多中心研究：联邦学习模型用于肾上腺转移瘤术前风险评估
该多中心回顾性研究纳入1100例患者共1187个肾上腺病变，基于三期CT构建联邦学习模型（RFLM）鉴别肾上腺转移瘤与良性病变。基于平扫期的RFLM在四个中心测试集AUC分别为0.7826、0.8318、0.8794、0.8895，优于动脉期/静脉期及联邦学习基线模型。结果表明平扫期RFLM可实现有效术前风险评估，有望减少对增强CT的依赖。
要点
- 平扫期RFLM在四个中心测试集AUC为0.7826~0.8895，优于动脉期和静脉期。
- 平扫期模型有望减少增强CT使用，降低额外辐射和并发症风险。
- 联邦学习框架可在保护数据隐私下利用多中心非独立同分布数据。
核心结论
- 基于平扫期的联邦学习模型（RFLM）能有效进行肾上腺转移瘤与良性病变的术前风险评估，可能减少对增强CT的依赖。
研究设计与样本
- 多中心回顾性研究，纳入2008年1月至2021年9月间1100例患者的1187个肾上腺病变，均行三期CT扫描。
- 结合图结构网络与互信息构建鲁棒联邦学习模型（RFLM），在平扫期、静脉期和动脉期分别进行实验。
- 对RFLM中各中心特征进行相关性分析以探索模型内在机制。
诊断标准与关键数值
- 基于平扫期的RFLM在中心1-4测试集AUC分别为0.7826、0.8318、0.8794、0.8895，均优于动脉期/静脉期及联邦学习基线。
临床应用与阅片要点
- 平扫期RFLM可用于术前鉴别肾上腺转移瘤与良性病变，减少增强CT依赖。
- 联邦学习框架有助于在多中心数据隐私保护下构建稳健模型。
局限性
- 回顾性研究设计。
- 仅报告AUC，未提供敏感度、特异度等完整诊断性能指标。
以上解读依据论文摘要（全文未开放获取或许可不允许翻译转载）。
英文原文（摘要）· 点击展开
RATIONALE AND OBJECTIVES: In clinical practice, the preoperative risk assessment of adrenal metastases versus benign adrenal lesions carries a substantial risk of misdiagnosis. The artificial intelligence technology holds promise for reducing misdiagnosis rates. However, due to the problem of data privacy protection and non-independent and identically distributed of multi-center data, the performance of artificial intelligence models is significantly affected.
MATERIALS AND METHODS: We retrospectively collected 1187 adrenal lesions from 1100 patients who underwent three phase Computed tomography (CT) scanning between January 2008 and September 2021. And then, we combined graph structure networks and mutual information to construct a robust federated learning model (RFLM) for the preoperative risk assessment of adrenal metastases and adrenal benign lesions. We conducted experiments on three-phase (pre-contrast phase (PCP), venous phase (VP) and arterial phase (AP)). In addition, we also conduct correlation analysis of the features of each center in RFLM to explore the intrinsic mechanism of the model.
RESULTS: PCP-based RFLM outperformed AP/VP and the evaluated federated learning baselines on all four center-specific test sets, with AUCs of 0.7826, 0.8318, 0.8794, and 0.8895 for Centers 1-4, respectively. Additional analyses supported its superior performance and potential clinical utility across centers.
CONCLUSION: Our results indicate that PCP-based RFLM enables effective preoperative risk assessment of adrenal metastases and benign lesions, potentially reducing reliance on enhanced CT and thus minimizing additional radiation and complications. These findings underscore RFLM as a robust and reliable diagnostic approach.
引用
- Feng B, Yu Z, Chen Y, et al. Preoperative Risk Assessment of Adrenal Metastases in a Multicenter Study: Development of a Robust Federated Learning Model. Acad Radiol. 2026. PMID: 42173766. doi:10.1016/j.acra.2026.04.041
供执业医师工作参考，不替代临床判断；数值与分级以指南原文为准。