Classification of moving coronary calcified plaques based on motion artifacts using convolutional neural networks: a robotic simulating study on influential factors.
Classification of moving coronary calcified plaques based on motion artifacts using convolutional neural networks: a robotic simulating study on influential factors.
复制标题
基于卷积神经网络的运动伪影运动冠状动脉钙化斑块分类：影响因素的机器人仿真研究。
DOI：
10.1186/s12880-021-00680-7
复制
发表时间：
2021-10-19
影响因子：
2.7
通讯作者：
Xie X
中科院分区：
文献类型：
--
作者：
Dobrolińska M;van der Werf N;Greuter M;Jiang B;Slart R;Xie X
运动伪影影响冠状动脉钙化斑块的图像。该研究利用卷积神经网络（CNN）对运动冠状动脉钙化斑块的运动污染图像进行分类，并确定分类性能的影响因素。将含有四个不同密度的人工斑块的两个人工冠状动脉放置在拟人胸部体模中的机械臂上。每条动脉以0 ~ 60 mm/s的速度线性运动。使用四种最先进的CT系统进行CT检查。所有图像均采用滤波反投影和至少三级迭代重建。每次检查均在100%、80%和40%辐射剂量下进行。三种深度CNN架构用于训练分类模型。应用五重交叉验证程序来验证模型。对于使用Inception v3、ResNet 101和DenseNet 201 CNN架构的人工斑块，CNN分类的准确性分别为90.2 ± 3.1%、90.6 ± 3.5%和90.1 ± 3.2%。在多因素分析中，高密度和高流速与高分类准确性显著相关（均P < 0.001）。CT系统、辐射剂量和图像重建方法对3种CNN结构的分类准确率均无影响（P > 0.05）。CNN在将运动污染的图像分类到实际类别时达到了90%的高准确度，无论不同的供应商，速度，辐射剂量和重建算法如何，这表明使用CNN来校正钙分数的潜在价值。在线版本包含补充材料，可通过10.1186/s12880-021-00680-7获得。
Motion artifacts affect the images of coronary calcified plaques. This study utilized convolutional neural networks (CNNs) to classify the motion-contaminated images of moving coronary calcified plaques and to determine the influential factors for the classification performance. Two artificial coronary arteries containing four artificial plaques of different densities were placed on a robotic arm in an anthropomorphic thorax phantom. Each artery moved linearly at velocities ranging from 0 to 60 mm/s. CT examinations were performed with four state-of-the-art CT systems. All images were reconstructed with filtered back projection and at least three levels of iterative reconstruction. Each examination was performed at 100%, 80% and 40% radiation dose. Three deep CNN architectures were used for training the classification models. A five-fold cross-validation procedure was applied to validate the models. The accuracy of the CNN classification was 90.2 ± 3.1%, 90.6 ± 3.5%, and 90.1 ± 3.2% for the artificial plaques using Inception v3, ResNet101 and DenseNet201 CNN architectures, respectively. In the multivariate analysis, higher density and increasing velocity were significantly associated with higher classification accuracy (all P < 0.001). The classification accuracy in all three CNN architectures was not affected by CT system, radiation dose or image reconstruction method (all P > 0.05). The CNN achieved a high accuracy of 90% when classifying the motion-contaminated images into the actual category, regardless of different vendors, velocities, radiation doses, and reconstruction algorithms, which indicates the potential value of using a CNN to correct calcium scores. The online version contains supplementary material available at 10.1186/s12880-021-00680-7.
登录
查看更多内容
影响因子：
--
作者：
Berrington de González A;Mahesh M;Kim KP;Bhargavan M;Lewis R;Mettler F;Land C
通讯作者：
Land C
影响因子：
5.9
作者：
He, Yifeng;Guo, Jiapan;Xie, Xueqian
通讯作者：
Xie, Xueqian
影响因子：
5.9
作者：
Jiang, Beibei;Zhang, Yaping;Xie, Xueqian
通讯作者：
Xie, Xueqian
DOI：
10.1016/0735-1097(90)90282-t
发表时间：
1990-03-15
影响因子：
24
作者：
AGATSTON, AS;JANOWITZ, WR;DETRANO, R
通讯作者：
DETRANO, R
影响因子：
3
作者：
Blagus R;Lusa L
通讯作者：
Lusa L