FedBrain-3DMRI: Federated Self-Supervised Learning for 3D Brain Tumor Segmentation using SCAFFOLD Algorithm
Abstract
Brain tumor segmentation is the most important way to separate tumor areas from healthy brain tissue in medical imaging. This is necessary for making an accurate diagnosis and planning treatment. But building strong deep learning models is often hard because there isn't much labeled medical data available, and strict privacy rules stop data from being shared in one place. Federated Learning (FL) helps keep patient data private by keeping it local, but its performance often drops when data from different hospitals have big differences in quality, imaging protocols, and distribution. Our research seeks to create a privacy-preserving federated learning framework that adeptly manages significant data heterogeneity while ensuring high segmentation accuracy across various institutions. We propose a new two-stage FL framework that allows multiple institutions to work together while keeping their privacy and effectively dealing with complicated non-IID data distributions. To start, we use a Federated Masked Autoencoder (MAE) for self-supervised pre-training. This lets the model learn strong anatomical features from unlabeled MRI scans. Second, the model is carefully fine-tuned using an Attention ResUNet3D architecture to get very accurate tumor segmentation. We use the SCAFFOLD optimization algorithm to keep training stable across all clients, even when the scanner varies from site to site, thereby directly addressing client drift. We also use strategic foreground-biased sampling and Test-Time Augmentation (TTA) techniques to greatly improve segmentation accuracy in difficult, uneven tumor sub-regions. We ran extensive experiments on the BraTS 2024 dataset in simulated federated settings with 10, 50, and 100 different clients. The Dice coefficients we got were 0.826, 0.824, and 0.818, which demonstrate strong performance. In the end, these strong results show that the suggested method works well on a larger scale and can be used in a clinical setting.
Downloads
References
M. L. Bondy, M. E. Scheurer, B. Malmer, J. S. Barnholtz-Sloan, F. G. Davis, D. Il'Yasova, et al., “Brain tumor epidemiology: Consensus from the Brain Tumor Epidemiology Consortium,” Cancer, vol. 113, no. S7, pp. 1953–1968,2008. https://doi.org/10.1002/cncr.23741
T. S. Armstrong, E. Vera-Bolanos, A. A. Acquaye, M. R. Gilbert, H. Ladha, and T. Mendoza, “The symptom burden of primary brain tumors: Evidence for a core set of tumor- and treatment-related symptoms,” Neuro-Oncology, vol. 18, no. 2, pp. 252–260, 2015. https://doi.org/10.1093/neuonc/nov166
F. Ullah, M. Nadeem, M. Abrar, F. Amin, A. Salam, and S. Khan, “Enhancing brain tumor segmentation accuracy through scalable federated learning with advanced data privacy and security measures,” Mathematics, vol. 11, Art. no. 4189, 2023. https://doi.org/10.3390/math11184189
A. N. Onaizah, Y. Xia, and K. Hussain, “FL-SiCNN: An improved brain tumor diagnosis using Siamese convolutional neural network in a peer-to-peer federated learning approach,” Alexandria Engineering Journal, vol. 114, pp. 1–11, 2025. https://doi.org/10.1016/j.aej.2024.11.063
D. Li, D. Han, T. H. Weng, Z. Zheng, H. Li, H. Liu, et al., “Blockchain for federated learning toward secure distributed machine learning systems: A systemic survey,” Soft Computing, vol. 26, no. 9, pp. 4423–4440, 2022. https://doi.org/10.1007/s00521-021-06491-5
T. K. Dang, X. Lan, J. Weng, and M. Feng, “Federated learning for electronic health records,” ACM Trans. Intell. Syst. Technol., vol. 13, pp. 1–17, 2022. https://doi.org/10.1145/3485730
S. Alphonse, F. Mathew, K. Dhanush, and V. Dinesh, “Federated learning with integrated attention multiscale model for brain tumor segmentation,” Scientific Reports, vol. 15, Art. no.11889,2025.
