基于超分辨率MRI的可解释融合深度学习预测胰腺导管腺癌神经周围侵犯:多中心研究
这项多中心回顾性研究纳入714例胰腺导管腺癌患者,基于超分辨率MRI构建融合临床-影像组学-深度迁移学习(FCDR)模型预测神经周围侵犯,开发集、内部验证集和外部验证集AUC分别为0.929、0.886和0.832。模型分层的高风险组术后总生存期和无复发生存期显著更差,且该模型识别的高风险神经周围侵犯亚组从辅助治疗中获得显著生存获益。
要点
- FCDR模型在开发集、内部验证集和外部验证集预测神经周围侵犯的AUC分别为0.929、0.886和0.832。
- 模型分层高风险组术后总生存期和无复发生存期显著更差(p < 0.05)。
- 模型识别的高风险神经周围侵犯亚组从辅助治疗中获得显著总生存期和无复发生存期获益。
核心结论
- 基于超分辨率MRI的可解释融合模型可作为胰腺导管腺癌神经周围侵犯评估、预后分层和辅助治疗定制的有效工具,对个性化精准医学有重要意义。
研究设计与样本
- 多中心回顾性研究,纳入714例符合条件的患者,608例分配至开发/内部验证集,106例来自三个外部中心构成外部验证集;基于超分辨率MRI的深度学习与影像组学特征结合临床危险因素构建FCDR模型,并从七种机器学习算法中选择表现最佳者进行优化。
诊断标准与关键数值
- FCDR模型预测神经周围侵犯的AUC在开发集为0.929、内部验证集为0.886、外部验证集为0.832,显著优于单一临床、深度学习或影像组学模型。
临床应用与阅片要点
- FCDR模型可用于术前无创评估胰腺导管腺癌神经周围侵犯,并据此进行预后分层和辅助治疗决策;模型可解释性经SHAP分析确认。
局限性
- 原文未报告局限性。
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
PURPOSE: To develop an interpretable fusion deep learning model based on super-resolution (SR) MRI for predicting preoperative perineural invasion (PNI) in pancreatic ductal adenocarcinoma (PDAC) and to evaluate its role in guiding postoperative prognostic and therapeutic decision-making.
MATERIALS AND METHODS: In this multicenter retrospective study, we enrolled 714 eligible patients, allocating 608 to a development/internal validation set and 106 from three external centers to an external validation set. The fusion clinical-radiomics-deep transfer learning (FCDR) was developed to predict PNI by integrating imaging signatures derived from deep learning and radiomics on SR-MRI with clinical risk factors and was optimized by selecting the best-performing among seven machine learning algorithms. The final model was subsequently validated for its incremental value in predicting postoperative prognosis and guiding adjuvant therapy.
RESULTS: The FCDR model achieved superior performance of PNI prediction with AUCs of 0.929, 0.886, and 0.832 across development, internal and external validation sets, significantly outperforming single clinical, DL, or radiomics models. The FCDR model-stratified high-risk group was associated with significantly worse postoperative OS and RFS (p < 0.05). Moreover, the high-risk PNI subgroup stratified by this model derived a significant OS and RFS benefit from adjuvant therapy. Model interpretability was affirmed by SHAP analysis.
CONCLUSION: The proposed interpretable fusion model serves as an effective tool for PNI evaluation, prognostic stratification, and tailoring of adjuvant therapy in PDAC, holding significant promise for personalized precision medicine.
CRITICAL RELEVANCE STATEMENT: The constructed fusion model offers a robust, non-invasive tool for identifying PNI in pancreatic ductal adenocarcinoma, showing significant potential to guide personalized treatment strategies and improve patient outcomes.
引用
- Li J, Xu J, Shen T, et al. Interpretable fusion deep learning on super-resolution MRI for perineural invasion prediction in pancreatic ductal adenocarcinoma: a multicenter study. Eur J Radiol. 2025. PMID: 41418691. doi:10.1016/j.ejrad.2025.112610
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。