Pneumothorax Segmentation in Chest X-ray

  • Xi Ouyang
  • Zhong Xue
  • Yiqiang Zhan
  • Xiang Sean Zhou
  • Qingfeng Wang
  • Ying Zhou
  • Qian Wang
  • Jie-Zhi ChengEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

Pneumothorax is a critical abnormality that shall be treated with higher priority, and hence a computerized triage scheme is needed. A deep-learning-based framework to automatically segment the pneumothorax in chest X-rays is developed to support the realization of a triage system. Since a large number of pixel-level annotations is commonly needed but difficult to obtain for deep learning model, we propose a weakly supervised framework that allows partial training data to be weakly annotated with only image-level labels. We employ the attention masks derived from an image-level classification model as the pixel-level masks for those weakly-annotated data. Because the attention masks are rough and may have errors, we further develop a spatial label smoothing regularization technique to explore the uncertainty for the incorrectness of the attention masks in the training of segmentation model. Experimental results show that the proposed weakly supervised segmentation algorithm relieves the need of well-annotated data and yield satisfactory performance on the pneumothorax segmentation.

Keywords

Pneumothorax Weakly supervised segmentation Spatial label smoothing regularization 

Notes

Acknowledgement

This work was partially supported by the National Key Research and Development Program of China (2018YFC0116400), STCSM grants (19QC1400600, 17411953300), and the Shanghai Municipal Commission of Economy and Informatization (2017RGZN01026).

Supplementary material

490281_1_En_68_MOESM_ESM.pdf (538 kb)
Supplementary material 1 (pdf 537 KB)

References

  1. 1.
    Annarumma, M., Withey, S.J., Bakewell, R.J., Pesce, E., Goh, V., Montana, G.: Automated triaging of adult chest radiographs with deep artificial neural networks. Radiology 291, 180921 (2019)CrossRefGoogle Scholar
  2. 2.
    Cai, J., Lu, L., Harrison, A.P., Shi, X., Chen, P., Yang, L.: Iterative attention mining for weakly supervised thoracic disease pattern localization in chest X-Rays. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 589–598. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00934-2_66CrossRefGoogle Scholar
  3. 3.
    Chaurasia, A., Culurciello, E.: LinkNet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing (VCIP), pp. 1–4. IEEE (2017)Google Scholar
  4. 4.
    Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1175–1183. IEEE (2017)Google Scholar
  5. 5.
    Kelly, B.S., Rainford, L.A., Darcy, S.P., Kavanagh, E.C., Toomey, R.J.: The development of expertise in radiology: in chest radiograph interpretation,"expert" search pattern may predate "expert" levels of diagnostic accuracy for pneumothorax identification. Radiology 280(1), 252–260 (2016)CrossRefGoogle Scholar
  6. 6.
    Li, K., Wu, Z., Peng, K.C., Ernst, J., Fu, Y.: Tell me where to look: guided attention inference network. arXiv preprint arXiv:1802.10171 (2018)
  7. 7.
    Li, Z., et al.: Thoracic disease identification and localization with limited supervision. arXiv preprint arXiv:1711.06373 (2017)
  8. 8.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  9. 9.
    Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097–2106 (2017)Google Scholar
  10. 10.
    Yan, C., Yao, J., Li, R., Xu, Z., Huang, J.: Weakly supervised deep learning for thoracic disease classification and localization on chest x-rays. In: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp. 103–110. ACM (2018)Google Scholar
  11. 11.
    Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 472–480 (2017)Google Scholar
  12. 12.
    Zarogoulidis, P., et al.: Pneumothorax: from definition to diagnosis and treatment. J. Thorac. Dis. 6(Suppl 4), S372 (2014)Google Scholar
  13. 13.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3754–3762 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Xi Ouyang
    • 1
    • 2
  • Zhong Xue
    • 1
  • Yiqiang Zhan
    • 1
  • Xiang Sean Zhou
    • 1
  • Qingfeng Wang
    • 3
  • Ying Zhou
    • 4
  • Qian Wang
    • 2
  • Jie-Zhi Cheng
    • 1
    Email author
  1. 1.Shanghai United Imaging Intelligence Co., Ltd.ShanghaiChina
  2. 2.Institute for Medical Imaging Technology, School of Biomedical EngineeringShanghai Jiao Tong UniversityShanghaiChina
  3. 3.School of Computer Science and TechnologySouthwest University of Science and TechnologyMianyangChina
  4. 4.Radiology DepartmentMianyang Central HospitalMianyangChina

Personalised recommendations