Yang Yanying, Zhou Zhen, Zhang Nan, Wang Rui, Gao Yifeng, Ran Xiaowei, Sun Zhonghua, Zhang Heye, Yang Guang, Song Xiantao, Xu Lei
Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
Department of Radiology, Beijing Geriatric Hospital, Beijing, China.
Cardiovasc Diagn Ther. 2024 Aug 31;14(4):655-667. doi: 10.21037/cdt-23-407. Epub 2024 Jun 20.
Coronary chronic total occlusion (CTO) increases the risk of developing major adverse cardiovascular events (MACE) and cardiogenic shock. Coronary computed tomography angiography (CCTA) is a safe, noninvasive method to diagnose CTO lesions. With the development of artificial intelligence (AI), AI has been broadly applied in cardiovascular images, but AI-based detection of CTO lesions from CCTA images is difficult. We aim to evaluate the performance of AI in detecting the CTO lesions of coronary arteries based on CCTA images.
We retrospectively and consecutively enrolled patients with 50% stenosis, 50-99% stenosis, and CTO lesions who received CCTA scans between June 2021 and June 2022 in Beijing Anzhen Hospital. Four-fifths of them were randomly assigned to the training dataset, while the rest (1/5) were randomly assigned to the testing dataset. Performance of the AI-assisted CCTA (CCTA-AI) in detecting the CTO lesions was evaluated through sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic analysis. With invasive coronary angiography as the reference, the diagnostic performance of AI method and manual method was compared.
A total of 537 patients with 1,569 stenotic lesions (including 672 lesions with <50% stenosis, 493 lesions with 50-99% stenosis, and 404 CTO lesions) were enrolled in our study. CCTA-AI saved 75% of the time in post-processing and interpreting the CCTA images when compared to the manual method (116±15 472±45 seconds). In the testing dataset, the accuracy of CCTA-AI in detecting CTO lesions was 86.2% (79.0%, 90.3%), with the area under the curve of 0.874. No significant difference was found in detecting CTO lesions between AI and manual methods (P=0.53).
AI can automatically detect CTO lesions based on CCTA images, with high diagnostic accuracy and efficiency.
冠状动脉慢性完全闭塞（CTO）会增加发生主要不良心血管事件（MACE）和心源性休克的风险。冠状动脉计算机断层扫描血管造影（CCTA）是诊断CTO病变的一种安全、无创的方法。随着人工智能（AI）的发展，AI已广泛应用于心血管图像，但基于CCTA图像对CTO病变进行AI检测具有一定难度。我们旨在评估基于CCTA图像的AI检测冠状动脉CTO病变的性能。
我们回顾性连续纳入了2021年6月至2022年6月在北京安贞医院接受CCTA扫描的有50%狭窄、50-99%狭窄和CTO病变的患者。其中五分之四被随机分配到训练数据集，其余五分之一被随机分配到测试数据集。通过灵敏度、特异度、阳性预测值、阴性预测值、准确性和受试者工作特征分析来评估AI辅助CCTA（CCTA-AI）检测CTO病变的性能。以有创冠状动脉造影为参考，比较AI方法和手动方法的诊断性能。
我们的研究共纳入了537例有1569个狭窄病变的患者（包括672个狭窄<50%的病变、493个狭窄50-99%的病变和404个CTO病变）。与手动方法相比，CCTA-AI在CCTA图像后处理和解读中节省了75%的时间（116±15秒对472±45秒）。在测试数据集中，CCTA-AI检测CTO病变的准确性为86.2%（79.0%，90.3%），曲线下面积为0.874。AI和手动方法在检测CTO病变方面无显著差异（P=0.53）。
AI可基于CCTA图像自动检测CTO病变，具有较高的诊断准确性和效率。
