Abstract
Federated learning (FL) allows multiple distributed clients to train a model while protecting their data. Medical data, especially brain MRIs, might be misdiagnosed due to capture noise and scanner abnormalities. Existing noise-handling technologies use data transmission, raising communication burdens and privacy risks. To address these challenges, we propose a novel Adaptive Sample Weighting Federated Learning (ASW-FL) approach incorporating co-training into the FL framework. The local and global models in FL have different learning abilities, which we use to our advantage. The two models “teach each other” to ignore noisy labels by exchanging samples with their confident predictions. Our method improved accuracy from 83.05% to 85.20% using various aggregation algorithms on a benchmark dataset of 1300 brain MRIs and our own Biobank UK data. Our methodology for accurate, privacy-preserving medical image analysis is adequate. The proposed model is precise but requires more processing resources, making it more appropriate for powerful servers than personal devices.
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
References
Jamil, F., Hameed, I.A.: Toward intelligent open-ended questions evaluation based on predictive optimization. Expert Syst. Appl. 120640 (2023)
Lotter, W., et al.: Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nat. Med. 27(2), 244–249 (2021)
Babar, F.F., Lukui, S., Babar, F.F., Muhammad, F.: Enhanced weather forecasting using the meteronet model: a comprehensive ensemble approach. Int. J. Adv. Multidisc. Res. 10(8), 20–38 (2023)
Wang, Y., Liu, L., Wang, C.: Trends in using deep learning algorithms in biomedical prediction systems. Front. Neurosci. 17, 1256351 (2023)
Adnan, M., Kalra, S., Cresswell, J.C., Taylor, G.W., Tizhoosh, H.R.: Federated learning and differential privacy for medical image analysis. Sci. Rep. 12(1), 1953 (2022)
Nguyen, D.C., et al.: Federated learning for smart healthcare: a survey. ACM Comput. Surv. (CSUR) 55(3), 1–37 (2022)
Jamil, F., Ahmad, S., Whangbo, T.K., Muthanna, A., Kim, D.-H.: Improving blockchain performance in clinical trials using intelligent optimal transaction traffic control mechanism in smart healthcare applications. Comput. Industr. Eng. 170, 108327 (2022)
Jamil, F., Qayyum, F., Alhelaly, S., Javed, F., Muthanna, A.: Intelligent microservice based on blockchain for healthcare applications. Comput. Mater. Continua 69(2) (2021)
Jamil, F., Kim, D.H.: Enhanced Kalman filter algorithm using fuzzy inference for improving position estimation in indoor navigation. J. Intell. Fuzzy Syst. 40(5), 8991–9005 (2021)
Zhu, C., Chen, W., Peng, T., Wang, Y., Jin, M.: Hard sample aware noise robust learning for histopathology image classification. IEEE Trans. Med. Imaging 41(4), 881–894 (2021)
Liu, J., Li, R., Sun, C.: Co-correcting: noise-tolerant medical image classification via mutual label correction. IEEE Trans. Med. Imaging 40(12), 3580–3592 (2021)
Yang, S., Park, H., Byun, J., Kim, C.: Robust federated learning with noisy labels. IEEE Intell. Syst. 37(2), 35–43 (2022)
Tam, K., Li, L., Han, B., Xu, C., Fu, H.: Federated noisy client learning. IEEE Trans. Neural Netw. Learn. Syst. (2023)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pp. 92–100 (1998)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Kairouz, P., et al.: Advances and open problems in federated learning. Found. Trends® Mach. Learn. 14(1–2), 1–210 (2021)
Li, W., et al.: Privacy-preserving federated brain tumour segmentation. In: Suk, H.-I., Liu, M., Yan, P., Lian, C. (eds.) MLMI 2019. LNCS, vol. 11861, pp. 133–141. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32692-0_16
Chen, Z., Yang, C., Zhu, M., Peng, Z., Yuan, Y.: Personalized retrogress-resilient federated learning toward imbalanced medical data. IEEE Trans. Med. Imaging 41(12), 3663–3674 (2022)
Karimi, D., Dou, H., Warfield, S.K., Gholipour, A.: Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med. Image Anal. 65, 101759 (2020)
Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)
Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Menon, A.K., Rawat, A.S., Reddi, S.J., Kumar, S.: Can gradient clipping mitigate label noise? In: International Conference on Learning Representations (2019)
Lie, J., et al.: Improving medical images classification with label noise using dual-uncertainty estimation. IEEE Trans. Med. Imaging 41(6), 1533–1546 (2022)
Goldberger, J., Ben-Reuven, E.: Training deep neural-networks using a noise adaptation layer. In: International Conference on Learning Representations (2022)
Jiang, L., Zhou, Z., Leung, T., Li, L.-J., Fei-Fei, L.: MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, pp. 2304–2313. PMLR (2018)
Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., Fergus, R.: Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080 (2014)
Xue, C., Yu, L., Chen, P., Dou, Q., Heng, P.-A.: Robust medical image classification from noisy labeled data with global and local representation guided co-training. IEEE Trans. Med. Imaging 41(6), 1371–1382 (2022)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Babar, F.F., Jamil, F., Babar, F.F. (2024). Intelligent Handling of Noise in Federated Learning with Co-training for Enhanced Diagnostic Precision. In: Nguyen, N.T., et al. Computational Collective Intelligence. ICCCI 2024. Lecture Notes in Computer Science(), vol 14810. Springer, Cham. https://doi.org/10.1007/978-3-031-70816-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-70816-9_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70815-2
Online ISBN: 978-3-031-70816-9
eBook Packages: Computer ScienceComputer Science (R0)