Abstract
Federated learning (FL) has been applied by several studies for pancreas segmentation. However, handling heterogeneous datasets across participating sites remains to be a challenge. To address the heterogeneity issues to further improve the performance of FL, we developed an innovative aggregation method, FedRNN, which used a Recurrent Neural Network (RNN) to adjust the aggregation weight of each site’s model based on the history of model loss and aggregation weight. At each round, the RNN took in the previous round aggregation weight and current round loss value from each site to estimate the optimal aggregation weight for the current round. Additionally, Mean Square Error (MSE) was applied for balanced performance across the clients. Based on cross-site validation, FedRNN outperformed the existing FL algorithms with an overall mean dice score of 78.7% and was up to 4.2% in improvement. In addition, FedRNN had the most stable performance across all clients in terms of the lowest standard deviation. Based on the results, the loss and aggregation weight history can be beneficial to the aggregation process of FL. Additionally, since FedRNN does not have restrictions on the form of loss functions, it can be applied to other tasks such as classification and object detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
References
Rieke, N., Hancox, J., Li, W. et al.: The future of digital health with federated learning. npj Digit. Med. 3, 119 (2020).
Roy, A. G., Siddiqui, S., Pölsterl, S., Navab, N. & Wachinger, C. Braintorrent: a peer-to-peer environment for decentralized federated learning. arXiv preprint arXiv:1905.06731 (2019).
Li, W., et al.: Privacy-Preserving Federated Brain Tumour Segmentation. In: Suk, HI., Liu, M., Yan, P., Lian, C. (eds) Machine Learning in Medical Imaging. MLMI 2019. LNCS, vol 11861, pp. 133–141. Springer, Cham (2019).
Sheller, M.J., et al.: Multi-institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2018. LNCS, vol 11383, pp. 92–104. Springer, Cham (2019).
Wang, P. et al.: Automated Pancreas Segmentation Using Multi-institutional Collaborative Deep Learning. In: Albarqouni S. et al. (eds) Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. DART 2020, DCL 2020. LNCS, vol 12444, pp. 192–200. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60548-3_19
Shen, C. et al.: Multi-task Federated Learning for Heterogeneous Pancreas Segmentation. In: Oyarzun Laura, C. et al. (eds) Clinical Image-Based Procedures, Distributed and Collaborative Learning, Artificial Intelligence for Combating COVID-19 and Secure and Privacy-Preserving Machine Learning. DCL 2021, PPML 2021, LL-COVID19 2021, CLIP 2021. LNCS, vol 12969, pp. 101–110. Springer, Cham (2021).
Xia, Y., et al.: Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation. arXiv preprint arXiv:2104.10195 (2021)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-Efficient Learning of Deep Networks from Decentralized Data. In: AISTATS (2017).
Qureshi, T. et al. ‘Predicting Pancreatic Ductal Adenocarcinoma Using Artificial Intelligence Analysis of Pre-diagnostic Computed Tomography Images’. 1 Jan. 2022: 211–217. https://doi.org/10.3233/CBM-210273
Ashish Vaswani et al. “Attention is all you need.” In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 6000–6010.
Qureshi, T., et al: Morphology-guided deep learning framework for segmentation of pancreas in computed tomography images. J. Med. Imag. 9(2) 024002 (4 April 2022)
Nilsson, A., et al.: A Performance Evaluation of Federated Learning Algorithms. In: Proceedings of the Second Workshop on Distributed Infrastructures for Deep Learning (DIDL’18), pp. 1–8. Association for Computing Machinery, New York, NY, USA (2018).
Simpson, A. L., Antonelli, M., Bakas, S., Bilello, M., Farahani, K., van Ginneken, B., Kopp-Schneider, A., Landman, B. A., Litjens, G., Menze, B.: A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063.
Holger R. Roth, Amal Farag, Evrim B. Turkbey, Le Lu, Jiamin Liu, and Ronald M. Summers. (2016). Data From Pancreas-CT. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2016.tNB1kqBU
Landman, BA, Xu, Z, Igelsias, JE, Styner, M, Langerak, TR, Klein, A: MICCAI multi-atlas labeling beyond the cranial vault—workshop and challenge, 2015.
The MONAI Consortium. (2020). Project MONAI. Zenodo.
Elman, J.L. (1990), Finding Structure in Time. Cognitive Science, 14: 179–211.
NVIDIA Clara Imaging. https://developer.nvidia.com/clara-medical-imaging (2022).
Kerfoot, E., Clough, J., Oksuz, I., Lee, J., King, A.P., Schnabel, J.A. (2019). Left-Ventricle Quantification Using Residual U-Net. In: , et al. Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018. Lecture Notes in Computer Science, vol 11395. Springer, Cham.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Deng, Z. et al. (2023). FedRNN: Federated Learning with RNN-Based Aggregation on Pancreas Segmentation. In: Su, R., Zhang, Y., Liu, H., F Frangi, A. (eds) Medical Imaging and Computer-Aided Diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering, vol 810. Springer, Singapore. https://doi.org/10.1007/978-981-16-6775-6_37
Download citation
DOI: https://doi.org/10.1007/978-981-16-6775-6_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6774-9
Online ISBN: 978-981-16-6775-6
eBook Packages: MedicineMedicine (R0)