健康与病理案例的胎儿脑部MRI自动生物测量
Automated Fetal Brain MRI Biometry in Healthy and Pathological Cases
- Faculty of Medicine, University of Ljubljana（卢布尔雅那大学医学院）
- University Medical Centre Ljubljana（卢布尔雅那大学医学中心）
- Faculty of Electrical Engineering, University of Ljubljana（卢布尔雅那大学电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究构建了基于NeSVoR的胎儿脑部MRI自动生物测量流程，对比H3DE-Net与SCN模型，发现H3DE-Net定位精度更高、诊断效用更好，其脑室宽度阈值符合VM临床分级标准。
AI中文摘要：
胎儿脑部MRI的自动生物测量分析可实现可重复、独立于观察者的定量评估，但现有方法通常局限于少数测量指标，或仅在健康案例上进行评估。本研究构建并评估了一套自动生物测量分析流程，该流程可在NeSVoR重建的三维体积上定位22个解剖标志点，并衍生出11项临床相关测量指标，涵盖幕上、脑室、小脑及中线结构。我们在包含122次扫描的异质性队列（含健康对照及各类病理案例）上比较了两种标志点定位模型：H3DE-Net与SCN。采用线性混合效应模型评估定位精度，通过校准百分位图评估与正常生长轨迹的一致性，采用决策树对脑室扩张（VM）严重程度进行分类以评估诊断效用。结果显示，H3DE-Net在所有标志点上的定位误差均显著低于SCN：健康对照（HC）中平均误差为1.36 mm，SCN为3.58 mm；病理案例（PC）中平均误差为1.90 mm，SCN为4.13 mm，p值均小于0.001；且在11项测量指标中的7项上，其表现优于基于孕龄（GA）的回归基线。H3DE-Net的测量指标在所有诊断组中均产生更高的分类AUC，在区分健康对照与VM时优势最为明显；其生成的脑室宽度决策树阈值接近用于定义和分级VM的临床10 mm与15 mm临界值。
英文摘要：
Automated biometric analysis of fetal brain MRI enables reproducible, observer-independent quantitative assessment, yet existing methods are often restricted to few measurements or evaluated only on healthy cases. We assemble and evaluate an automated biometric analysis pipeline that localizes 22 anatomical landmarks on NeSVoR-reconstructed 3D volumes and derives 11 clinically relevant measurements spanning supratentorial, ventricular, cerebellar, and midline structures. We compare two landmark localization models, H3DE-Net and SCN, on a heterogeneous cohort of 122 acquisitions (both healthy controls and range pathologies). Localization accuracy was assessed with a linear mixed-effects model, agreement with normative growth trajectories with calibrated centile charts, and diagnostic utility with a decision tree classifying VM severity. H3DE-Net achieved significantly lower localization error than SCN across all landmarks (mean 1.36 mm vs. 3.58 mm in HC and 1.90 mm vs. 4.13 mm in PC; p < 0.001), and outperformed a GA-based regression baseline in 7 of 11 measurements. H3DE-Net measurements yielded higher classification AUC in every diagnostic group, with the clearest advantage in separating healthy controls from VM. Decision tree thresholds for ventricular width fell near the clinical 10 mm and 15 mm cut-offs used to define and grade VM.
