Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease
Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease
复制标题
DOI：
10.1016/j.ijcard.2021.03.020
复制
发表时间：
2021-05-04
影响因子：
3.5
通讯作者：
Honda, Yasuhiro
中科院分区：
文献类型：
--
作者：
Nishi, Takeshi;Yamashita, Rikiya;Honda, Yasuhiro
背景：血管内超声（IVUS）准确分割冠状动脉对优化冠状动脉支架植入术具有重要意义。近年来，人们提出了深度学习方法来实现IVUS的自动分割。然而，这些方法大多局限于分割管腔和血管（即管腔-内膜和中膜-外膜边界），而不适用于分割支架尺寸。因此，本研究旨在开发一种除管腔和血管区域外，还可用于支架区域自动IVUS分割的DL方法。方法：本研究共纳入1576例IVUS回拉的45,449张图像。数据集随机分为训练、验证和测试数据集（0.7:0.15:0.15）。在使用训练和验证数据集开发了基于dl的IVUS图像分割系统后，我们通过独立的测试数据集评估了性能。结果：基于dl的分割与专家分析的分割具有良好的相关性，管腔、血管和支架面积的平均相交度（+/-标准差）为0.80 +/- 0.20，相关系数为0.98（95%可信区间：0.98 ~ 0.98）、0.96（0.95 ~ 0.96）和0.96(0.96 ~ 0.96)，管腔、血管和支架面积的平均差（+/-标准差）分别为0.02 = 0.57、-0.44 +/- 1.56和- 0.17 +/- 0.74 mm(2)。结论：基于dl的管腔、血管和支架区域IVUS自动分割与专家手工分割的结果非常吻合，支持人工智能辅助IVUS评估冠状动脉支架植入术患者的可行性。(C) 2020年Elsevier B.V.出版
Background: Accurate segmentation of the coronary arteries with intravascular ultrasound (IVUS) is important to optimize coronary stent implantation. Recently, deep learning (DL) methods have been proposed to develop automatic IVUS segmentation. However, most of those have been limited to segmenting the lumen and vessel (i.e. lumen-intima and media-adventitia borders), not applied to segmenting stent dimension. Hence, this study aimed to develop a DL method for automatic IVUS segmentation of stent area in addition to lumen and vessel area.Methods: This study included a total of 45,449 images from 1576 IVUS pullback runs. The datasets were randomly split into training, validation, and test datasets (0.7:0.15:0.15). After developing the DL-based system to segment IVUS images using the training and validation datasets, we evaluated the performance through the independent test dataset.Results: The DL-based segmentation correlated well with the expert-analyzed segmentation with a mean intersection over union (+/- standard deviation) of 0.80 +/- 0.20, correlation coefficient of 0.98 (95% confidence intervals: 0.98 to 0.98), 0.96 (0.95 to 0.96), and 0.96 (0.96 to 0.96) for lumen, vessel, and stent area, and the mean difference (+/- standard deviation) of 0.02 = 0.57, -0.44 +/- 1.56 and - 0.17 +/- 0.74 mm(2) for lumen, vessel and stent area, respectively.Conclusion: This automated DL-based IVUS segmentation of lumen, vessel and stent area showed an excellent agreement with manual segmentation by experts, supporting the feasibility of artificial intelligence-assisted IVUS assessment in patients undergoing coronary stent implantation. (C) 2020 Published by Elsevier B.V.