利用 UTE 质子 MRI 通过多层面一致性标记的深度卷积神经网络进行肺功能定量
Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI.
机构信息
Department of Medical Physics, University of Wisconsin-Madison, Madison, Wisconsin, USA.
Department of Radiology, University of Wisconsin-Madison, Madison, Wisconsin, USA.
出版信息
J Magn Reson Imaging. 2019 Oct;50(4):1169-1181. doi: 10.1002/jmri.26734. Epub 2019 Apr 4.
BACKGROUND
Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor-intensive lung segmentation.
PURPOSE
To evaluate a deep learning (DL) approach for automated lung segmentation to extract image-based biomarkers from functional lung imaging using 3D radial UTE oxygen-enhanced (OE) MRI.
STUDY TYPE
Retrospective study aimed to evaluate a technical development.
POPULATION
Forty-five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.
FIELD STRENGTH/SEQUENCE: 1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.
ASSESSMENT
Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O ) and hyperoxic (100% O ) conditions. Automated segmentation of the lungs using 2D convolutional encoder-decoder based DL method, and the subsequent functional quantification via adaptive K-means were compared with the results obtained from the reference method, supervised region growing.
STATISTICAL TESTS
Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two-sided Wilcoxon signed-rank test for computation time, and Bland-Altman analysis on the functional measure derived from the OE images.
RESULTS
The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland-Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs.
DATA CONCLUSION
DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.
LEVEL OF EVIDENCE
2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1169-1181.
背景
超短回波时间（UTE）质子 MRI 已在肺部成像中广泛用于评估肺结构和功能；然而，由于肺分割工作繁琐，快速生物标志物提取和区域定量的发展一直滞后。
目的
评估一种深度学习（DL）方法，用于从功能肺部成像的 3D 径向 UTE 氧增强（OE）MRI 中自动分割肺部以提取基于图像的生物标志物。
研究类型
旨在评估技术发展的回顾性研究。
人群
45 名人类受试者，包括 16 名健康志愿者、5 名哮喘患者和 24 名囊性纤维化患者。
磁场强度/序列：1.5T MRI，3D 径向 UTE（TE = 0.08 毫秒）序列。
评估
在正常氧（21%O ）和高氧（100%O ）条件下连续采集两个 3D 径向 UTE 容积。使用基于二维卷积编码器-解码器的 DL 方法自动分割肺部，并通过自适应 K-均值对随后的功能进行量化，与参考方法（监督区域生长）的结果进行比较。
统计检验
与参考方法相比，使用 95%置信区间（CI）的 Dice 系数评估 DL 在体积量化方面的性能，以双侧 Wilcoxon 符号秩检验评估计算时间，并对 OE 图像衍生的功能测量值进行 Bland-Altman 分析。
结果
DL 方法与监督区域生长法对右（Dice：0.97；95%CI=[0.96,0.97]；P<0.001）和左（Dice：0.96；95%CI=[0.96,0.97]；P<0.001）肺均产生了强烈的一致性。DL 方法平均需要 46 秒即可生成自动分割，而参考方法则需要 1.93 小时（P<0.001）。Bland-Altman 分析显示，左、右肺的容积（P≥0.12）和功能测量（P≥0.34）的方法间差异无统计学意义。
数据结论
DL 为使用 UTE 质子 MRI 对区域性肺功能进行定量分析提供了快速、自动和强大的肺分割。
证据水平
2 技术功效：阶段 1 J. Magn. Reson. Imaging 2019；50：1169-1181.
Zotero 插件