Automatic segmentation of the coronary artery using coronary computed tomography angiography (CCTA) images can facilitate several analyses related to coronary artery disease (CAD). Accurate segmentation of the lumen or plaque region is one of the most important factors. This study aimed to analyze the performance of the coronary artery segmentation of a software platform with a deep learning-based location-adaptive threshold method (DL-LATM) against commercially available software platforms using CCTA. The dataset from intravascular ultrasound (IVUS) of 26 vessel segments from 19 patients was used as the gold standard to evaluate the performance of each software platform. Statistical analyses (Pearson correlation coefficient [PCC], intraclass correlation coefficient [ICC], and Bland-Altman plot) were conducted for the lumen or plaque parameters by comparing the dataset of each software platform with IVUS. The software platform with DL-LATM showed the bias closest to zero for detecting lumen volume (mean difference = -9.1 mm³, 95% confidence interval [CI] = -18.6 to 0.4 mm³) or area (mean difference = -0.72 mm², 95% CI = -0.80 to -0.64 mm²) with the highest PCC and ICC. Moreover, lumen or plaque area in the stenotic region was analyzed. The software platform with DL-LATM showed the bias closest to zero for detecting lumen (mean difference = -0.07 mm², 95% CI = -0.16 to 0.02 mm²) or plaque area (mean difference = 1.70 mm², 95% CI = 1.37 to 2.03 mm²) in the stenotic region with significantly higher correlation coefficient than other commercially available software platforms (p < 0.001). The result shows that the software platform with DL-LATM has the potential to serve as an aiding system for CAD evaluation.

使用冠状动脉计算机断层扫描血管造影 (CCTA) 图像自动分割冠状动脉可以促进与冠状动脉疾病 (CAD) 相关的多项分析。管腔或斑块区域的准确分割是最重要的因素之一。本研究旨在分析采用基于深度学习的位置自适应阈值方法 (DL-LATM) 的软件平台与使用 CCTA 的商用软件平台的冠状动脉分割性能。来自 19 名患者 26 个血管段的血管内超声 (IVUS) 数据集被用作评估每个软件平台性能的金标准。通过将各软件平台的数据集与IVUS进行比较，对管腔或斑块参数进行统计分析（Pearson相关系数[PCC]、组内相关系数[ICC]和Bland-Altman图）。具有 DL-LATM 的软件平台显示检测管腔体积（平均差 = -9.1 mm ³，95% 置信区间 [CI] = -18.6 至 0.4 mm ³）或面积（平均差 = -0.72 mm ）的偏差最接近于零如图²所示，95% CI = -0.80 至 -0.64 mm ² )，PCC 和 ICC 最高。此外，还分析了狭窄区域的管腔或斑块面积。 DL-LATM 软件平台显示检测管腔（平均差 = -0.07 mm ²，95% CI = -0.16 至 0.02 mm 2 ）或斑块面积（平均差 = 1.70 mm ² ，95 % CI = -0.16 至 0.02 mm ² ）的偏差最接近于零= 1.37 至 2.03 mm ²）在狭窄区域，相关系数显着高于其他商用软件平台（p  < 0.001）。结果表明，带有 DL-LATM 的软件平台具有作为 CAD 评估辅助系统的潜力。