基于解剖形态的三维主动脉血流动力学:流体物理信息深度学习方法的可行性研究
该研究回顾性纳入1765例(二叶式主动脉瓣1242例、三叶式主动脉瓣523例)临床心胸MRI检查患者,以4D flow MRI为参考标准,评估流体物理信息循环生成对抗网络(FPI-CycleGAN)仅从主动脉三维分割解剖输入预测收缩期血流动力学的可行性与准确性。结果显示AI计算时间平均0.15秒,速度矢量场偏差<0.01 m/sec,峰值速度与壁面剪切应力一致性高(r²=0.930-0.957),主动脉瓣狭窄分级准确率85.8%(κ=0.80)。
要点
- FPI-CycleGAN仅需主动脉三维解剖分割即可在不足1秒内预测收缩期三维速度矢量场。
- 峰值速度与壁面剪切应力与4D flow MRI高度一致(r²=0.930-0.957,相对差异6.2%-9.8%)。
- 主动脉瓣狭窄严重程度分级准确率85.8%(302/352,κ=0.80)。
核心结论
- 利用FPI-CycleGAN可从解剖输入在不足1秒内导出主动脉三维血流动力学,并与体内4D flow MRI收缩期血流动力学呈现高度一致性。
研究设计与样本
- 回顾性研究,从2011年11月至2020年7月临床心胸MRI检查数据集中识别患者,共1765例(中位年龄53岁,IQR 41-63岁;二叶式主动脉瓣1242例、三叶式主动脉瓣523例),以主动脉4D flow MRI为参考标准;训练集二叶式主动脉瓣994例、三叶式主动脉瓣419例,测试集二叶式主动脉瓣248例、三叶式主动脉瓣104例;外部测试集以对比增强MR血管成像为AI输入(n=60例)。
诊断标准与关键数值
- 体素级与区域分析比较AI与4D flow的收缩期速度矢量场、峰值速度、壁面剪切应力及主动脉瓣狭窄分级;速度矢量场偏差<0.01 m/sec,一致性界限±0.06-0.08 m/sec;峰值速度与壁面剪切应力r²=0.930-0.957(P<.001),相对差异6.2%-9.8%;主动脉瓣狭窄严重程度分级准确率85.8%(302/352),κ=0.80(95%CI:0.71,0.89);输入数据一至两体素膨胀与腐蚀时偏差-0.05至0.1 m/sec,±5°旋转时偏差-0.02至0.03 m/sec;外部测试集峰值速度与壁面剪切应力r²=0.944-0.965(P<.001),相对差异6.2%-9.2%。
临床应用与阅片要点
- AI计算时间平均0.15秒±0.11(SD),三叶式主动脉瓣与二叶式主动脉瓣网络总训练时间分别为1500分钟和3600分钟;模型对输入数据一体素至两体素膨胀与腐蚀及±5°旋转具有稳健性。
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 Four-dimensional (4D) flow MRI provides assessment of thoracic aorta hemodynamic measures that are increasingly recognized as important biomarkers for risk assessment. However, long acquisition times and cumbersome data analysis limit widespread availability. Purpose To evaluate the feasibility and accuracy of a generative artificial intelligence (AI) approach (fluid physics-informed cycle generative adversarial network [FPI-CycleGAN]) in quantifying aorta hemodynamics directly from anatomic input as an alternative to 4D flow MRI. Materials and Methods Patients were retrospectively identified from a dataset of clinical cardiothoracic MRI examinations performed between November 2011 and July 2020. All patients underwent aortic 4D flow MRI, which served as a reference standard for training and testing of FPI-CycleGANs. A three-dimensional (3D) segmentation of the aortic geometry was used as the only input to predict systolic aortic hemodynamics, with separate networks for bicuspid aortic valve (BAV) (994 in the training set and 248 in the test set) and tricuspid aortic valve (TAV) (419 in the training set and 104 in the test set). Voxel-by-voxel and regional analyses were used to quantify and compare (AI vs the reference standard, 4D flow) systolic velocity vector fields, peak velocity, wall shear stress (WSS), and classification of aortic valve stenosis. Results In total, 1765 patients (median age, 53 years [IQR, 41-63 years]; 1242 patients had BAV and 523 had TAV) were included. Mean AI computation time was 0.15 second ± 0.11 (SD), and total training was 1500 and 3600 minutes for the TAV and BAV networks, respectively. The FPI-CycleGAN predicted systolic 3D velocity vector fields accurately, with low bias (<0.01 m/sec) and excellent limits of agreements (±0.06-0.08 m/sec). For peak velocities and WSS, there was strong agreement between FPI-CycleGAN and 4D flow (r2 = 0.930-0.957 [P < .001], with relative differences of 6.2%-9.8%). AI accurately classified aortic valve stenosis severity in 85.8% of patients (302 of 352) (κ = 0.80 [95% CI: 0.71, 0.89]). The FPI-CycleGAN was robust to one- and two-voxel dilation and erosion (bias, -0.05 to 0.1 m/sec) and ±5° rotation (bias, -0.02 to 0.03 m/sec) of the input data. The application of the trained FPI-CycleGAN in an external test set with contrast-enhanced MR angiography (n = 60 patients) as AI input data demonstrated strong to excellent performance for peak velocities and WSS (r2 = 0.944-0.965 [P < .001], with relative differences of 6.2%-9.2%). Conclusion Aorta 3D hemodynamics can be derived from anatomic input in less than 1 second using an FPI-CycleGAN and demonstrate strong agreement with in vivo 4D flow MRI systolic hemodynamics. © RSNA, 2025 Supplemental material is available for this article.
引用
- Berhane H, Maroun A, Dushfunian D, et al. Anatomy-derived 3D Aortic Hemodynamics Using Fluid Physics-informed Deep Learning. Radiology. 2025. PMID: 40326877. doi:10.1148/radiol.240714
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。