Advertisement

Uncertainty in Multitask Learning: Joint Representations for Probabilistic MR-only Radiotherapy Planning

  • Felix J. S. BragmanEmail author
  • Ryutaro Tanno
  • Zach Eaton-Rosen
  • Wenqi Li
  • David J. Hawkes
  • Sebastien Ourselin
  • Daniel C. Alexander
  • Jamie R. McClelland
  • M. Jorge Cardoso
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11073)

Abstract

Multi-task neural network architectures provide a mechanism that jointly integrates information from distinct sources. It is ideal in the context of MR-only radiotherapy planning as it can jointly regress a synthetic CT (synCT) scan and segment organs-at-risk (OAR) from MRI. We propose a probabilistic multi-task network that estimates: (1) intrinsic uncertainty through a heteroscedastic noise model for spatially-adaptive task loss weighting and (2) parameter uncertainty through approximate Bayesian inference. This allows sampling of multiple segmentations and synCTs that share their network representation. We test our model on prostate cancer scans and show that it produces more accurate and consistent synCTs with a better estimation in the variance of the errors, state of the art results in OAR segmentation and a methodology for quality assurance in radiotherapy treatment planning.

Notes

Acknowledgements

FB, JM, DH and MJC were supported by CRUK Accelerator Grant A21993. RT was supported by Microsoft Scholarship. ZER was supported by EPSRC Doctoral Prize. DA was supported by EU Horizon 2020 Research and Innovation Programme Grant 666992 and EPSRC Grant M020533, M006093 and J020990. We thank NVIDIA Corporation for hardware donation.

References

  1. 1.
    Burgos, N., et al.: Iterative framework for the joint segmentation and CT synthesis of MR images: application to MRI-only radiotherapy treatment planning. Phys. Med. Biol. 62, 4237 (2017)CrossRefGoogle Scholar
  2. 2.
    Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. arXiv:1612.05362
  3. 3.
    Wolterink, J.M., Dinkla, A.M., Savenije, M.H.F., Seevinck, P.R., van den Berg, C.A.T., Išgum, I.: Deep MR to CT synthesis using unpaired data. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2017. LNCS, vol. 10557, pp. 14–23. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68127-6_2CrossRefGoogle Scholar
  4. 4.
    Moeskops, P., et al.: Deep learning for multi-task medical image segmentation in multiple modalities. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 478–486. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_55CrossRefGoogle Scholar
  5. 5.
    Kendall, A., et al.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)Google Scholar
  6. 6.
    Tanno, R., et al.: Bayesian image quality transfer with CNNs: exploring uncertainty in dMRI super-resolution. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 611–619. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_70CrossRefGoogle Scholar
  7. 7.
    Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NIPS, pp. 5580–5590 (2017)Google Scholar
  8. 8.
    Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML, pp. 1050–1059 (2016)Google Scholar
  9. 9.
    Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: ICML (1993)Google Scholar
  10. 10.
    Li, W., Wang, G., Fidon, L., Ourselin, S., Cardoso, M.J., Vercauteren, T.: On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Niethammer, M., Styner, M., Aylward, S., Zhu, H., Oguz, I., Yap, P.-T., Shen, D. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 348–360. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_28CrossRefGoogle Scholar
  11. 11.
    Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113-122 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Felix J. S. Bragman
    • 1
    Email author
  • Ryutaro Tanno
    • 1
  • Zach Eaton-Rosen
    • 1
  • Wenqi Li
    • 1
  • David J. Hawkes
    • 1
  • Sebastien Ourselin
    • 2
  • Daniel C. Alexander
    • 1
    • 3
  • Jamie R. McClelland
    • 1
  • M. Jorge Cardoso
    • 1
    • 2
  1. 1.Centre for Medical Image ComputingUniversity College LondonLondonUK
  2. 2.Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK
  3. 3.Clinical Imaging Research CentreNational University of SingaporeSingaporeSingapore

Personalised recommendations