Abstract
The purpose of this study is to investigate the model generalizability using multi-institutional data for virtual contrast-enhanced MRI (VCE-MRI) synthesis. This study presented a retrospective analysis of contrast-free T1-weighted (T1w), T2-weighted (T2w), and gadolinium-based contrast-enhanced T1w MRI (CE-MRI) images of 231 NPC patients enrolled from four institutions. Data from three of the participating institutions were employed to generate a training and an internal testing set, while data from the remaining institution was employed as an independent external testing set. The multi-institutional data were trained separately (single-institutional model) and jointly (joint-institutional model) and tested using the internal and external sets. The synthetic VCE-MRI was quantitatively evaluated using MAE and SSIM. In addition, visual qualitative evaluation was performed to assess the quality of synthetic VCE-MRI compared to the ground-truth CE-MRI. Quantitative analyses showed that the joint-institutional models outperformed single-institutional models in both internal and external testing sets, and demonstrated high model generalizability, yielding top-ranked MAE, and SSIM of 71.69 ± 21.09 and 0.81 ± 0.04 respectively on the external testing set. Qualitative evaluation indicated that the joint-institutional model gave a closer visual approximation between the synthetic VCE-MRI and ground-truth CE-MRI on the external testing set, compared with single-institutional models. The model generalizability for VCE-MRI synthesis was enhanced, both quantitatively and qualitatively, when data from more institutions was involved during model development.
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
Marckmann, P., Skov, L., Rossen, K., et al.: Nephrogenic systemic fibrosis: suspected causative role of gadodiamide used for contrast-enhanced magnetic resonance imaging. J. Am. Soc. Nephrol. 17(9), 2359–2362 (2006)
Saxena, S.K., Sharma, M., Patel, M., Oreopoulos, D.: Nephrogenic systemic fibrosis: an emerging entity. Int. Urol. Nephrol. 40(3), 715–724 (2008)
Swaminathan, S., High, W., Ranville, J., et al.: Cardiac and vascular metal deposition with high mortality in nephrogenic systemic fibrosis. Kidney Int. 73(12), 1413–1418 (2008)
Khawaja, A.Z., Cassidy, D.B., Al Shakarchi, J., McGrogan, D.G., Inston, N.G., Jones, R.G.: Revisiting the risks of MRI with Gadolinium based contrast agents-review of literature and guidelines. Insights Imaging 6(5), 553–558 (2015). https://doi.org/10.1007/s13244-015-0420-2
Roberts, D.R., Chatterjee, A., Yazdani, M., et al.: Pediatric patients demonstrate progressive T1-weighted hyperintensity in the dentate nucleus following multiple doses of gadolinium-based contrast agent. Am. J. Neuroradiol. 37(12), 2340–2347 (2016)
Grobner, T., Prischl, F.: Gadolinium and nephrogenic systemic fibrosis. Kidney Int. 72(3), 260–264 (2007)
Aime, S., Caravan, P.: Biodistribution of gadolinium-based contrast agents, including gadolinium deposition. J. Magn. Reson. Imaging Official J. Int. Soc. Magn. Res. Med. 30(6), 1259–1267 (2009)
Gong, E., Pauly, J.M., Wintermark, M., Zaharchuk, G.: Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J. Magn. Reson. Imaging 48(2), 330–340 (2018)
Kleesiek, J., Morshuis, J.N., Isensee, F., et al.: Can virtual contrast enhancement in brain MRI replace gadolinium?: a feasibility study. Invest. Radiol. 54(10), 653–660 (2019)
Xu, C., Zhang, D., Chong, J., Chen, B., Li, S.: Synthesis of gadolinium-enhanced liver tumors on nonenhanced liver MR images using pixel-level graph reinforcement learning. Med. Image Anal. 69, 101976 (2021)
Zhao, J., Li, D., Kassam, Z., et al.: Tripartite-GAN: synthesizing liver contrast-enhanced MRI to improve tumor detection. Med. Image Anal. 63, 101667 (2020)
Kim, E., Cho, H.-H., Ko, E., Park, H.: Generative adversarial network with local discriminator for synthesizing breast contrast-enhanced MRI. In: 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) (2021)
Li, W., Xiao, H., Li, T., 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)
Cho, H., Nishimura, K., Watanabe, K., Bise, R.: Cell detection in domain shift problem using pseudo-cell-position heatmap. In: de Bruijne, M., et al. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. LNCS, vol. 12908, pp. 384–394. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87237-3_37
Klein, S., Staring, M., Murphy, K., Viergever, M.A., Pluim, J.P.: Elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2009)
Onofrey, J.A., Casetti-Dinescu, D.I., Lauritzen, A.D., et al.: Generalizable multi-site training and testing of deep neural networks using image normalization. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) (2019)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Kanbak, C., Moosavi-Dezfooli, S.-M., Frossard, P.: Geometric robustness of deep networks: analysis and improvement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Sanford, T.H., Zhang, L., Harmon, S.A., et al.: Data augmentation and transfer learning to improve generalizability of an automated prostate segmentation model. Am. J. Roentgenol. 215(6), 1403–1410 (2020)
Liu, Q., Dou, Q., Yu, L., Heng, P.A.: MS-Net: multi-site network for improving prostate segmentation with heterogeneous MRI data. IEEE Trans. Med. Imaging 39(9), 2713–2724 (2020)
Li, W., Kazemifar, S., Bai, T., et al.: Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning. Biomed. Phys. Eng. Express 7(2), 025020 (2021)
Acknowledgment
This work was partly supported by funding GRF 151022/19M and ITS/080/19.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, W. et al. (2022). Multi-institutional Investigation of Model Generalizability for Virtual Contrast-Enhanced MRI Synthesis. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13437. Springer, Cham. https://doi.org/10.1007/978-3-031-16449-1_73
Download citation
DOI: https://doi.org/10.1007/978-3-031-16449-1_73
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16448-4
Online ISBN: 978-3-031-16449-1
eBook Packages: Computer ScienceComputer Science (R0)
