Advertisement

Multi-institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation

  • Micah J. ShellerEmail author
  • G. Anthony Reina
  • Brandon Edwards
  • Jason Martin
  • Spyridon BakasEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)

Abstract

Deep learning models for semantic segmentation of images require large amounts of data. In the medical imaging domain, acquiring sufficient data is a significant challenge. Labeling medical image data requires expert knowledge. Collaboration between institutions could address this challenge, but sharing medical data to a centralized location faces various legal, privacy, technical, and data-ownership challenges, especially among international institutions. In this study, we introduce the first use of federated learning for multi-institutional collaboration, enabling deep learning modeling without sharing patient data. Our quantitative results demonstrate that the performance of federated semantic segmentation models (Dice = 0.852) on multimodal brain scans is similar to that of models trained by sharing data (Dice = 0.862). We compare federated learning with two alternative collaborative learning methods and find that they fail to match the performance of federated learning.

Keywords

Machine learning Deep learning Glioma Segmentation Federated Incremental BraTS 

Notes

Acknowledgements

Research reported in this publication was partly supported by the National Institutes of Health (NIH) under award numbers NIH/NINDS:R01NS042645 and NIH/NCI:U24CA189523. The content of this publication is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.

References

  1. 1.
    Bakas, S., et al.: In vivo detection of EGFRvIII in glioblastoma via perfusion magnetic resonance imaging signature consistent with deep peritumoral infiltration: the \(\phi \)-index. Clin. Cancer Res. 23(16), 4724–4734 (2017).  https://doi.org/10.1158/1078-0432.CCR-16-1871CrossRefGoogle Scholar
  2. 2.
    Chang, K., et al.: Residual convolutional neural network for the determination of IDH status in low- and high-grade gliomas from MR imaging. Clin. Cancer Res. 24(5), 1073–1081 (2018).  https://doi.org/10.1158/1078-0432.CCR-17-2236CrossRefGoogle Scholar
  3. 3.
    Korfiatis, P., Kline, T.L., Lachance, D.H., Parney, I.F., Buckner, J.C., Erickson, B.J.: Residual deep convolutional neural network predicts MGMT methylation status. J. Digit. Imaging 30(5), 622–628 (2017).  https://doi.org/10.1007/s10278-017-0009-zCrossRefGoogle Scholar
  4. 4.
    Binder, Z.A., et al.: Epidermal growth factor receptor extracellular domain mutations in glioblastoma present opportunities for clinical imaging and therapeutic development. Cancer Cell 34(1), 163–177 (2018).  https://doi.org/10.1016/j.ccell.2018.06.006CrossRefGoogle Scholar
  5. 5.
    Akbari, H., et al.: Imaging Surrogates of infiltration obtained via multiparametric imaging pattern analysis predict subsequent location of recurrence of glioblastoma. Neurosurgery 78(4), 572–580 (2016).  https://doi.org/10.1227/NEU.0000000000001202CrossRefGoogle Scholar
  6. 6.
    Macyszyn, L., et al.: Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques. Neuro-Oncology 18(3), 417–425 (2016).  https://doi.org/10.1093/neuonc/nov127CrossRefGoogle Scholar
  7. 7.
    Menze, B.H., et al.: The multimodal brain tumor image segmentation Benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015).  https://doi.org/10.1109/TMI.2014.2377694CrossRefGoogle Scholar
  8. 8.
    Bakas, S., et al.: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Nat. Sci. Data 4, 170117 (2017).  https://doi.org/10.1038/sdata.2017.117CrossRefGoogle Scholar
  9. 9.
    Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. In: The Cancer Imaging Archive (2017).  https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q
  10. 10.
    Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. In: The Cancer Imaging Archive (2017).  https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF
  11. 11.
    Tresp, V., Overhage, J.M., Bundschus, M., Rabizadeh, S., Fasching, P.A., Yu, S.: Going digital: a survey on digitalization and large-scale data analytics in healthcare. Proc. IEEE 104, 2180–2206 (2016).  https://doi.org/10.1109/JPROC.2016.2615052CrossRefGoogle Scholar
  12. 12.
    Chen, M., Qian, Y., Chen, J., Hwang, K., Mao, S., Hu, L.: Privacy protection and intrusion avoidance for cloudlet-based medical data sharing. IEEE Trans. Cloud Comput. 1 (2017).  https://doi.org/10.1109/TCC.2016.2617382
  13. 13.
    Brendan McMahan, H., Moore, E., Ramage, D., Hampson, S., Agera y Arcas, B.: Communication-efficient learning of deep networks from decentralized data. ArXiv e-prints (2016)Google Scholar
  14. 14.
    Chang, K., et al.: Distributed deep learning networks among institutions for medical imaging. J. Am. Med. Inform. Assoc. 25(8), 945–954 (2018).  https://doi.org/10.1093/jamia/ocy017CrossRefGoogle Scholar
  15. 15.
    Geyer, R.C., Klein, T., Nabi, M.: Differentially Private Federated Learning: A Client Level Perspective. ArXiv e-prints (2017)Google Scholar
  16. 16.
    Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., Shmatikov, V.: How To Backdoor Federated Learning. ArXiv e-prints (2018)Google Scholar
  17. 17.
    Brendan McMahan, H., Ramage, D., Talwar, K., Zhang, L.: Learning Differentially Private Recurrent Language Models. ArXiv e-prints (2017)Google Scholar
  18. 18.
    Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated Learning with Non-IID Data. ArXiv e-prints (2018)Google Scholar
  19. 19.
    French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128–135 (1999).  https://doi.org/10.1016/S1364-6613(99)01294-2CrossRefGoogle Scholar
  20. 20.
    Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Nat. Acad. Sci. 114, 3521–3526 (2017).  https://doi.org/10.1073/pnas.1611835114MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv e-prints (2015)Google Scholar
  22. 22.
    Zhao, X., Wu, Y., Song, G., Li, Z., Zhang, Y., Fan, Y.: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med. Image Anal. 43, 98–111 (2018).  https://doi.org/10.1016/j.media.2017.10.002CrossRefGoogle Scholar
  23. 23.
    Shokri, R., Smatikov, V.: Privacy-preserving deep learning. In: CCS 2015 Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1310–1321 (2015).  https://doi.org/10.1145/2810103.2813687
  24. 24.
    Abadi, M., et al.: Deep learning with differential privacy. In: CCS 2016 Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318 (2016).  https://doi.org/10.1145/2976749.2978318

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Intel CorporationSanta ClaraUSA
  2. 2.Center for Biomedical Image Computing and Analytics (CBICA)University of PennsylvaniaPhiladelphiaUSA

Personalised recommendations