Evaluation of the diagnostic value of artificial intelligence-based CT-FFR and FAI for coronary artery stenosis
- VernacularTitle:基于人工智能的CT-FFR与FAI对冠状动脉狭窄的诊断价值评估
- Author:
Weiqiang WU
1
;
Liangfei ZHU
1
;
Zhuonan DAI
1
;
Yuhuan LIN
1
;
Lili CAI
1
Author Information
1. Department of Radiology, Guangdong Province Traditional Chinese and Western Medicine Hospital, Foshan, 528000, Guangdong, P. R. China
- Publication Type:Journal Article
- Keywords:
Artificial intelligence;
cardiovascular diseases;
radiation dose;
computed tomography angiography;
CT-fractional flow reserve;
fat attenuation index;
coronary artery stenosis
- From:
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery
2026;33(10):1650-1656
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the diagnostic value of CT-fractional flow reserve (CT-FFR) and fat attenuation index (FAI) based on artificial intelligence-assisted diagnostic software in coronary artery stenosis. Methods A retrospective analysis was conducted on patients clinically suspected of coronary artery syndrome who underwent coronary computed tomography angiography at Guangdong Province Traditional Chinese and Western Medicine Hospital between June 2021 and May 2025. Patients were divided into two groups according to scanning protocols: group A underwent conventional retrospective electrocardiography-gated scanning, while group B used Flash_ChestPlin mode. Invasive coronary angiography data served as the gold standard for diagnosing vascular stenosis (stenosis rate<50% defined as negative group, ≥50% with clinical symptoms as positive group). Radiation dose was compared between the two scanning protocols. The diagnostic efficacy of CT-FFR, pericoronary FAI, and transluminal attenuation gradient (TAG) based on artificial intelligence system for coronary stenosis was analyzed, including sensitivity, specificity, and area under the curve (AUC). Results A total of 567 vessels from 189 patients were analyzed, including 105 males, 84 females with a mean age of (62.5±12.3) years and a mean body mass index of (24.21±3.5) kg/m2. There were 112 patients in the group A and 77 patients in the group B. The radiation dose in the group B was significantly lower than that in the group A [69.7 (58.1, 84.1) mGy·cm vs. 420.4 (338.6, 514.2) mGy·cm, P<0.001]. Significant differences in FAI and CT-FFR were observed between negative and positive groups under both scanning protocols (P<0.05), while no significant difference existed in TAG (P>0.05). In the group A, the AUC values for diagnosing stenosis were 0.925 for CT-FFR, 0.615 for FAI, and 0.516 for TAG. Corresponding values in the group B were 0.889, 0.677, and 0.548 respectively, with CT-FFR demonstrating optimal diagnostic performance. Conclusion Under both conventional scanning and Flash scanning, the artificial intelligence-based CT-FFR demonstrates good diagnostic performance for coronary artery stenosis, and the Flash protocol significantly lowers radiation dose, indicating substantial potential for clinical application.
