基于MRI多层级放射组学与Transformer特征预测鼻咽癌放疗后放射性颈动脉损伤的多中心研究
本研究为多中心回顾性研究,纳入四家医院500例鼻咽癌患者,构建融合常规放射组学、亚区域放射组学和Swin Transformer深度学习特征的Rad-SRad-SwinT模型,用于预测放疗后放射性颈动脉损伤。融合模型在内部测试集AUC为0.814(95%CI: 0.737-0.891),外部测试集AUC为0.871(95%CI: 0.794-0.932),外部测试集分类性能ACC 0.815、SEN 0.763、SPE 0.878,校准良好(Brier score 0.148)。
要点
- 融合Rad、SRad和SwinT特征的多层级模型预测放射性颈动脉损伤性能最佳。
- 外部测试集AUC达0.871(95%CI: 0.794-0.932),分类与校准表现良好。
- SwinT深度学习特征对模型决策贡献最大,其次为SRad和Rad。
核心结论
- 整合多层级放射组学与Transformer深度学习特征可提升鼻咽癌放疗后放射性颈动脉损伤的预测性能,有望作为无创风险分层工具。
研究设计与样本
- 多中心回顾性研究,纳入四家医院500例鼻咽癌患者,分为训练集274例、内部测试集118例和外部测试集108例。
主要发现
- 放射性颈动脉损伤在训练集、内部测试集和外部测试集的发生率分别为48.5%、48.3%和54.6%。
- 单源模型中SwinT与SRad性能相当,Rad稍逊,但均优于临床模型。
- 融合模型Rad-SRad-SwinT在内部测试集AUC为0.814(95%CI: 0.737-0.891),外部测试集AUC为0.871(95%CI: 0.794-0.932)。
- 外部测试集分类性能:ACC 0.815、SEN 0.763、SPE 0.878;校准良好,Brier score 0.148。
- NRI/IDI分析显示融合模型较单源模型显著改善重分类;SHAP分析显示SwinT特征贡献最大,其次为SRad和Rad。
临床怎么用
- 该融合模型可作为鼻咽癌放疗后放射性颈动脉损伤的无创风险分层工具,辅助临床识别高危患者。
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)。
原文
PURPOSE: To develop and validate an MRI-based fusion model (Rad-SRad-SwinT) integrating conventional radiomics (Rad), subregional radiomics (SRad), and Transformer-derived deep learning features (Swin Transformer, SwinT) to predict post-radiotherapy radiation-induced carotid artery injury (RICAI) in nasopharyngeal carcinoma (NPC). MATERIALS AND METHODS: In this multicenter retrospective study, 500 NPC patients from four hospitals were allocated to training (n = 274), internal testing (n = 118), and external testing cohorts (n = 108). Rad features were extracted from MRI-defined carotid artery regions of interest, SRad features from K-means-derived subregions, and deep features from a SwinT backbone. Single-source and fusion models were developed. Discrimination (AUC), classification (ACC/SEN/SPE), calibration (Brier score and calibration curves), reclassification (NRI/IDI), and interpretability (SHAP) were assessed. RESULTS: RICAI was observed in 48.5%, 48.3%, and 54.6% of the training, internal testing, and external testing cohorts, respectively. Among single-source models, SwinT and SRad showed comparable performance, with Rad slightly inferior; all outperformed the clinical model. The fused Rad-SRad-SwinT achieved the best performance, with AUCs of 0.814 (95% CI: 0.737-0.891) in internal testing and 0.871 (95% CI: 0.794-0.932) in external testing, alongside favorable classification in external testing (ACC 0.815, SEN 0.763, SPE 0.878) and good calibration (Brier score 0.148). NRI/IDI analyses indicated significantly improved reclassification versus single-source models. SHAP analyses demonstrated that SwinT-derived features contributed most to model decisions, followed by SRad and Rad, supporting complementary gains from deep semantic representation and subregional heterogeneity quantification. CONCLUSION: Integrating multilevel radiomics with Transformer-derived deep learning features enhances prediction of RICAI after NPC radiotherapy and shows promise as a noninvasive risk-stratification tool.
引用
- Zhang H, Ding J, Zhang L, et al. MRI-based multilevel radiomics and transformer features for predicting radiation-induced carotid artery injury after nasopharyngeal carcinoma radiotherapy: A multicenter study. Radiother Oncol. 2026. PMID: 41587618. doi:10.1016/j.radonc.2026.111390
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。