Multi-institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
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.
KeywordsMachine learning Deep learning Glioma Segmentation Federated Incremental BraTS
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.
- 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.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
- 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.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
- 15.Geyer, R.C., Klein, T., Nabi, M.: Differentially Private Federated Learning: A Client Level Perspective. ArXiv e-prints (2017)Google Scholar
- 16.Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., Shmatikov, V.: How To Backdoor Federated Learning. ArXiv e-prints (2018)Google Scholar
- 17.Brendan McMahan, H., Ramage, D., Talwar, K., Zhang, L.: Learning Differentially Private Recurrent Language Models. ArXiv e-prints (2017)Google Scholar
- 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
- 21.Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv e-prints (2015)Google Scholar
- 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.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