深度学习自动背景相位误差校正用于腹盆部四维血流MRI
本研究回顾性收集139例腹盆部四维血流MRI采集,以手动图像相位误差校正为参考标准,训练多通道三维U-Net卷积神经网络实现自动校正。自动校正与手动校正高度相关(ρ=0.98),两者均降低流入-流出方差且无显著差异(P=.10),自动校正效果与手动校正相当。
要点
- 自动校正与手动校正流量测量高度相关(ρ=0.98,P<.001)。
- 自动与手动校正的流入-流出方差无显著差异(P=.10)。
- 校正后流入-流出相关由ρ=0.50提升至手动ρ=0.94、自动ρ=0.91。
核心结论
- 深度学习自动相位误差校正降低了四维血流MRI体积流量测量的流入-流出偏差和方差,效果与手动图像相位误差校正相当。
研究设计与样本
- 回顾性收集2016年1月至2020年7月间139例腹盆部四维血流MRI采集的便利样本。
- 手动相位误差校正使用专用成像软件完成,并作为参考标准。
- 保留40例用于测试,其余99例随机分为训练集(86%,85/99)和验证集(14%,14/99),训练多通道三维U-Net卷积神经网络。
- 流量测量部位为肾下主动脉、髂总动脉、髂总静脉和下腔静脉。
- 统计分析包括Pearson相关、Bland-Altman分析和采用Bonferroni校正的F检验。
诊断标准与关键数值
- 流入-流出相关:未校正ρ=0.50(P<.001),手动校正ρ=0.94(P<.001),自动校正ρ=0.91(P<.001)。
- 自动校正与手动校正流量测量相关ρ=0.98(P<.001)。
- 流入-流出平均差值:未校正-0.14 L/min(95%一致性界限:-1.61,1.32),手动校正0.05 L/min(95%一致性界限:-0.32,0.42),自动校正0.05 L/min(95%一致性界限:-0.38,0.49)。
- 手动与自动校正的流入-流出方差差异无统计学意义(P=.10)。
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 has the potential to provide hemodynamic insights for a variety of abdominopelvic vascular diseases, but its clinical utility is currently impaired by background phase error, which can be challenging to correct. Purpose To assess the feasibility of using deep learning to automatically perform image-based background phase error correction in 4D flow MRI and to compare its effectiveness relative to manual image-based correction. Materials and Methods A convenience sample of 139 abdominopelvic 4D flow MRI acquisitions performed between January 2016 and July 2020 was retrospectively collected. Manual phase error correction was performed using dedicated imaging software and served as the reference standard. After reserving 40 examinations for testing, the remaining examinations were randomly divided into training (86% [85 of 99]) and validation (14% [14 of 99]) data sets to train a multichannel three-dimensional U-Net convolutional neural network. Flow measurements were obtained for the infrarenal aorta, common iliac arteries, common iliac veins, and inferior vena cava. Statistical analyses included Pearson correlation, Bland-Altman analysis, and F tests with Bonferroni correction. Results A total of 139 patients (mean age, 47 years ± 14 [standard deviation]; 108 women) were included. Inflow-outflow correlation improved after manual correction (ρ = 0.94, P < .001) compared with that before correction (ρ = 0.50, P < .001). Automated correction showed similar results (ρ = 0.91, P < .001) and demonstrated very strong correlation with manual correction (ρ = 0.98, P < .001). Both correction methods reduced inflow-outflow variance, improving mean difference from -0.14 L/min (95% limits of agreement: -1.61, 1.32) (uncorrected) to 0.05 L/min (95% limits of agreement: -0.32, 0.42) (manually corrected) and 0.05 L/min (95% limits of agreement: -0.38, 0.49) (automatically corrected). There was no significant difference in inflow-outflow variance between manual and automated correction methods (P = .10). Conclusion Deep learning automated phase error correction reduced inflow-outflow bias and variance of volumetric flow measurements in four-dimensional flow MRI, achieving results comparable with manual image-based phase error correction. © RSNA, 2021 See also the editorial by Roldán-Alzate and Grist in this issue.
引用
- You, Masutani, Alley, et al. Deep Learning Automated Background Phase Error Correction for Abdominopelvic 4D Flow MRI. Radiology. 2021. PMID: 34846200. doi:10.1148/radiol.2021211270
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。