Deep Learning-Based Automated Detection of Arterial Vessel Wall and Plaque on Magnetic Resonance Vessel Wall Images.
Deep Learning-Based Automated Detection of Arterial Vessel Wall and Plaque on Magnetic Resonance Vessel Wall Images.
复制标题
基于深度学习的磁共振血管壁图像中动脉血管壁及斑块的自动检测
DOI：
10.3389/fnins.2022.888814
复制
发表时间：
2022
影响因子：
4.3
通讯作者：
Zhang, Na
中科院分区：
文献类型：
--
作者：
Xu, Wenjing;Yang, Xiong;Li, Yikang;Jiang, Guihua;Jia, Sen;Gong, Zhenhuan;Mao, Yufei;Zhang, Shuheng;Teng, Yanqun;Zhu, Jiayu;He, Qiang;Wan, Liwen;Liang, Dong;Li, Ye;Hu, Zhanli;Zheng, Hairong;Liu, Xin;Zhang, Na
目的：研究和评价一种动脉血管壁和斑块的自动分割方法，为磁共振血管壁成像（MRVWI）中的动脉形态定量提供帮助。包括124例动脉粥样硬化斑块患者的MRVWI图像。使用基于卷积神经网络的深度学习模型VWISegNet从MRVWI图像中提取特征，并计算每个像素的类别，以促进血管壁的分割。使用从115名患者的所有斑块和7个主要动脉段重建的二维（2D）横截面切片来构建和优化深度学习模型。使用骰子相似系数（DSC）和平均表面距离（ASD）在剩余的九名患者测试集中评估了模型性能。所提出的自动分割方法表现出令人满意的协议与手动方法，与DSC的93.8%的管腔轮廓和86.0%的外壁轮廓，这是高于从传统的U-Net，注意力U-Net，和Inception U-Net获得相同的九个主题的测试集。Bland-Altman图和散点图也显示了两种方法的良好一致性。自动法与手工法之间的组内相关系数均大于0.780，且均大于两次手工读数之间的相关系数。本文提出的基于深度学习的自动分割方法在动脉血管壁和斑块的分割上与人工方法取得了良好的一致性，甚至比人工结果更准确，从而提高了动脉形态量化的便利性。
To develop and evaluate an automatic segmentation method of arterial vessel walls and plaques, which is beneficial for facilitating the arterial morphological quantification in magnetic resonance vessel wall imaging (MRVWI). MRVWI images acquired from 124 patients with atherosclerotic plaques were included. A convolutional neural network-based deep learning model, namely VWISegNet, was used to extract the features from MRVWI images and calculate the category of each pixel to facilitate the segmentation of vessel wall. Two-dimensional (2D) cross-sectional slices reconstructed from all plaques and 7 main arterial segments of 115 patients were used to build and optimize the deep learning model. The model performance was evaluated on the remaining nine-patient test set using the Dice similarity coefficient (DSC) and average surface distance (ASD). The proposed automatic segmentation method demonstrated satisfactory agreement with the manual method, with DSCs of 93.8% for lumen contours and 86.0% for outer wall contours, which were higher than those obtained from the traditional U-Net, Attention U-Net, and Inception U-Net on the same nine-subject test set. And all the ASD values were less than 0.198 mm. The Bland–Altman plots and scatter plots also showed that there was a good agreement between the methods. All intraclass correlation coefficient values between the automatic method and manual method were greater than 0.780, and greater than that between two manual reads. The proposed deep learning-based automatic segmentation method achieved good consistency with the manual methods in the segmentation of arterial vessel wall and plaque and is even more accurate than manual results, hence improved the convenience of arterial morphological quantification.
登录
查看更多内容
影响因子：
4.7
作者：
Yamashita R;Nishio M;Do RKG;Togashi K
通讯作者：
Togashi K
影响因子：
3.3
作者：
Giavarina D
通讯作者：
Giavarina D
DOI：
10.1161/atvbaha.112.245415
发表时间：
2012-06-01
影响因子：
8.7
作者：
Burtea, Carmen;Ballet, Sebastien;Muller, Robert N.
通讯作者：
Muller, Robert N.
DOI：
10.11406/rinketsu.61.564
发表时间：
2020-01-01
期刊：
[Rinsho ketsueki] The Japanese journal of clinical hematology
影响因子：
--
作者：
Ohsaka, Akimichi
通讯作者：
Ohsaka, Akimichi
影响因子：
10.6
作者：
Eelbode, Tom;Bertels, Jeroen;Blaschko, Matthew B.
通讯作者：
Blaschko, Matthew B.