Abstract
In this study, we developed a trusted federated learning framework (FL-TrustVCE) for multi-institutional virtual contrast-enhanced MRI (VCE-MRI) synthesis. The FL-TrustVCE is featured with patient privacy preservation, data poisoning prevention, and multi-institutional data training. For FL-TrustVCE development, we retrospectively collected MRI data from 18 institutions, in total 438 patients were involved. For each patient, T1-weighted MRI, T2-weighted MRI, and corresponding CE-MRI were collected. T1-weighted and T2-weighted MRI were used as input to provide complementary information, and CE-MRI was used as the learning target. Data from 14 institutions were used for FL-TrustVCE model development and internal evaluation, while data from the other 4 institutions were used for external evaluation. The synthetic VCE-MRI was quantitatively evaluated using MAE and PSNR. The data poisoning prevention was visually assessed by reviewing the excluded images after training. Three single institutional models (separately trained with single institutional data), a joint model (jointly trained using multi-institutional data), and two popular federated learning frameworks (FedAvg and FedProx) were used for comparison. Quantitative results show that the proposed FL-TrustVCE outperformed all comparison methods in both internal and external testing datasets, yielding top-ranked average MAE and PSNR of 23.45 ± 4.93 and 33.23 ± 1.50 for internal datasets and 30.86 ± 7.20 and 31.87 ± 1.71 for external datasets. The poisoned data was successfully excluded. This study demonstrated that the proposed FL-TrustVCE is able to improve the VCE-MRI model generalizability and defend against data poisoning in the setting of multi-institutional model development.
W. Li and Y. Shi—Contributed equally to this work.
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
References
Zahra, M.A., et al.: Dynamic contrast-enhanced MRI as a predictor of tumour response to radiotherapy. Lancet Oncol. 8(1), 63–74 (2007)
Grossman, R.I., et al.: Multiple sclerosis: gadolinium enhancement in MR imaging. Radiology 161(3), 721–725 (1986)
Sadowski, E.A., et al.: Nephrogenic systemic fibrosis: risk factors and incidence estimation. Radiology 243(1), 148–157 (2007)
Thomsen, H.S.: Nephrogenic systemic fibrosis: a serious late adverse reaction to gadodiamide. Eur. Radiol. 16(12), 2619–2621 (2006)
Schlaudecker, J.D., Bernheisel, C.R.: Gadolinium-associated nephrogenic systemic fibrosis. Am. Fam. Physician 80(7), 711–714 (2009)
Kleesiek, J., et al.: Can virtual contrast enhancement in brain MRI replace gadolinium?: a feasibility study. Invest. Radiol. 54(10), 653–660 (2019)
Gong, E., et al.: Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J. Magn. Reson. Imaging 48(2), 330–340 (2018)
Li, W., et al., Gadolinium-free Contrast-enhanced MRI (GFCE-MRI) Synthesis via Generalizable MHDgN-Net for Patients with Nasopharyngeal Carcinoma
Li, W., et al., CE-Net: multi-inputs contrast enhancement network for nasopharyngeal carcinoma contrast enhanced T1-weighted MR synthesis
Zhao, J., et al.: Tripartite-GAN: synthesizing liver contrast-enhanced MRI to improve tumor detection. Med. Image Anal. 63, 101667 (2020)
Li, W., et al.: Virtual contrast-enhanced magnetic resonance images synthesis for patients with nasopharyngeal carcinoma using multimodality-guided synergistic neural network. Int. J. Radiat. Oncol. Biol. Phys. 112(4), 1033–1044 (2022). https://doi.org/10.1016/j.ijrobp.2021.11.007
Li, W., et al.: Multi-institutional investigation of model generalizability for virtual contrast-enhanced MRI synthesis. In: Wang, L., Qi Dou, P., Fletcher, T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VII, pp. 765–773. Springer Nature Switzerland, Cham (2022). https://doi.org/10.1007/978-3-031-16449-1_73
Rieke, N., et al.: The future of digital health with federated learning. NPJ Dig. Med. 3(1), 119 (2020)
Biggio, B., Nelson, B., Laskov, P.: Poisoning attacks against support vector machines. arXiv preprint arXiv:1206.6389 (2012)
Fang, M., et al. Local model poisoning attacks to byzantine-robust federated learning. In: Proceedings of the 29th USENIX Conference on Security Symposium (2020)
Bagdasaryan, E., et al.: How to backdoor federated learning. In: International Conference on Artificial Intelligence and Statistics. PMLR (2020)
Xie, C., et al.: DBA: distributed backdoor attacks against federated learning. In: International Conference on Learning Representations (2020)
Cao, X., et al.: FLTrust: byzantine-robust federated learning via trust bootstrapping. arXiv preprint arXiv:2012.13995 (2020)
Li, X., et al.: FedBN: federated learning on Non-IID features via local batch normalization. arXiv preprint arXiv:2102.07623 (2021)
Kamp, M., Fischer, J., Vreeken, J.: Federated learning from small datasets. arXiv preprint arXiv:2110.03469 (2021)
Kamp, M., et al. Efficient decentralized deep learning by dynamic model averaging. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2018, Dublin, Ireland, September 10–14, 2018, Proceedings, Part I 18. Springer (2019). https://doi.org/10.1007/978-3-030-10925-7_24
Yaniv, Z., et al.: SimpleITK image-analysis notebooks: a collaborative environment for education and reproducible research. J. Digit. Imaging 31(3), 290–303 (2018)
McMahan, B., et al.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics. PMLR (2017)
Li, T., et al.: Federated optimization in heterogeneous networks. Proc. Mach. Learn. Syst. 2, 429–450 (2020)
Acknowledgement
This research was partly supported by research grants of General Research Fund (GRF 15102219, GRF 15103520), the University Grants Committee, and Project of Strategic Importance Fund (P0035421), Projects of RISA (P0043001), One-line Budget (P0039824, P0044474), The Hong Kong Polytechnic University, and Shenzhen-Hong Kong-Macau S&T Program (Category C) (SGDX20201103095002019), Shenzhen Basic Research Program (R2021A067), Shenzhen Science and Technology Innovation Committee (SZSTI).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, W. et al. (2023). Virtual Contrast-Enhanced MRI Synthesis with High Model Generalizability Using Trusted Federated Learning (FL-TrustVCE): A Multi-institutional Study. In: Qin, W., Zaki, N., Zhang, F., Wu, J., Yang, F., Li, C. (eds) Computational Mathematics Modeling in Cancer Analysis. CMMCA 2023. Lecture Notes in Computer Science, vol 14243. Springer, Cham. https://doi.org/10.1007/978-3-031-45087-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-45087-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45086-0
Online ISBN: 978-3-031-45087-7
eBook Packages: Computer ScienceComputer Science (R0)
