Performance evaluation of neural networks in federated learning for classification of alzheimer’s disease stages

• Luan Mantegazine UFRGS
• Claudio F. R. Geyer UFRGS
• Andrei Bieger UFRGS
• Diogo O. Souza UFRGS
• Eduardo R. Zimmer UFRGS

DOI: https://doi.org/10.5753/semish.2025.7137

Resumo

Alzheimer’s disease is a progressive neurodegenerative disorder where early detection is critical for improving treatment outcomes. This study investigates the performance of ResNet 50 and DenseNet 169 architectures integrated with Federated Learning (FL) techniques to classify the stages of Alzheimer’s disease into three main groups: AD (Alzheimer’s Disease), MCI (Mild Cognitive Impairment) and CN (Cognitively Normal). We evaluate three aggregation strategies (FedAvg, FedAvgM and FedProx), across varying client configurations (3-7), while introducing a hybrid FL-Split Learning (SL) approach to optimize computational efficiency and privacy preservation. As a results of the ResNet-FedProx combination achieved superior performance (91.2% accuracy) in 7-client federated scenarios. In contrast, FedAvgM showed unexpected limitations, with accuracy decreasing by 6.7 percentage points as the number of customers increased. Future work should explore hybrid neural networks that combine ResNet and DenseNet architectures and adapt them to other aggregation models available in the literature to optimize performance.

Referências

Alzheimer’s Disease Neuroimaging Initiative (2024). Adni dataset. [link].

Association, A. (2018). 2018 alzheimer’s disease facts and figures. Alzheimer’s Dementia, 14(3):367–429.

Basnin, N., Biswas, D., and Bhowmik, M. (2025). An evolutionary federated learning approach to diagnose alzheimer’s disease under uncertainty. Neurocomputing.

Elsersy, M., El-Bayoumi, M., and El-Hawashy, H. (2023). Federated learning model for early detection of dementia using blood biosamples. IEEE Access.

Farina, F., Emek-Savaş, D., Rueda-Delgado, L., Boyle, R., Kiiski, H., Yener, G., and Whelan, R. (2020). A comparison of resting state eeg and structural mri for classifying alzheimer’s disease and mild cognitive impairment. Neuroimage, 215.

Ghosh, A. and Krishnamoorthy, S. (2023). Diffcvodensefed: Differential evolution optimization based densenet federated model in alzheimer’s detection. Expert Systems with Applications.

Hariharan, A. (2024). med2image: Python package for medical image conversion. [link].

He, K. et al. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, Las Vegas, NV, USA. IEEE.

Hsu, T.-M. H., Qi, H., and Brown, M. (2019). Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335.

Huang, G. et al. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4700–4708, Honolulu, HI, USA. IEEE.

Huang, L., Zhang, J., Wu, H., Yang, D., Li, D., Wu, X., and Sun, C. (2021). Federated learning via conditional mutual learning for alzheimer’s disease classification on t1w mri. Medical Image Analysis.

Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical Report, Keele University and University of Durham.

Lei, X., Sun, Y., Wang, Q., Zhang, H., Zhang, X., Zhao, Y., Ma, Y., Li, H., Wang, L., and Liu, M. (2024). Hybrid federated learning with brain-region attention network for multi-center alzheimer’s disease detection. Medical Image Analysis.

Li, T. et al. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems, 2:429–450.

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and Arcas, B. A. Y. (2016). Federated learning of deep networks using model averaging. arXiv.

Mihelčić, M., Šimić, G., Babić Leko, M., Lavrač, N., Džeroski, S., and Šmuc, T. (2017). Using redescription mining to relate clinical and biological characteristics of cognitively impaired and alzheimer’s disease patients. PLoS ONE, 12(10).

Naeem, A., Anees, T., Naqvi, R., and Loh, W.-K. (2022). A comprehensive analysis of recent deep and federated-learning-based methodologies for brain tumor diagnosis. J. Pers. Med., 12:275.

Narayanee, S., Reddy, K. R., Shankar, S., Sanyal, S., and Pradhan, A. (2024). Enhancing alzheimer’s disease classification through split federated learning and gans for imbalanced datasets. Neural Computing and Applications.

Ouyang, Z., Lin, L., Ding, W., Yang, T., Gao, C., Wei, Y., Zheng, C., and Zhang, M. (2024). Admarker: A multi-modal federated learning system for monitoring digital biomarkers of alzheimer’s disease. IEEE Journal of Biomedical and Health Informatics.

Rauniyar, A., Haileselassie Hagos, D., Jha, D., Håkegård, J. E., Bagci, U., and Rawat, D. B. (2022). Federated learning for medical applications: A taxonomy current trends challenges and future research directions. arXiv.

Sahid, M. M., Momin, K., and Parvin, N. (2024). Enhancing parallelism in cross-silo federated learning for brain disease classification. Concurrency and Computation: Practice and Experience.

Song, Y., Li, M., Zhang, Y., Li, H., and Liu, M. (2025). Harmonized swarm learning with guided optimization for multi-center smri classification of alzheimer’s disease. IEEE Journal of Biomedical and Health Informatics.

Thapa, C., Chamikara, M. A. P., Camtepe, S., and Sun, L. (2022). Splitfed: When federated learning meets split learning. IEEE Transactions on Parallel and Distributed Systems.

Wei, T., Zhu, T., Jiang, Y., Sun, L., and Wei, X. (2023). Fedcpc: An effective federated contrastive learning method for privacy preserving early-stage alzheimers speech detection. IEEE Journal of Biomedical and Health Informatics.

Zagoruyko, S. and Komodakis, N. (2016). Wide residual networks. In Proceedings of the British Machine Vision Conference, pages 87.1–87.12, York, UK. BMVA Press.