Advertisement

Semi-supervised Learning of Fetal Anatomy from Ultrasound

  • Jeremy TanEmail author
  • Anselm Au
  • Qingjie Meng
  • Bernhard Kainz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11795)

Abstract

Semi-supervised learning methods have achieved excellent performance on standard benchmark datasets using very few labelled images. Anatomy classification in fetal 2D ultrasound is an ideal problem setting to test whether these results translate to non-ideal data. Our results indicate that inclusion of a challenging background class can be detrimental and that semi-supervised learning mostly benefits classes that are already distinct, sometimes at the expense of more similar classes.

Keywords

Semi-supervised learning Fetal ultrasound 

Notes

Acknowledgments

Support from Wellcome Trust IEH Award iFind project [102431]. JT is supported by the ICL President’s Scholarship.

References

  1. 1.
    Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G.: There are many consistent explanations of unlabeled data: why you should average. In: ICLR (2019)Google Scholar
  2. 2.
    Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans. Med. Imaging 36(11), 2204–2215 (2017)CrossRefGoogle Scholar
  3. 3.
    Cai, Y., Sharma, H., Chatelain, P., Noble, J.A.: Multi-task SonoEyeNet: detection of fetal standardized planes assisted by generated sonographer attention maps. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 871–879 (2018)Google Scholar
  4. 4.
    Chen, H., et al.: Standard plane localization in fetal ultrasound via domain transferred deep neural networks. IEEE J. Biomed. Health Inform. 19, 1627–1636 (2015)CrossRefGoogle Scholar
  5. 5.
    Cheplygina, V., de Bruijne, M., Pluim, J.P.: Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Med. Image Anal. 54, 280–296 (2019)CrossRefGoogle Scholar
  6. 6.
    Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation policies from data. In: CVPR (2019)Google Scholar
  7. 7.
    Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: NeurIPS (2005)Google Scholar
  8. 8.
    Kong, P., Ni, D., Chen, S., Li, S., Wang, T., Lei, B.: Automatic and efficient standard plane recognition in fetal ultrasound images via multi-scale dense networks. In: Melbourne, A., et al. (eds.) PIPPI/DATRA -2018. LNCS, vol. 11076, pp. 160–168. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00807-9_16CrossRefGoogle Scholar
  9. 9.
    Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: ICLR (2017)Google Scholar
  10. 10.
    Oliver, A., Odena, A., Raffel, C., Cubuk, E.D., Goodfellow, I.J.: Realistic evaluation of deep semi-supervised learning algorithms. In: NeurIPS (2018)Google Scholar
  11. 11.
    Singh, A., Nowak, R., Zhu, J.: Unlabeled data: now it helps, now it doesn’t. In: NeurIPS (2008)Google Scholar
  12. 12.
    Verma, V., Lamb, A., Kannala, J., Bengio, Y.: Interpolation consistency training for semi-supervised learning. In: IJCAI (2019)Google Scholar
  13. 13.
    World Health Organization, et al.: WHO recommendations on antenatal care for a positive pregnancy experience. World Health Organization (2016)Google Scholar
  14. 14.
    Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848 (2019)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jeremy Tan
    • 1
    Email author
  • Anselm Au
    • 1
  • Qingjie Meng
    • 1
  • Bernhard Kainz
    • 1
  1. 1.Imperial College LondonLondonUK

Personalised recommendations