Abstract
Graph neural networks (GNNs) have achieved extraordinary enhancements in various areas including the fields medical imaging and network neuroscience where they displayed a high accuracy in diagnosing challenging neurological disorders such as autism. In the face of medical data scarcity and high-privacy, training such data-hungry models remains challenging. Federated learning brings an efficient solution to this issue by allowing to train models on multiple datasets, collected independently by different hospitals, in fully data-preserving manner. Although both state-of-the-art GNNs and federated learning techniques focus on boosting classification accuracy, they overlook a critical unsolved problem: investigating the reproducibility of the most discriminative biomarkers (i.e., features) selected by the GNN models within a federated learning paradigm. Quantifying the reproducibility of a predictive medical model against perturbations of training and testing data distributions presents one of the biggest hurdles to overcome in developing translational clinical applications. To the best of our knowledge, this presents the first work investigating the reproducibility of federated GNN models with application to classifying medical imaging and brain connectivity datasets. We evaluated our framework using various GNN models trained on medical imaging and connectomic datasets. More importantly, we showed that federated learning boosts both the accuracy and reproducibility of GNN models in such medical learning tasks. Our source code is available at https://github.com/basiralab/reproducibleFedGNN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lee, J.G., et al.: Deep learning in medical imaging: general overview. Korean J. Radiol. 18, 570–584 (2017)
Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221 (2017)
Wolterink, J., Suk, J.: Geometric deep learning for precision medicine. Key Enabling Technol. Sci. Mach. Learn. 60
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34, 18–42 (2017)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 4–24 (2020)
Bessadok, A., Mahjoub, M.A., Rekik, I.: Graph neural networks in network neuroscience. arXiv preprint arXiv:2106.03535 (2021)
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, PMLR, pp. 1273–1282 (2017)
Nebli, A., Gharsallaoui, M.A., Gürler, Z., Rekik, I., Initiative, A.D.N., et al.: Quantifying the reproducibility of graph neural networks using multigraph data representation. Neural Netw. 148, 254–265 (2022)
Georges, N., Mhiri, I., Rekik, I., Initiative, A.D.N., et al.: Identifying the best data-driven feature selection method for boosting reproducibility in classification tasks. Pattern Recogn. 101, 107183 (2020)
Georges, N., Rekik, I.: Data-specific feature selection method identification for most reproducible connectomic feature discovery fingerprinting brain states. In: Wu, G., Rekik, I., Schirmer, M.D., Chung, A.W., Munsell, B. (eds.) CNI 2018. LNCS, vol. 11083, pp. 99–106. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00755-3_11
Forcier, M.B., Gallois, H., Mullan, S., Joly, Y.: Integrating artificial intelligence into health care through data access: can the GDPR act as a beacon for policymakers? J. Law Biosci. 6, 317 (2019)
Chen, C., Hu, W., Xu, Z., Zheng, Z.: Fedgl: federated graph learning framework with global self-supervision. arXiv preprint arXiv:2105.03170 (2021)
He, C., et al.: Fedgraphnn: a federated learning benchmark system for graph neural networks. In: ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML) (2021)
Yang, J., et al.: Medmnist v2: A large-scale lightweight benchmark for 2D and 3d biomedical image classification. arXiv preprint arXiv:2110.14795 (2021)
Gereige, R.S., Laufer, P.M.: Pneumonia. Pediatr. Rev. 34, 438–456 (2013)
Di Martino, A., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19, 659–667 (2014)
Soussia, M., Rekik, I.: Unsupervised manifold learning using high-order morphological brain networks derived from T1-w MRI for autism diagnosis. Front. Neuroinform. 12, 70 (2018)
Fischl, B., et al.: Sequence-independent segmentation of magnetic resonance images. Neuroimage 23, S69–S84 (2004)
Fischl, B.: Freesurfer. Neuroimage 62, 774–781 (2012)
Mahjoub, I., Mahjoub, M.A., Rekik, I.: Brain multiplexes reveal morphological connectional biomarkers fingerprinting late brain dementia states. Sci. Rep. 8, 1–14 (2018)
Ying, R., You, J., Morris, C., Ren, X., Hamilton, W.L., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. arXiv preprint arXiv:1806.08804 (2018)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lou, B., et al.: Quantitative analysis of synthetic magnetic resonance imaging in Alzheimer’s disease. Front. Aging Neurosci. 13, 638731 (2021)
Gasquoine, P.G.: Contributions of the insula to cognition and emotion. Neuropsychol. Rev. 24, 77–87 (2014). https://doi.org/10.1007/s11065-014-9246-9
Nomi, J.S., Molnar-Szakacs, I., Uddin, L.Q.: Insular function in autism: update and future directions in neuroimaging and interventions. Prog. Neuropsychopharmacol. Biol. Psychiatry 89, 412–426 (2019)
Gebauer, L., Foster, N.E., Vuust, P., Hyde, K.L.: Is there a bit of autism in all of us? autism spectrum traits are related to cortical thickness differences in both autism and typical development. Res. Autism Spectr. Disord. 13, 8–14 (2015)
Habata, K., et al.: Relationship between sensory characteristics and cortical thickness/volume in autism spectrum disorders. Transl. Psychiatry 11, 1–7 (2021)
Kitamura, S., et al.: Association of adverse childhood experiences and precuneus volume with intrusive reexperiencing in autism spectrum disorder. Autism Res. 14, 1886–1895 (2021)
Khundrakpam, B.S., Lewis, J.D., Kostopoulos, P., Carbonell, F., Evans, A.C.: Cortical thickness abnormalities in autism spectrum disorders through late childhood, adolescence, and adulthood: a large-scale MRI study. Cereb. Cortex 27, 1721–1731 (2017)
Acknowledgements
This work was funded by generous grants from the European H2020 Marie Sklodowska-Curie action (grant no. 101003403, http://basira-lab.com/normnets/) to I.R. and the Scientific and Technological Research Council of Turkey to I.R. under the TUBITAK 2232 Fellowship for Outstanding Researchers (no. 118C288, http://basira-lab.com/reprime/). However, all scientific contributions made in this project are owned and approved solely by the authors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Balık, M.Y., Rekik, A., Rekik, I. (2022). Investigating the Predictive Reproducibility of Federated Graph Neural Networks Using Medical Datasets. In: Rekik, I., Adeli, E., Park, S.H., Cintas, C. (eds) Predictive Intelligence in Medicine. PRIME 2022. Lecture Notes in Computer Science, vol 13564. Springer, Cham. https://doi.org/10.1007/978-3-031-16919-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-16919-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16918-2
Online ISBN: 978-3-031-16919-9
eBook Packages: Computer ScienceComputer Science (R0)