Privacy-Preserving Virtual Contrast-enhanced MRI for Nasopharyngeal Carcinoma: A Multi-center Study.

Abstract

Contrast-enhanced MRI imaging via administration of contrast agents is critical for diagnosis, staging, and treatment of nasopharyngeal carcinoma. However, gadolinium-based contrast agents can lead to severe adverse effects, especially in patients with compromised kidney function, necessitating a safer alternative for contrast enhancement. In this study, we aim to develop and assess the clinical feasibility of a federated learning model for synthesizing virtual contrast-enhanced MRI (VCE-MRI) images from contrast-free scans for patients with nasopharyngeal carcinoma (NPC). In this multicenter, retrospective study, we developed and clinically evaluated a federated learning-based VCE-MRI synthesis model (FL-VCE-MRI) using pre-treatment contrast-free T1-weighted and T2-weighted MRI scans. The model was trained using data from 14 centers involving 2,061 patients. External validation was performed with an independent dataset from 25 centers comprising 126 patients. Additionally, ten clinicians from eight centers assessed the quality of the synthetic images. The FL-VCE-MRI model demonstrated high generalizability in the external validation dataset, achieving a mean absolute error (MAE) of 45.85 (95% CI, 43.73-47.96). For centers facing challenges in developing well-performing single-center models, the FL-VCE-MRI improved the average MAE from 53.93 (95% CI: 49.21-58.65) to 45.93 (95% CI: 41.64-50.22). Clinical evaluations indicated that the synthesized VCE-MRI images are both reliable and clinically valuable, with no significant differences compared to gadolinium-enhanced MRI in disease diagnosis, tumor staging, and delineation. The FL-VCE-MRI model shows potential as a non-invasive alternative to gadolinium-enhanced MRI for NPC patients.