文献速递妇产影像腹部MR

放射组学、深度学习及融合模型预测产后出血的多中心比较分析

A Multicentre Comparative Analysis of Radiomics, Deep-learning, and Fusion Models for Predicting Postpartum Hemorrhage.
PubMed 文献 · Acad Radiol · 2025-06-24

这项回顾性研究连续纳入两家医院2018年5月至2024年6月间因疑似胎盘植入谱系疾病接受胎盘MRI评估的581例孕妇,基于矢状位T2加权MRI构建放射组学、2D/3D深度学习及融合模型预测产后出血。晚期融合模型DLRad_LF表现最佳,训练集和验证集AUC分别为0.955和0.898;验证集中3D深度学习模型AUC显著大于放射组学模型和2D深度学习模型。

要点

  • DLRad_LF模型基于矢状位T2加权MRI预测产后出血,验证集AUC为0.898(95%CI 0.848-0.949)。
  • 验证集中3D深度学习模型AUC显著大于放射组学模型(P<0.001)和2D深度学习模型(P<0.001)。
  • 亚组分析显示前置胎盘和胎盘植入谱系疾病未显著影响模型性能。

核心结论

  • DLRad_LF模型基于矢状位T2加权MRI图像可较为准确地预测产后出血。

研究设计与样本

  • 回顾性研究,连续纳入两家医院581例疑似胎盘植入谱系疾病孕妇,训练集为医院1的421例,验证集为医院2的160例;基于胎盘MRI矢状位T2加权图像提取放射组学特征并构建放射组学模型、2D和3D深度学习模型及早期与晚期融合模型,由两名经验丰富的放射科医师分析MRI图像。

诊断标准与关键数值

  • 晚期融合模型DLRad_LF在训练集AUC为0.955(95%CI 0.935-0.974),验证集AUC为0.898(95%CI 0.848-0.949);验证集中放射组学模型AUC为0.676,2D深度学习模型AUC为0.752,3D深度学习模型AUC显著大于放射组学模型(P<0.001)和2D深度学习模型(P<0.001)。

临床应用与阅片要点

  • 作者结论认为DLRad_LF模型基于矢状位T2加权MRI可较为准确地预测产后出血。
  • 亚组分析显示前置胎盘和胎盘植入谱系疾病未显著影响模型性能。

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

RATIONALE AND OBJECTIVE: This study compared the capabilities of two-dimensional (2D) and three-dimensional (3D) deep learning (DL), radiomics, and fusion models to predict postpartum hemorrhage (PPH), using sagittal T2-weighted MRI images.

MATERIALS AND METHODS: This retrospective study successively included 581 pregnant women suspected of placenta accreta spectrum (PAS) disorders who underwent placental MRI assessment between May 2018 and June 2024 in two hospitals. Clinical information was collected, and MRI images were analyzed by two experienced radiologists. The study cohort was divided into training (hospital 1, n=421) and validation (hospital 2, n=160) sets. Radiomics features were extracted after image segmentation to develop the radiomics model, 2D and 3D DL models were developed, and two fusion strategies (early and late fusion) were used to construct the fusion models. ROC curves, AUC, sensitivity, specificity, calibration curves, and decision curve analysis were used to evaluate the models' performance.

RESULTS: The late-fusion model (DLRad_LF) yielded the highest performance, with AUCs of 0.955 (95% CI: 0.935-0.974) and 0.898 (95% CI: 0.848-0.949) in the training and validation sets, respectively. In the validation set, the AUC of the 3D DL model was significantly larger than those of the radiomics (AUC=0.676, P<0.001) and 2D DL (AUC=0.752, P<0.001) models. Subgroup analysis found that placenta previa and PAS did not impact the models' performance significantly.

CONCLUSION: The DLRad_LF model could predict PPH reasonably accurately based on sagittal T2-weighted MRI images.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang W, Zhao X, Meng L, et al. A Multicentre Comparative Analysis of Radiomics, Deep-learning, and Fusion Models for Predicting Postpartum Hemorrhage. Acad Radiol. 2025. PMID: 40562675. doi:10.1016/j.acra.2025.05.068

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。