Machine Learning for Aiding Blood Flow Velocity Estimation Based on Angiography.
Machine Learning for Aiding Blood Flow Velocity Estimation Based on Angiography.
复制标题
DOI：
10.3390/bioengineering9110622
复制
发表时间：
2022-10-28
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）广泛用于预测动脉模型中的血流动力学特征，但由于数值模拟的复杂性，不利于临床应用。另外，这项工作提出了一个框架，使用机器学习（ML）算法根据血管造影图像估计血管中的血流动力学。首先，在经过实验验证的 CFD 模型中，通过扩散到水中的染料流来模拟血液中的碘对比灌注。模拟生成的投影图像模拟了穿过流场的光的对应物，类似于 X 射线成像。因此，CFD 模拟提供了地面真实速度场和染料流动模式的投影图像。使用基于 53 个投影图像的光流法 (OFM) 估计粗略速度场。以 CFD 速度数据作为基本事实，以 OFM 速度估计作为输入，进行最小绝对收缩、选择算子和卷积神经网络的 ML 训练。每个模型的性能根据平均绝对误差和均方误差进行评估，所有模型分别达到或超过了 3 × 10−3 和 5 × 10−7 m/s 的标准，标准偏差小于 1 × 10−6 m/s。最后，可解释的回归和机器学习模型通过超过 613 个图像集进行了验证。验证结果表明，与 CFD 相比，所采用的 ML 模型将 v 速度估计的平均错误率从 53.5% 显着降低至 2.5%。机器学习框架通过高效、准确地预测血流动力学信息，提供了支持临床诊断的替代途径。
Computational fluid dynamics (CFD) is widely employed to predict hemodynamic characteristics in arterial models, while not friendly to clinical applications due to the complexity of numerical simulations. Alternatively, this work proposed a framework to estimate hemodynamics in vessels based on angiography images using machine learning (ML) algorithms. First, the iodine contrast perfusion in blood was mimicked by a flow of dye diffusing into water in the experimentally validated CFD modeling. The generated projective images from simulations imitated the counterpart of light passing through the flow field as an analogy of X-ray imaging. Thus, the CFD simulation provides both the ground truth velocity field and projective images of dye flow patterns. The rough velocity field was estimated using the optical flow method (OFM) based on 53 projective images. ML training with least absolute shrinkage, selection operator and convolutional neural network was conducted with CFD velocity data as the ground truth and OFM velocity estimation as the input. The performance of each model was evaluated based on mean absolute error and mean squared error, where all models achieved or surpassed the criteria of 3 × 10−3 and 5 × 10−7 m/s, respectively, with a standard deviation less than 1 × 10−6 m/s. Finally, the interpretable regression and ML models were validated with over 613 image sets. The validation results showed that the employed ML model significantly reduced the error rate from 53.5% to 2.5% on average for the v-velocity estimation in comparison with CFD. The ML framework provided an alternative pathway to support clinical diagnosis by predicting hemodynamic information with high efficiency and accuracy.
登录
查看更多内容
影响因子：
19.5
作者：
Meijering, EHW;Zuiderveld, KJ;Viergever, MA
通讯作者：
Viergever, MA
影响因子：
3.5
作者：
Shi, Z.;Chen, G. Z.;Zhang, L. J.
通讯作者：
Zhang, L. J.
影响因子：
2.4
作者：
Chaichana, Thanapong;Sun, Zhonghua;Jewkes, James
通讯作者：
Jewkes, James
DOI：
10.1109/tpami.2019.2910523
发表时间：
2020-09-01
影响因子：
23.6
作者：
Lathuiliere, Stephane;Mesejo, Pablo;Horaud, Radu
通讯作者：
Horaud, Radu
DOI：
10.1016/j.colsurfa.2012.10.032
发表时间：
2014-01-20
影响因子：
5.2
作者：
Javadi, A.;Karbaschi, M.;Miller, R.
通讯作者：
Miller, R.