深度学习超分辨率重建提升MRI影像组学预测胎盘植入谱系疾病及侵袭性的效能
本研究回顾性纳入三个中心共245例胎盘MRI患者,采用生成对抗网络生成超分辨率T2WI(SRT2WI),并构建T2WI、SRT2WI及SRT2WI-临床联合模型预测胎盘植入谱系疾病(PAS)及侵袭性PAS。结果显示SRT2WI-临床模型在训练集及验证集中AUC最高,SRT2WI的AUC数值上高于T2WI,提示超分辨率联合影像组学有潜力改善PAS预测。
要点
- SRT2WI-临床联合模型对PAS及侵袭性PAS的预测AUC最高,外部验证AUC分别为0.793/0.788和0.843/0.815。
- SRT2WI在全部四个队列中AUC数值上均高于原始T2WI,但部分验证集差异未达统计学显著。
- 临床特征联合影像组学可进一步提升模型性能,决策曲线分析支持其临床净获益。
核心结论
- 超分辨率重建联合影像组学可提升MRI对PAS及侵袭性PAS的预测效能,整合临床特征后模型性能进一步提高。
研究设计与样本
- 回顾性多中心研究,共纳入245例胎盘MRI患者,来自三家机构。
- 158例来自机构I用于训练集和内部验证集,34例来自机构II、53例来自机构III作为外部验证集1和2。
- 采用生成对抗网络(GAN)对T2WI进行超分辨率重建生成SRT2WI。
- 基于T2WI、SRT2WI及SRT2WI-临床联合构建预测PAS和侵袭性PAS的模型。
- 以两位放射科医师独立基于T2WI诊断PAS的结果作为参考标准评估模型性能。
诊断标准与关键数值
- PAS预测:SRT2WI-临床模型在训练集、内部验证集、外部验证集1和2的AUC分别为0.953、0.887、0.793、0.788;T2WI对应AUC为0.738、0.697、0.654、0.652;SRT2WI对应AUC为0.879、0.820、0.696、0.768。
- 侵袭性PAS预测:SRT2WI-临床模型在训练集、内部验证集、外部验证集1和2的AUC分别为0.895、0.875、0.843、0.815;T2WI对应AUC为0.774、0.699、0.575、0.745;SRT2WI对应AUC为0.861、0.794、0.729、0.808。
- PAS预测中,SRT2WI-临床模型仅在训练集显著优于T2WI(P < 0.001)和SRT2WI(P = 0.004),验证集中差异无统计学意义。
- 侵袭性PAS预测中,SRT2WI-临床模型在训练集、内部验证集和外部验证集1显著优于T2WI(P = 0.003、0.021、0.019),在外部验证集2无显著差异(P = 0.398);与SRT2WI比较均无显著差异。
- 校准曲线显示良好一致性,决策曲线分析支持SRT2WI-临床模型,SHAP值量化了特征贡献。
临床应用与阅片要点
- 在胎盘MRI阅片及报告中,可关注超分辨率重建T2WI图像辅助影像组学分析,以提高PAS及侵袭性PAS的预测准确性。
- 联合临床特征构建模型可能进一步提升预测效能,但需注意外部验证中部分对比未达统计学显著,模型泛化性需进一步验证。
- 目前模型性能评估以两位放射科医师T2WI诊断为参考,临床应用中仍需结合医师判读。
局限性
- 回顾性研究设计。
- 外部验证集中SRT2WI-临床模型与T2WI或SRT2WI的部分性能比较无统计学显著差异。
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
OBJECTIVES: Placenta Accreta Spectrum (PAS) is a severe obstetric complication. This study evaluated whether retrospective, post-processing deep learning-based super-resolution reconstruction (SR) was associated with improved MRI radiomics performance for predicting PAS and invasive PAS.
MATERIALS & METHODS: This retrospective study involved 245 patients who had placental MRI scans at three different institutions. Of these, 158 cases from Institution I for training set and internal validation set, while 34 patients from Institution II and 53 patients from Institution III served as external validation sets. SR using a generative adversarial network (GAN) was applied to generate SR T2WI (SRT2WI). Predictive models for PAS and invasive PAS were developed based on T2WI, SRT2WI, and the SRT2WI-Clinical model. Two radiologists independently diagnosed PAS using T2WI to serve as a reference for evaluating model performance. Model performance was assessed using the area under the curve (AUC), calibration curves, decision curve analysis (DCA), Delong test, and net reclassification improvement (NRI). SHAP values interpreted the models and quantified feature contributions.
RESULTS: Across all four cohorts, SRT2WI yielded numerically higher AUCs than T2WI, and SRT2WI-Clinical achieved the highest AUCs. For PAS, SRT2WI-Clinical achieved AUCs of 0.953, 0.887, 0.793, and 0.788 in the training, internal validation, and external validation cohorts 1 and 2, respectively (T2WI: 0.738, 0.697, 0.654, and 0.652; SRT2WI: 0.879, 0.820, 0.696, and 0.768). Corresponding AUCs for invasive PAS were 0.895, 0.875, 0.843, and 0.815 (T2WI: 0.774, 0.699, 0.575, and 0.745; SRT2WI: 0.861, 0.794, 0.729, and 0.808). For PAS, SRT2WI-Clinical significantly outperformed T2WI (P < 0.001) and SRT2WI (P = 0.004) only in training, with no significant validation differences. For invasive PAS, it significantly outperformed T2WI in training, internal validation, and external validation cohort 1 (P = 0.003, 0.021, and 0.019, respectively), but not external validation cohort 2 (P = 0.398); comparisons with SRT2WI were nonsignificant. Calibration showed good agreement, DCA favored SRT2WI-Clinical, and SHAP quantified feature contributions.
CONCLUSIONS: The combination of SR and radiomics shows promise for improving the prediction of PAS and invasive PAS. Integrating clinical features may further enhance model performance, supporting its potential clinical utility.
引用
- Yang CZ, Qin LH, Chen L, et al. Deep learning super-resolution enhances MRI radiomics for predicting placenta accreta spectrum and invasiveness. Eur J Radiol. 2026. PMID: 42887436. doi:10.1016/j.ejrad.2026.113268
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。