https://doi.org/10.1038/s41598-025-96416-6
R. Ahsan, I. Shahzadi, F. Najeeb, and H. Omer, “Brain tumor detection and segmentation using deep learning,” Magn. Reson. Mater. Phys. Biol. Med., vol. 38, pp. 13–22, 2025.
https://doi.org/10.1007/s10334-024-01203-5
A. Anaya-Isaza and L. Mera-Jiménez, “Data augmentation and transfer learning for brain tumor detection in magnetic resonance imaging,” IEEE Access, vol. 10, pp. 23217–23233, 2022.
https://doi.org/10.1109/ACCESS.2022.3154061
T. Shelatkar, Urvashi, M. Shorfuzzaman, A. Alsufyani, and K. Lakshmanna, “Diagnosis of brain tumor using lightweight deep learning model with fine-tuning approach,” Comput. Math. Methods Med., vol. 2022, Art. no. 2858845, 2022.
https://doi.org/10.1155/2022/2858845
M. F. Almufareh, M. Imran, A. Khan, M. Humayun, and M. Asim, “Automated brain tumor segmentation and classification in MRI using YOLO-based deep learning,” IEEE Access, vol. 12, pp. 16189–16207, 2024. https://doi.org/10.1109/ACCESS.2024.3359418
M. Rizwan, A. Shabbir, A. R. Javed, M. Shabbir, T. Baker, and D. A. J. Obe, “Brain tumor and glioma grade classification using Gaussian convolutional neural network,” IEEE Access, vol. 10, pp. 29731–29740, 2022.
https://doi.org/10.1109/ACCESS.2022.3153108
A. S. Musallam, A. S. Sherif, and M. K. Hussein, “A new convolutional neural network architecture for automatic detection of brain tumors in magnetic resonance imaging images,” IEEE Access, vol. 10, pp. 2775–2782,2022. https://doi.org/10.1109/ACCESS.2022.3140289
S. Li, J. Liu, and Z. Song, “Brain tumor segmentation based on region of interest-aided localization and segmentation U-Net,” Int. J. Mach. Learn. Cybern., vol. 13, pp. 2435–2445, 2022.
https://doi.org/10.1007/s13042-022-01536-4
U. Bhimavarapu, N. Chintalapudi, and G. Battineni, “Brain tumor detection and categorization with segmentation using an improved unsupervised clustering approach and machine learning classifier,” Bioengineering, vol. 11, no. 3, Art. no. 266, 2024. https://doi.org/10.3390/bioengineering11030266
S. Anantharajan, S. Gunasekaran, T. Subramanian, et al., “MRI brain tumor detection using deep learning and machine learning approaches,” Measurement: Sensors, vol. 31, Art. no. 101026, 2024. https://doi.org/10.1016/j.measen.2024.101026
J. Walsh, A. Othmani, M. Jain, and S. Dev, “Using U-Net network for efficient brain tumor segmentation in MRI images,” Healthcare Analytics, vol. 2, Art. no. 100098, 2022. https://doi.org/10.1016/j.health.2022.100098
Y. Jiang, Y. Zhang, X. Lin, J. Dong, T. Cheng, and J. Liang, “SwinBTS: A method for 3D multimodal brain tumor segmentation using swin transformer,” Brain Sciences, vol. 12, no. 6, Art. no. 797, 2022. https://doi.org/10.3390/brainsci12060797
L. ZongRen, W. Silamu, W. Yuzhen, and W. Zhe, “DenseTrans: Multimodal brain tumor segmentation using swin transformer,” IEEE Access, vol. 11, pp. 42895–42908, 2023. https://doi.org/10.1109/ACCESS.2023.3272055
Z. Zhu, X. He, G. Qi, Y. Li, B. Cong, and Y. Liu, “Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI,” Information Fusion, vol. 91, pp. 376–387, 2023. https://doi.org/10.1016/j.inffus.2022.10.022
