Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Whole-brain radiomics for clustered federated personalization in brain tumor segmentation (2310.11480v1)

Published 17 Oct 2023 in eess.IV, cs.CV, and cs.LG

Abstract: Federated learning and its application to medical image segmentation have recently become a popular research topic. This training paradigm suffers from statistical heterogeneity between participating institutions' local datasets, incurring convergence slowdown as well as potential accuracy loss compared to classical training. To mitigate this effect, federated personalization emerged as the federated optimization of one model per institution. We propose a novel personalization algorithm tailored to the feature shift induced by the usage of different scanners and acquisition parameters by different institutions. This method is the first to account for both inter and intra-institution feature shift (multiple scanners used in a single institution). It is based on the computation, within each centre, of a series of radiomic features capturing the global texture of each 3D image volume, followed by a clustering analysis pooling all feature vectors transferred from the local institutions to the central server. Each computed clustered decentralized dataset (potentially including data from different institutions) then serves to finetune a global model obtained through classical federated learning. We validate our approach on the Federated Brain Tumor Segmentation 2022 Challenge dataset (FeTS2022). Our code is available at (https://github.com/MatthisManthe/radiomics_CFFL).

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. Debiasing Model Updates for Improving Personalized Federated Training. In Proceedings of the 38th International Conference on Machine Learning, July 2021.
  2. Federated Learning with Personalization Layers. arXiv:1912.00818 [cs, stat], December 2019.
  3. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific Data, 4(1), September 2017.
  4. Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach. In Advances in Neural Information Processing Systems, volume 33, 2020.
  5. Optimized U-Net for Brain Tumor Segmentation. In Alessandro Crimi and Spyridon Bakas, editors, Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Lecture Notes in Computer Science, 2022.
  6. An efficient framework for clustered federated learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, December 2020.
  7. SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. In International Conference on Machine Learning, November 2020.
  8. Federated Optimization in Heterogeneous Networks, April 2020.
  9. Ditto: Fair and Robust Federated Learning Through Personalization. In Proceedings of the 38th International Conference on Machine Learning, July 2021.
  10. Privacy-Preserving Federated Brain Tumour Segmentation. In Heung-Il Suk, Mingxia Liu, Pingkun Yan, and Chunfeng Lian, editors, Machine Learning in Medical Imaging, Lecture Notes in Computer Science, 2019.
  11. FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021a.
  12. A Review of Deep-Learning-Based Medical Image Segmentation Methods. Sustainability, 13(3), January 2021b.
  13. Federated Multi-Task Learning under a Mixture of Distributions. In Advances in Neural Information Processing Systems, volume 34, 2021.
  14. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Artificial Intelligence and Statistics, April 2017.
  15. The Federated Tumor Segmentation (FeTS) Challenge. arXiv:2105.05874 [cs, eess], May 2021.
  16. Federated Learning with Partial Model Personalization. In Proceedings of the 39th International Conference on Machine Learning, June 2022.
  17. OpenFL: An open-source framework for Federated Learning. Physics in Medicine & Biology, 67(21), November 2022.
  18. Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints. IEEE Transactions on Neural Networks and Learning Systems, 32(8), August 2021.
  19. Personalized Federated Learning using Hypernetworks. In Proceedings of the 38th International Conference on Machine Learning, July 2021.
  20. Radiomics in oncology: A practical guide. RadioGraphics, 41(6), 2021.
  21. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage, 170, April 2018.
  22. Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning. In Proceedings of the 39th International Conference on Machine Learning, June 2022.
  23. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Research, 77(21), November 2017.
  24. Federated learning with matched averaging. In International Conference on Learning Representations, 2020a.
  25. Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. In Advances in Neural Information Processing Systems, volume 33, 2020b.
  26. Closing the generalization gap of cross-silo federated medical image segmentation. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), jun 2022.
  27. Salvaging Federated Learning by Local Adaptation, March 2022.
  28. What do we mean by generalization in federated learning? In International Conference on Learning Representations, 2022.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now