Brendel Jan M, Walterspiel Jonathan, Hagen Florian, Kübler Jens, Brendlin Andreas S, Afat Saif, Paul Jean-François, Küstner Thomas, Nikolaou Konstantin, Gawaz Meinrad, Greulich Simon, Krumm Patrick, Winkelmann Moritz T
Department of Radiology, Diagnostic and Interventional Radiology, University of Tübingen, 72076, Germany.
Institut Mutualiste Montsouris, Department of Radiology, Cardiac Imaging, 75014 Paris, France; Spimed-AI, 75014 Paris, France.
Diagn Interv Imaging. 2025 Feb;106(2):68-75. doi: 10.1016/j.diii.2024.09.012. Epub 2024 Oct 4.
The purpose of this study was to evaluate the diagnostic performance of automated deep learning in the detection of coronary artery disease (CAD) on photon-counting coronary CT angiography (PC-CCTA).
Consecutive patients with suspected CAD who underwent PC-CCTA between January 2022 and December 2023 were included in this retrospective, single-center study. Non-ultra-high resolution (UHR) PC-CCTA images were analyzed by artificial intelligence using two deep learning models (CorEx, Spimed-AI), and compared to human expert reader assessment using UHR PC-CCTA images. Diagnostic performance for global CAD assessment (at least one significant stenosis ≥ 50 %) was estimated at patient and vessel levels.
A total of 140 patients (96 men, 44 women) with a median age of 60 years (first quartile, 51; third quartile, 68) were evaluated. Significant CAD on UHR PC-CCTA was present in 36/140 patients (25.7 %). The sensitivity, specificity, accuracy, positive predictive value), and negative predictive value of deep learning-based CAD were 97.2 %, 81.7 %, 85.7 %, 64.8 %, and 98.9 %, respectively, at the patient level and 96.6 %, 86.7 %, 88.1 %, 53.8 %, and 99.4 %, respectively, at the vessel level. The area under the receiver operating characteristic curve was 0.90 (95 % CI: 0.83-0.94) at the patient level and 0.92 (95 % CI: 0.89-0.94) at the vessel level.
Automated deep learning shows remarkable performance for the diagnosis of significant CAD on non-UHR PC-CCTA images. AI pre-reading may be of supportive value to the human reader in daily clinical practice to target and validate coronary artery stenosis using UHR PC-CCTA.
本研究旨在评估自动深度学习在光子计数冠状动脉CT血管造影（PC-CCTA）上检测冠状动脉疾病（CAD）的诊断性能。
本回顾性单中心研究纳入了2022年1月至2023年12月期间接受PC-CCTA检查的疑似CAD连续患者。使用两种深度学习模型（CorEx、Spimed-AI）通过人工智能分析非超高分辨率（UHR）PC-CCTA图像，并与使用UHR PC-CCTA图像的人类专家读者评估进行比较。在患者和血管层面评估整体CAD评估（至少一处显著狭窄≥50%）的诊断性能。
共评估了140例患者（96例男性，44例女性），中位年龄为60岁（第一四分位数，51岁；第三四分位数，68岁）。140例患者中有36例（25.7%）在UHR PC-CCTA上存在显著CAD。基于深度学习的CAD在患者层面的敏感性、特异性、准确性、阳性预测值和阴性预测值分别为97.2%、81.7%、85.7%、64.8%和98.9%，在血管层面分别为96.6%、86.7%、88.1%、53.8%和99.4%。受试者操作特征曲线下面积在患者层面为0.90（95%CI：0.83-0.94），在血管层面为0.92（95%CI：0.89-0.94）。
自动深度学习在非UHR PC-CCTA图像上诊断显著CAD表现出卓越性能。在日常临床实践中，人工智能预读对于人类读者使用UHR PC-CCTA靶向和验证冠状动脉狭窄可能具有辅助价值。