C. Yan, J. Ding, H. Zhang, K. Tong, B. Hua, and S. Shi, “SEResU-Net for multimodal brain tumor segmentation,” IEEE Access, vol. 10, pp. 117033–117044, 2022. https://doi.org/10.1109/ACCESS.2022.3214309
M. E. Yahiaoui, M. Derdour, R. Abdulghafor, S. Turaev, M. Gasmi, A. Bennour, A. Aborujilah, and M. A. Sarem, “Federated learning with privacy-preserving techniques for multi-institutional three-dimensional brain tumor segmentation,” Diagnostics, vol. 14, Art. no. 2891, 2024. https://doi.org/10.3390/diagnostics14242891
A. Giri, P. Thapa, J. S. Banu, S. Poudyal, B. Rijal, and S. Karki, “Harnessing ResUHybridNet with federated learning: A new paradigm in brain segmentation,” Revue d’Intelligence Artificielle, vol. 38, pp. 765–772, 2024. https://doi.org/10.18280/ria.380303
M. Islam, M. T. Reza, M. Kaosar, and M. Z. Parvez, “Effectiveness of federated learning and CNN ensemble architectures for identifying brain tumors using MRI images,” Neural Processing Letters, vol. 55, no. 4, pp. 3779–3809, 2023. https://doi.org/10.1007/s11063-022-11014-1
Q. Dai, D. Wei, H. Liu, J. Sun, L. Wang, and Y. Zheng, “Federated modality-specific encoders and multimodal anchors for personalized brain tumor segmentation,” in Proc. AAAI Conf. Artif. Intell., pp. 1445–1453, 2024. https://doi.org/10.1609/aaai.v38i2.27909
F. Wagner, W. Xu, P. Saha, Z. Liang, D. Whitehouse, D. Menon, V. Newcombe, N. Voets, J. A. Noble, and K. Kamnitsas, “Feasibility of federated learning from client databases with different brain diseases and MRI modalities,” in Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis. (WACV), pp. 357–367, 2025. http://doi.org/10.1109/WACV61041.2025.00045
M. Grama, M. Musat, L. Muñoz-González, J. Passerat-Palmbach, D. Rueckert, and A. Alansary, “Robust aggregation for adaptive privacy-preserving federated learning in healthcare,” arXiv preprint, 2020. https://doi.org/10.48550/arXiv.2009.08294
Q. U. A. Mastoi, S. Latif, S. Brohi, J. Ahmad, A. Alqhatani, M. S. Alshehri, et al., “Explainable AI in medical imaging: An interpretable and collaborative federated learning model for brain tumor classification,” Frontiers in Oncology, vol. 15, Art. no. 1535478, 2025. https://doi.org/10.3389/fonc.2025.1535478
M. Islam, M. T. Reza, M. Kaosar, and M. Z. Parvez, “Effectiveness of federated learning and CNN ensemble architectures for identifying brain tumors using MRI images,” Neural Processing Letters, vol. 55, no. 4, pp. 3779–3809, 2023. https://doi.org/10.1007/s11063-022-11014-1
S. Sharma, K. Guleria, A. Dogra, D. Gupta, S. Juneja, S. Kumari, and A. Nauman, “A privacy-preserved horizontal federated learning approach for malignant glioma detection using distributed data silos,” PLOS ONE, vol. 20, Art. no. e0316543, 2025. https://doi.org/10.1371/journal.pone.0316543
D. H. Mahlool and M. H. Abed, “Distributed brain tumor diagnosis using a federated learning environment,” Bull. Electr. Eng. Informatics, vol. 11, no. 6, pp. 3313–3320, 2022. https://doi.org/10.11591/eei.v11i6.4131
Y. M. Elbachir, D. Makhlouf, G. Mohamed, M. M. Bouhamed, and K. Abdellah, “Federated learning for multi-institutional 3D brain tumor segmentation,” in Proc. Int. Conf. Pattern Anal. Intell. Syst. (PAIS), pp. 1–8, Apr. 2024. https://doi.org/10.1109/PAIS62114.2024.10541292
