Vollbrecht Thomas M, Hart Christopher, Katemann Christoph, Isaak Alexander, Voigt Marilia B, Pieper Claus C, Kuetting Daniel, Geipel Annegret, Strizek Brigitte, Luetkens Julian A
Department of Diagnostic and Interventional Radiology (T.M.V., C.H., A.I., M.B.V., C.C.P., D.K., J.A.L.), University Hospital Bonn, Germany.
Quantitative Imaging Lab Bonn (QILaB) (T.M.V., C.H., A.I., D.K., J.A.L.), University Hospital Bonn, Germany.
Circ Cardiovasc Imaging. 2025 Aug;18(8):e018090. doi: 10.1161/CIRCIMAGING.125.018090. Epub 2025 Jun 26.
Fetal cardiovascular magnetic resonance is an emerging tool for prenatal congenital heart disease assessment, but long acquisition times and fetal movements limit its clinical use. This study evaluates the clinical utility of deep learning super-resolution reconstructions for rapidly acquired, low-resolution fetal cardiovascular magnetic resonance.
This prospective study included participants with fetal congenital heart disease undergoing fetal cardiovascular magnetic resonance in the third trimester of pregnancy, with axial cine images acquired at normal resolution and low resolution. Low-resolution cine data was subsequently reconstructed using a deep learning super-resolution framework (cine). Acquisition times, apparent signal-to-noise ratio, contrast-to-noise ratio, and edge rise distance were assessed. Volumetry and functional analysis were performed. Qualitative image scores were rated on a 5-point Likert scale. Cardiovascular structures and pathological findings visible in cine images only were assessed. Statistical analysis included the Student paired test and the Wilcoxon test.
A total of 42 participants were included (median gestational age, 35.9 weeks [interquartile range (IQR), 35.1-36.4]). Cine acquisition was faster than cine images acquired at normal resolution (134±9.6 s versus 252±8.8 s; <0.001). Quantitative image quality metrics and image quality scores for cine were higher or comparable with those of cine images acquired at normal-resolution (eg, fetal motion, 4.0 [IQR, 4.0-5.0] versus 4.0 [IQR, 3.0-4.0]; <0.001). Nonpatient-related artifacts (eg, backfolding) were more pronounced in cine compared with cine images acquired at normal-resolution images (4.0 [IQR, 4.0-5.0] versus 5.0 [IQR, 3.0-4.0]; <0.001). Volumetry and functional results were comparable. Cine revealed additional structures in 10 of 42 fetuses (24%) and additional pathologies in 5 of 42 fetuses (12%), including partial anomalous pulmonary venous connection.
Deep learning super-resolution reconstructions of low-resolution acquisitions shorten acquisition times and achieve diagnostic quality comparable with standard images, while being less sensitive to fetal bulk movements, leading to additional diagnostic findings. Therefore, deep learning super-resolution may improve the clinical utility of fetal cardiovascular magnetic resonance for accurate prenatal assessment of congenital heart disease.
胎儿心血管磁共振成像正逐渐成为一种用于产前先天性心脏病评估的工具，但采集时间长和胎儿运动限制了其临床应用。本研究评估深度学习超分辨率重建技术在快速采集的低分辨率胎儿心血管磁共振成像中的临床应用价值。
这项前瞻性研究纳入了在妊娠晚期接受胎儿心血管磁共振成像检查的胎儿先天性心脏病患者，采集了正常分辨率和低分辨率的轴位电影图像。随后使用深度学习超分辨率框架对低分辨率电影数据进行重建（电影）。评估采集时间、表观信噪比、对比噪声比和边缘上升距离。进行容积分析和功能分析。图像质量采用5分李克特量表进行定性评分。评估仅在电影图像中可见的心血管结构和病理表现。统计分析包括学生配对t检验和威尔科克森检验。
共纳入42名参与者（中位孕周，35.9周[四分位间距（IQR），35.1 - 36.4]）。电影采集比正常分辨率采集的电影图像更快（134±9.6秒对252±8.8秒；P<0.001）。电影的定量图像质量指标和图像质量评分高于或与正常分辨率采集的电影图像相当（例如，胎儿运动，4.0[IQR，4.0 - 5.0]对4.0[IQR，3.0 - 4.0]；P<0.001）。与正常分辨率图像采集的电影图像相比，电影中的非患者相关伪影（如回折）更明显（4.0[IQR，4.0 - 5.0]对5.0[IQR，3.0 - 4.0]；P<0.001）。容积分析和功能结果相当。电影在42例胎儿中的10例（24%）中显示出额外的结构，在42例胎儿中的5例（12%）中显示出额外的病变，包括部分肺静脉异位连接。
低分辨率采集的深度学习超分辨率重建可缩短采集时间，并达到与标准图像相当的诊断质量，同时对胎儿整体运动不太敏感，从而带来额外的诊断发现。因此，深度学习超分辨率技术可能会提高胎儿心血管磁共振成像在先天性心脏病准确产前评估中的临床应用价值。
