人工智能驱动的常模建模预测胎儿脑室扩大中的脑脊液干预需求
本研究为回顾性研究,纳入222例单胎妊娠,训练nnUNet在胎儿脑MRI上分割脑室,用138例正常胎儿建立18-36周脑室容积常模,并应用于64例脑室扩大胎儿(14例需产后干预)。以正常均值2个标准差为阈值识别脑室扩大,敏感度92%、特异度93%(AUC 0.97);以11个标准差为阈值预测产后干预需求,敏感度86%、特异度100%(AUC 0.97)。作者结论认为该方法可快速准确量化胎儿脑室容积,常模参考标准可预测脑室扩大及产后脑脊液干预需求,脑室容积增大是产后干预的强预测因子。
要点
- nnUNet自动分割胎儿脑室质量高,中位Dice评分0.96(四分位距0.93-0.99)。
- 识别脑室扩大的最佳阈值为正常均值2个标准差,敏感度92%、特异度93%(AUC 0.97;95%CI 0.91-0.98)。
- 预测产后干预需求的最佳阈值为正常均值11个标准差,敏感度86%、特异度100%(AUC 0.97;95%CI 0.86-1.00)。
核心结论
- 基于深度学习的胎儿脑MRI脑室容积量化方法可快速准确测量脑室容积,其建立的常模参考标准能预测脑室扩大及产后脑脊液干预需求,脑室容积增大是产后干预的强预测因子。
研究设计与样本
- 回顾性研究,纳入222例单胎妊娠;nnUNet在20例本院手工分割胎儿脑MRI联合80例公共数据集研究上训练,验证后应用于138例正常胎儿脑MRI建立18-36周常模,再应用于64例脑室扩大胎儿(其中14例需产后干预);计算ROC曲线及AUC。
关键影像表现/征象
- nnUNet在参考数据集上预测的胎儿脑室分割质量高且准确,中位Dice评分0.96(四分位距0.93-0.99)。
- 需产后干预者胎儿脑室容积(经颅内体积归一化后)更高、蛛网膜下腔容积更低(P < .001,P = .003)。
诊断标准与关键数值
- 识别脑室扩大的最佳阈值为正常均值2个标准差,敏感度92%、特异度93%(AUC 0.97;95%CI 0.91-0.98)。
- 预测产后干预需求的最佳阈值为正常均值11个标准差,敏感度86%、特异度100%(AUC 0.97;95%CI 0.86-1.00)。
临床应用与阅片要点
- 作者提出基于深度学习的胎儿脑MRI脑室容积量化方法,可快速准确测量脑室容积并用于预测脑室扩大及产后脑脊液干预需求。
- 作者认为脑室容积增大是产后干预的强预测因子。
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
BACKGROUND AND PURPOSE: Fetal ventriculomegaly (VM) is common and largely benign when isolated. However, it can occasionally progress to hydrocephalus, a more severe condition associated with increased mortality and neurodevelopmental delay that may require surgical postnatal intervention. Accurate differentiation between VM and hydrocephalus is essential but remains challenging, relying on subjective assessment and limited 2D measurements. Deep learning-based segmentation offers a promising solution for objective and reproducible volumetric analysis. This work presents an artificial intelligence-powered method for segmentation, volume quantification, and classification of the ventricles in fetal brain MRI to predict the need for postnatal intervention.
MATERIALS AND METHODS: This retrospective study included 222 patients with singleton pregnancies. An nnUNet was trained to segment the fetal ventricles on 20 manually segmented, institutional fetal brain MRIs combined with 80 studies from a publicly available data set. The validated model was then applied to 138 normal fetal brain MRIs to generate a normative reference range across a range of gestational ages (18-36 weeks). Finally, it was applied to 64 fetal brains with VM (14 of which required postnatal intervention). Receiver operating characteristic curves and area under curve (AUC) to predict VM and a need for postnatal intervention were calculated.
RESULTS: The nnUNet predicted segmentation of the fetal ventricles in the reference data set were of high quality and accurate (median Dice score: 0.96; interquartile range: 0.93-0.99). A normative reference range of ventricular volumes across gestational ages was developed by using automated segmentation volumes. The optimal threshold for identifying VM was 2 SD from normal with a sensitivity of 92% and a specificity of 93% (AUC 0.97; 95% CI: 0.91-0.98). When normalized to intracranial volume, fetal ventricular volume was higher and subarachnoid volume lower among those who required postnatal intervention (P < .001, P = .003). The optimal threshold for identifying the need for postnatal intervention was 11 SD from normal, with a sensitivity of 86% and a specificity of 100% (AUC: 0.97; 95% CI: 0.86-1.00).
CONCLUSIONS: This work introduces a deep learning-based method for fast and accurate quantification of ventricular volumes in fetal brain MRI. A normative reference standard derived by using this method can predict VM and a need for postnatal CSF intervention. Increased ventricular volume is a strong predictor of postnatal intervention.
引用
- Zhou M, Rajan SA, Nedelec P, et al. Prediction of CSF Intervention in Fetal Ventriculomegaly via Artificial Intelligence-Powered Normative Modeling. AJNR Am J Neuroradiol. 2026. PMID: 40957691. doi:10.3174/ajnr.A9000
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。