Advertisement

Multi-domain Adaptation in Brain MRI Through Paired Consistency and Adversarial Learning

  • Mauricio Orbes-ArteagaEmail author
  • Thomas Varsavsky
  • Carole H. Sudre
  • Zach Eaton-Rosen
  • Lewis J. Haddow
  • Lauge Sørensen
  • Mads Nielsen
  • Akshay Pai
  • Sébastien Ourselin
  • Marc Modat
  • Parashkev Nachev
  • M. Jorge Cardoso
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11795)

Abstract

Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain. Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to n target domains (as long as there is paired data covering all domains). Our multi-domain adaptation method utilises a consistency loss combined with adversarial learning. We provide results on white matter lesion hyperintensity segmentation from brain MRIs using the MICCAI 2017 challenge data as the source domain and two target domains. The proposed method significantly outperforms other domain adaptation baselines.

Keywords

Domain adaptation Adversarial learning Brain MR 

Notes

Acknowledgements

We gratefully acknowledge the support of NVIDIA Corporation with the donation of one Titan Xp. This project has received funding from the EU H2020 under the Marie Skłodowska-Curie grant agreement No 721820, Wellcome Flagship Programme (WT213038/Z/18/Z) and Wellcome EPSRC CME (WT203148/Z/16/Z). Carole H. Sudre is supported by AS-JF-17-011 Alzheimer’s Society Junior Fellowship.

References

  1. 1.
    Bai, W., et al.: Semi-supervised learning for network-based cardiac MR image segmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 253–260. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66185-8_29CrossRefGoogle Scholar
  2. 2.
    Dou, Q., et al.: Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 691–697. AAAI Press (2018)Google Scholar
  3. 3.
    Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. arXiv preprint arXiv:1709.03485 (2017)
  4. 4.
    Haddow, L.J., et al.: Magnetic resonance imaging of cerebral small vessel disease in men living with HIV and HIV-negative men aged 50 and above. AIDS Res. Hum. Retroviruses 35(5), 453–460 (2019)CrossRefGoogle Scholar
  5. 5.
    Kamnitsas, K., et al.: Unsupervised domain adaptation in brain lesion segmentation with adversarial networks. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 597–609. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_47CrossRefGoogle Scholar
  6. 6.
    Kuijf, H.J., et al.: Standardized assessment of automatic segmentation of white matter hyperintensities; results of the WMH segmentation challenge. IEEE Trans. Med. Imaging 99, 1 (2019)CrossRefGoogle Scholar
  7. 7.
    Milletari, F., et al.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571. IEEE (2016)Google Scholar
  8. 8.
    Miotto, R., et al.: Deep learning for healthcare: review, opportunities and challenges. Briefings bioinform. 19(6), 1236–1246 (2017)CrossRefGoogle Scholar
  9. 9.
    Perone, C.S., et al.: Unsupervised domain adaptation for medical imaging segmentation with self-ensembling. NeuroImage 194, 1–11 (2019)CrossRefGoogle Scholar
  10. 10.
    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
  11. 11.
    Schoenauer-Sebag, A., et al.: Multi-domain adversarial learning. arXiv preprint arXiv:1903.09239 (2019)
  12. 12.
    Shaw, R., et al.: MRI k-space motion artefact augmentation: model robustness and task-specific uncertainty. In: MIDL, pp. 427–436 (2019)Google Scholar
  13. 13.
    Xie, Q., et al.: Unsupervised data augmentation. arXiv:1904.12848 (2019)
  14. 14.
    Zhao, A., et al.: Data augmentation using learned transforms for one-shot medical image segmentation. CoRR abs/1902.09383 (2019). http://arxiv.org/abs/1902.09383

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mauricio Orbes-Arteaga
    • 1
    • 2
    Email author
  • Thomas Varsavsky
    • 1
    • 3
  • Carole H. Sudre
    • 1
    • 3
    • 4
  • Zach Eaton-Rosen
    • 1
    • 3
  • Lewis J. Haddow
    • 5
  • Lauge Sørensen
    • 2
    • 6
    • 7
  • Mads Nielsen
    • 2
    • 6
    • 7
  • Akshay Pai
    • 2
    • 6
    • 7
  • Sébastien Ourselin
    • 1
  • Marc Modat
    • 1
  • Parashkev Nachev
    • 4
  • M. Jorge Cardoso
    • 1
  1. 1.Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK
  2. 2.Biomediq A/SCopenhagenDenmark
  3. 3.Department of Medical Physics and Biomedical EngineeringUCLLondonUK
  4. 4.Institute of NeurologyUniversity College LondonLondonUK
  5. 5.Chelsea and Westminster Hospital NHS Foundation TrustLondonUK
  6. 6.Cereriu A/SCopenhagenDenmark
  7. 7.Department of Computer ScienceUniversity of CopenhagenCopenhagenDenmark

Personalised recommendations