E. Albalawi, M. T. R., A. Thakur, V. V. Kumar, M. Gupta, S. B. Khan, and A. Almusharraf, “Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor,” BMC Med. Imaging, vol. 24, no. 1, Art. no. 110, 2024. https://doi.org/10.1186/s12880-024-01261-0
A. Al-Saleh, G. G. Tejani, S. Mishra, S. K. Sharma, and S. J. Mousavirad, “A federated learning-based privacy-preserving image processing framework for brain tumor detection from CT scans,” Scientific Reports, vol. 15, no. 1, Art. no. 23578, 2025. https://doi.org/10.1038/s41598-025-07807-8
B. C. Tedeschini, S. Savazzi, R. Stoklasa, L. Barbieri, I. Stathopoulos, M. Nicoli, and L. Serio, “Decentralized federated learning for healthcare networks: A case study on tumor segmentation,” IEEE Access, vol. 10, pp. 8693–8708, 2022. https://doi.org/10.1109/ACCESS.2022.3141913
G. Luo, T. Liu, J. Lu, X. Chen, L. Yu, J. Wu, et al., “Influence of data distribution on federated learning performance in tumor segmentation,” Radiology: Artificial Intelligence, vol. 5, no. 3, Art. no. e220082, 2023. https://doi.org/10.1148/ryai.220082
V. Kukreja, A. Dogra, R. K. Kaushal, S. Mehta, S. Vats, and B. Goyal, “Segmentation synergy with a dual U-Net and federated learning with CNN-RF models for enhanced brain tumor analysis,” Current Medical Imaging, vol. 20, no. 1, 2024. https://doi.org/10.2174/0115734056312765240905104112
S. Bakas, et al., “The 2024 Brain Tumor Segmentation (BraTS) challenge,” Synapse, 2024. https://doi.org/10.48550/arXiv.2405.18368
S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, R. T. Shinohara, C. Berger, S. H. Ha, M. Rozycki, et al., “Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BraTS challenge,” arXiv preprint, 2018. https://doi.org/10.48550/arXiv.1811.02629
A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool,” BMC Medical Imaging, vol. 15, no. 1, p. 29, 2015. https://doi.org/10.1186/s12880-015-0068-x
G. Wang, W. Li, S. Ourselin, and T. Vercauteren, “Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks,” in Proc. MICCAI BrainLesion Workshop, pp. 178–190, 2017. https://doi.org/10.48550/arXiv.1709.00382
V. Satushe, V. Vyas, S. Metkar, and D. P. Singh, “Advanced CNN architecture for brain tumor segmentation and classification using the BraTS-GoAT 2024 dataset,” Current Medical Imaging, early access, 2025. https://doi.org/10.2174/0115734056344235241217155930
K. Kamnitsas, C. Ledig, V. F. Newcombe, J. P. Simpson, A. D. Kane, D. K. Menon, et al., “Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation,” Medical Image Analysis, vol. 36, pp. 61–78, 2017. https://doi.org/10.1016/j.media.2016.10.004
K. He, X. Chen, S. Xie, Y. Li, P. Dollár, and R. Girshick, “Masked autoencoders are scalable vision learners,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 16000–16009. https://doi.org/10.48550/arXiv.2111.06377
S. P. Karimireddy, S. Kale, M. Mohri, S. Reddi, S. U. Stich, and A. T. Suresh, “SCAFFOLD: Stochastic controlled averaging for federated learning,” in Proc. Int. Conf. Mach. Learn. (ICML), 2020, pp. 5132–5143. https://doi.org/10.48550/arXiv.1910.06378
Copyright (c) 2026 Neeshu Chaudhary, Chintan Thacker
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
