深度学习自动重建晚孕期胎儿动态二维心脏MRI
本研究基于23例晚孕期(34-36周)胎儿的2327幅实时心脏MR图像,训练nnU-Net模型自动选取感兴趣区并集成入电影重建流程。自动与手动ROI选择在Dice系数、ROI大小、平移参数及互信息上无显著差异,PIQE评分统计学更低但绝对差异小。结论认为深度学习自动ROI选择用于胎儿CMR重建可行。
要点
- nnU-Net自动选取ROI的Dice均值为0.83±0.23,81%评分超过0.8。
- 自动与手动电影重建的解剖保真度定性可比,自动法PIQE评分略低。
- 自动ROI选择可减少手工操作时间和观察者间变异。
核心结论
- 深度学习自动ROI选择用于胎儿心脏MR电影重建是可行的,可解决该技术临床转化的关键障碍。
研究设计与样本
- 研究类型为方法学开发与验证研究,样本为23例晚孕期(34-36周)妊娠的2327幅实时多层面堆叠图像。
- 23例胎儿中21例为健康胎儿,2例患有先天性心脏病;图像在方位、时间分辨率和信噪比方面存在差异。
- 使用nnU-Net模型进行ROI自动分割训练与测试,并与手动ROI选择进行比较。
关键影像表现/征象
- 自动与手动选择的ROI在大小上无显著差异(p=0.13),ROI质心未见显著偏移。
- 重建电影在沿x轴(p=0.58)和y轴(p=0.11)的平面内平移参数上无显著差异。
- 自动与手动电影在互信息值上无显著差异(p=0.59),解剖结构显示定性可比。
诊断标准与关键数值
- nnU-Net模型ROI分割的平均Dice相似系数为0.83±0.23。
- Dice评分超过0.8的比例为81%。
- 自动电影重建的PIQE评分显著低于手动电影(p<0.001),但绝对差异约0.5分,临床意义不确定。
临床应用与阅片要点
- 自动ROI选择可集成入运动校正与度量优化门控的电影重建流程,减少放射科医生手动勾画的资源消耗。
- 阅片时需注意自动与手动电影图像质量差异虽有统计学意义但绝对差值很小,临床解读影响有限。
- 该自动化流程有助于降低观察者间变异,适合临床常规胎儿心脏MR检查的推广应用。
局限性
- 样本量较小,仅23例胎儿,其中先天性心脏病仅2例。
- 图像来自单一晚孕期窗口(34-36周),对其他孕周的适用性未验证。
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
INTRODUCTION: Fetal cardiovascular magnetic resonance (CMR) suffers from motion corruption and cardiac gating challenges. Data-driven motion correction and gating remain dependent on manual region-of-interest (ROI) selection, limiting clinical utility through resource demands, processing time, and inter-observer variability. We developed an nnU-Net model to automatically select ROIs and integrated it into a cine reconstruction pipeline.
METHODS: 2327 real-time images acquired as multi-slice stacks from 23 late third-trimester pregnancies (34-36 weeks gestational age), comprising 21 healthy fetuses and 2 with congenital heart disease, were used to train and test the model. Images varied in orientation, temporal resolution, and signal-to-noise ratio. Manual and automatic ROI selections were compared using the Dice similarity coefficient, ROI sizes, and ROI centroids, and were separately input into a cine reconstruction pipeline with motion correction and metric-optimized gating. Cines were compared between methods using in-plane translational parameters, RR intervals, mutual information (MI), the blind Perception-derived Image Quality Evaluator (PIQE), and qualitative anatomical review.
RESULTS: The nnU-Net model achieved a mean Dice score of 0.83 ± 0.23 with 81% of scores exceeding 0.8. No significant differences were found between ROI sizes (p = 0.13), translational parameters (along x-dimension: p = 0.58 or y-dimension: p = 0.11), or MI values (p = 0.59). Automatic and manual cines showed broadly comparable image quality, with statistically lower PIQE scores for automatic cines (p < 0.001) but a small absolute difference (∼0.5 points) of uncertain clinical significance. Cines displayed qualitatively comparable anatomical fidelity.
CONCLUSIONS: Deep-learning-automated ROI selection for fetal CMR reconstruction is feasible and addresses a key barrier to clinical adoption of the modality.
引用
- Myers, Goolaub, Seed, et al. Automated reconstruction of dynamic 2D fetal cardiac MRI using deep learning in late third-trimester fetuses. Eur J Radiol. 2026. PMID: 42700702. doi:10.1016/j.ejrad.2026.113197
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。