用联邦学习实现跨机构头颈CBCT转sCT，保护隐私还能保持高精度。
A Privacy-Preserving Federated Learning Framework for Generalizable CBCT to Synthetic CT Translation in Head and Neck
- 采用跨中心联邦学习训练生成对抗网络，无需共享原始数据。
- 多中心测试误差在64.38至85.90 HU间，外部验证达75.22 HU。
- 适合医疗影像协作建模，尤其关注数据隐私与模型泛化者。
锥形束计算机断层扫描（CBCT）在图像引导放疗中广泛应用，但存在噪声大、软组织对比度低、伪影等问题，导致亨氏单位值不可靠，难以直接用于剂量计算。从CBCT生成合成CT（sCT）可缓解此问题，尤其借助深度学习方法。现有方法受限于机构差异、设备依赖及数据隐私法规，难以实现多中心数据共享。为此，我们提出一种跨域水平联邦学习框架，用于头颈部区域的CBCT到sCT转换，扩展了原有的FedSynthCT框架。基于公开的SynthRAD2025挑战数据集，三个欧洲医学中心的联合数据上协同训练条件生成对抗网络。联邦模型在各中心表现良好，平均绝对误差（MAE）为64.38±13.63至85.90±7.10 HU，结构相似性指数（SSIM）为0.882±0.022至0.922±0.039，峰值信噪比（PSNR）为32.86±0.94至34.91±1.04 dB。在60例患者的外部验证集上，未重新训练即达到相当性能（MAE: 75.22±11.81 HU，SSIM: 0.904±0.034，PSNR: 33.52±2.06 dB），证实其在不同扫描协议、设备差异和配准误差下仍具强泛化能力。结果表明，联邦学习可用于实现私密保护下的CBCT-to-sCT合成，为跨机构通用模型构建提供无需集中数据共享或站点微调的协作方案。
原文摘要 · Abstract (English)
Shortened Abstract Cone-beam computed tomography (CBCT) has become a widely adopted modality for image-guided radiotherapy (IGRT). However, CBCT suffers from increased noise, limited soft-tissue contrast, and artifacts, resulting in unreliable Hounsfield unit values and hindering direct dose calculation. Synthetic CT (sCT) generation from CBCT addresses these issues, especially using deep learning (DL) methods. Existing approaches are limited by institutional heterogeneity, scanner-dependent variations, and data privacy regulations that prevent multi-center data sharing. To overcome these challenges, we propose a cross-silo horizontal federated learning (FL) approach for CBCT-to-sCT synthesis in the head and neck region, extending our FedSynthCT framework. A conditional generative adversarial network was collaboratively trained on data from three European medical centers in the public SynthRAD2025 challenge dataset. The federated model demonstrated effective generalization across centers, with mean absolute error (MAE) ranging from $64.38\pm13.63$ to $85.90\pm7.10$ HU, structural similarity index (SSIM) from $0.882\pm0.022$ to $0.922\pm0.039$, and peak signal-to-noise ratio (PSNR) from $32.86\pm0.94$ to $34.91\pm1.04$ dB. Notably, on an external validation dataset of 60 patients, comparable performance was achieved (MAE: $75.22\pm11.81$ HU, SSIM: $0.904\pm0.034$, PSNR: $33.52\pm2.06$ dB) without additional training, confirming robust generalization despite protocol, scanner differences and registration errors. These findings demonstrate the technical feasibility of FL for CBCT-to-sCT synthesis while preserving data privacy and offer a collaborative solution for developing generalizable models across institutions without centralized data sharing or site-specific fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。