Automatic segmentation of the great arteries for computational hemodynamic assessment.
Automatic segmentation of the great arteries for computational hemodynamic assessment.
复制标题
DOI：
10.1186/s12968-022-00891-z
复制
发表时间：
2022-11-07
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
计算流体动力学（CFD）越来越多地用于评估先天性心脏病（CHD）患者的血流状况。这需要患者特定的解剖结构，通常从分割的3D心血管磁共振（CMR）图像中获得。然而，分割是耗时的，并且需要专家输入。本研究旨在开发和验证用于CFD研究的主动脉和肺动脉分割的机器学习（ML）方法。回顾性选择90例冠心病患者进行研究。手动分割3D CMR图像以获得地面实况（GT）背景、主动脉和肺动脉标签。这些用于训练和优化U-Net模型，使用70-10-10的训练-验证-测试分割。分割性能主要使用Dice评分进行评估。使用半自动网格化和模拟管道，从GT和ML分割中建立CFD模拟。提取沿着血管中心线的99个平面上的平均压力和速度场，并计算每个血管对（ML vs GT）的平均平均百分比误差（MAPE）。第二个观察者（SO）对测试数据集进行分段，以评估观察者间的变异性。Friedman检验用于比较ML与GT、SO与GT和ML与SO度量以及压力/速度场误差。主动脉和肺动脉的网络Dice评分（ML vs GT）分别为0.945（四分位距：0.929-0.955）和0.885（0.851-0.899）。对于主动脉或肺动脉，观察者间Dice评分（SO vs GT）和ML vs SO Dice评分的差异无统计学显著性（p = 0.741，p = 0.061）。主动脉压力和流速的ML与GT MAPE分别为10.1%（8.5-15.7%）和4.1%（3.1-6.9%），肺动脉分别为14.6%（11.5-23.2%）和6.3%（4.3-7.9%）。观察者间（SO vs GT）和ML vs SO压力和速度MAPE的幅度与ML vs GT相似（p > 0.2）。ML可以成功地分割大血管CFD，误差类似于观察者之间的变化。这种快速、自动的方法减少了CFD分析所需的时间和精力，使其对常规临床应用更具吸引力。在线版本包含补充材料，可通过10.1186/s12968-022-00891-z获得。
Computational fluid dynamics (CFD) is increasingly used for the assessment of blood flow conditions in patients with congenital heart disease (CHD). This requires patient-specific anatomy, typically obtained from segmented 3D cardiovascular magnetic resonance (CMR) images. However, segmentation is time-consuming and requires expert input. This study aims to develop and validate a machine learning (ML) method for segmentation of the aorta and pulmonary arteries for CFD studies. 90 CHD patients were retrospectively selected for this study. 3D CMR images were manually segmented to obtain ground-truth (GT) background, aorta and pulmonary artery labels. These were used to train and optimize a U-Net model, using a 70-10-10 train-validation-test split. Segmentation performance was primarily evaluated using Dice score. CFD simulations were set up from GT and ML segmentations using a semi-automatic meshing and simulation pipeline. Mean pressure and velocity fields across 99 planes along the vessel centrelines were extracted, and a mean average percentage error (MAPE) was calculated for each vessel pair (ML vs GT). A second observer (SO) segmented the test dataset for assessment of inter-observer variability. Friedman tests were used to compare ML vs GT, SO vs GT and ML vs SO metrics, and pressure/velocity field errors. The network’s Dice score (ML vs GT) was 0.945 (interquartile range: 0.929–0.955) for the aorta and 0.885 (0.851–0.899) for the pulmonary arteries. Differences with the inter-observer Dice score (SO vs GT) and ML vs SO Dice scores were not statistically significant for either aorta or pulmonary arteries (p = 0.741, p = 0.061). The ML vs GT MAPEs for pressure and velocity in the aorta were 10.1% (8.5–15.7%) and 4.1% (3.1–6.9%), respectively, and for the pulmonary arteries 14.6% (11.5–23.2%) and 6.3% (4.3–7.9%), respectively. Inter-observer (SO vs GT) and ML vs SO pressure and velocity MAPEs were of a similar magnitude to ML vs GT (p > 0.2). ML can successfully segment the great vessels for CFD, with errors similar to inter-observer variability. This fast, automatic method reduces the time and effort needed for CFD analysis, making it more attractive for routine clinical use. The online version contains supplementary material available at 10.1186/s12968-022-00891-z.
登录
查看更多内容
影响因子：
6.4
作者：
Steeden, Jennifer A.;Quail, Michael;Muthurangu, Vivek
通讯作者：
Muthurangu, Vivek
影响因子：
10.9
作者：
Zhuang, Xiahai;Li, Lei;Yang, Guang
通讯作者：
Yang, Guang
影响因子：
37.8
作者：
GABE, IT;GAULT, JH;BRAUNWAL.E
通讯作者：
BRAUNWAL.E
DOI：
10.1136/heartjnl-2016-310423
发表时间：
2017-01-15
期刊：
Heart (British Cardiac Society)
影响因子：
--
作者：
Biglino G;Capelli C;Bruse J;Bosi GM;Taylor AM;Schievano S
通讯作者：
Schievano S
DOI：
10.1098/rsif.2017.0632
发表时间：
2017-11
期刊：
Journal of the Royal Society, Interface
影响因子：
--
作者：
Bonfanti M;Balabani S;Greenwood JP;Puppala S;Homer-Vanniasinkam S;Díaz-Zuccarini V
通讯作者：
Díaz-Zuccarini V