Advertisement

Weakly Supervised Universal Fracture Detection in Pelvic X-Rays

  • Yirui WangEmail author
  • Le Lu
  • Chi-Tung Cheng
  • Dakai Jin
  • Adam P. Harrison
  • Jing Xiao
  • Chien-Hung Liao
  • Shun Miao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

Hip and pelvic fractures are serious injuries with life-threatening complications. However, diagnostic errors of fractures in pelvic X-rays (PXRs) are very common, driving the demand for computer-aided diagnosis (CAD) solutions. A major challenge lies in the fact that fractures are localized patterns that require localized analyses. Unfortunately, the PXRs residing in hospital picture archiving and communication system do not typically specify region of interests. In this paper, we propose a two-stage hip and pelvic fracture detection method that executes localized fracture classification using weakly supervised ROI mining. The first stage uses a large capacity fully-convolutional network, i.e., deep with high levels of abstraction, in a multiple instance learning setting to automatically mine probable true positive and definite hard negative ROIs from the whole PXR in the training data. The second stage trains a smaller capacity model, i.e., shallower and more generalizable, with the mined ROIs to perform localized analyses to classify fractures. During inference, our method detects hip and pelvic fractures in one pass by chaining the probability outputs of the two stages together. We evaluate our method on \(4\,410\) PXRs, reporting an under the ROC curve value of 0.975, the highest among state-of-the-art fracture detection methods. Moreover, we show that our two-stage approach can perform comparably to human physicians (even outperforming emergency physicians and surgeons), in a preliminary reader study of 23 readers.

Keywords

Fracture classification and localization Pelvic X-ray Weakly supervised detection Cascade two-stage training Image level labels 

Supplementary material

490281_1_En_51_MOESM1_ESM.pdf (11.5 mb)
Supplementary material 1 (pdf 11733 KB)

References

  1. 1.
    Badgeley, M.A., Zech, J.R., Oakden-Rayner, L., et al.: Deep learning predicts hip fracture using confounding patient and healthcare variables. arXiv:1811.03695 (2018)
  2. 2.
    Chellam, W.: Missed subtle fractures on the trauma-meeting digital projector. Injury 47(3), 674–676 (2016)CrossRefGoogle Scholar
  3. 3.
    Chen, H., Miao, S., Xu, D., Hager, G.D., Harrison, A.P.: Deep hierarchical multi-label classification of chest X-ray images. In: MIDL (2019)Google Scholar
  4. 4.
    Gale, W., Oakden-Rayner, L., Carneiro, G., Bradley, A.P., Palmer, L.J.: Detecting hip fractures with radiologist-level performance using deep neural networks. arXiv:1711.06504 (2017)
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  6. 6.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE CVPR, pp. 4700–4708 (2017)Google Scholar
  7. 7.
    Jiménez-Sánchez, A., et al.: Weakly-supervised localization and classification of proximal femur fractures. arXiv:1809.10692 (2018)
  8. 8.
    Johnell, O., Kanis, J.: An estimate of the worldwide prevalence, mortality and disability associated with hip fracture. Osteoporos. Int. 15(11), 897–902 (2004)CrossRefGoogle Scholar
  9. 9.
    Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)
  10. 10.
    Tarrant, S., Hardy, B., Byth, P., Brown, T., Attia, J., Balogh, Z.: Preventable mortality in geriatric hip fracture inpatients. Bone Joint J. 96(9), 1178–1184 (2014)CrossRefGoogle Scholar
  11. 11.
    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: IEEE CVPR (2017)Google Scholar
  12. 12.
    Yao, L., Prosky, J., Poblenz, E., Covington, B., Lyman, K.: Weakly supervised medical diagnosis and localization from multiple resolutions. arXiv preprint arXiv:1803.07703 (2018)
  13. 13.
    Yuille, A.L., Liu, C.: Deep nets: what have they ever done for vision? CoRR abs/1805.04025 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yirui Wang
    • 1
    Email author
  • Le Lu
    • 1
  • Chi-Tung Cheng
    • 2
  • Dakai Jin
    • 1
  • Adam P. Harrison
    • 1
  • Jing Xiao
    • 3
  • Chien-Hung Liao
    • 2
  • Shun Miao
    • 1
  1. 1.PAII Inc.BethesdaUSA
  2. 2.Chang Gung Memorial HospitalLinkouTaiwan, ROC
  3. 3.Ping An TechnologyShenzhenChina

Personalised recommendations