OBJECTIVES:To evaluate the image quality and diagnostic accuracy of third-generation dual-source CT with high-pitch scanning for coronary computed tomography angiography (CCTA) in patients with atrial fibrillation (AF) who were unable to hold their breath. METHODS:A total of 144 patients with AF and inability to hold their breath were enrolled and assigned into 2 groups: the high-pitch scanning group (N=70) and the prospective ECG-triggered sequential scanning group (N=74). Image quality, radiation dose, and diagnostic performance were compared between the 2 groups. RESULTS:The subjective image quality in the high-pitch group was significantly superior to that in the sequential group ( P <0.001), and it was particularly noticeable in mid-distal coronary artery segments. Radiation dose was significantly lower in the high-pitch group (effective dose: 1.52±0.57 vs. 6.23±3.41 mSv, P <0.001). The diagnostic performance for detecting significant coronary artery stenosis (≥50%), as assessed by the area under the curve (AUC) and diagnostic accuracy, was significantly superior in the high-pitch group compared with the sequential group ( P <0.05). CONCLUSION:Third-generation dual-source CT with high-pitch scanning demonstrated superior image quality, significantly reduced radiation dose, and enhanced diagnostic performance in CCTA for patients with AF who were unable to perform breath-holding. Therefore, it can be recommended as the preferred noninvasive imaging technique for this patient population.

BACKGROUND:China is adopting and promoting the mini-midline catheter insertion technique, which requires professional training to ensure its application and patient safety. This study aims to explore the effectiveness of the Train-the-Trainer model in nurse training for Mini-Midline Catheter Insertion. METHODS:A medical center selected venous therapy specialist nurses for mini-midline catheter procedure training, after which these nurses became trainers and guided other nurses. The research utilized a mixed-methods design, incorporating puncture condition surveys and open-ended questions. Over the following six months, outcomes such as catheter insertion success rates were monitored, and nurses' interviews were analyzed using the Kawakita Jiro method. RESULTS:A total of 675 mini-midline catheters were inserted in the study, with a success rate of 97.54%. The success rate for first-attempt punctures was 86.51%, with 584 successful cases and no catheterization-related complications. After training, expert consultations for catheter issues decreased from 28.46 to 9.25%. Additionally, three key themes of the training were identified: (1) enhancing nurses' professional sense of achievement and job satisfaction through skill mastery; (2) familiar groups and environments are more conducive to improving training effectiveness; and (3) the multifaceted role opens up a brand new path for the professional development of nurses. CONCLUSION:The mini-midline catheter insertion training program based on the "train-the-trainer" model effectively ensures the standardization of nurses' techniques and the safety of punctures while also cultivating educators and thus deserves widespread promotion. CLINICAL TRIAL NUMBER:Not applicable.

BACKGROUND: Quantitative flow ratio derived from computed tomography angiography (CT-QFR) and invasive coronary angiography (Murray law–based quantitative flow ratio [μQFR]) are novel approaches enabling rapid computation of fractional flow reserve without the use of pressure guidewires and vasodilators. However, the feasibility and diagnostic performance of both CT-QFR and μQFR in evaluating complex coronary lesions remain unclear. METHODS: Between September 2014 and September 2021, 240 patients with 30% to 90% coronary diameter stenosis who underwent both coronary computed tomography angiography and invasive coronary angiography with fractional flow reserve within 60 days were retrospectively enrolled. The diagnostic performance of CT-QFR and μQFR in detecting functional ischemia among all lesions, especially complex coronary lesions, was analyzed using fractional flow reserve as the reference standard. RESULTS: CT-QFR and μQFR analyses were performed on 309 and 289 vessels, respectively. The diagnostic sensitivity, specificity, positive predictive value, negative predictive value, and accuracy for CT-QFR in all lesions at the per-vessel level were 91% (with a 95% CI of 84%–96%), 92% (95% CI, 88%–95%), 83% (95% CI, 75%–90%), 96% (95% CI, 93%–98%), and 92% (95% CI, 88%–95%), with values for μQFR of 90% (95% CI, 81%–95%), 97% (95% CI, 93%–99%), 92% (95% CI, 84%–97%), 96% (95% CI, 92%–98%), and 94% (95% CI, 91%–97%), respectively. Among bifurcation, tandem, and moderate-to-severe calcified lesions, the diagnostic values of CT-QFR and μQFR showed great correlation and agreement with those of invasive fractional flow reserve, achieving an area under the receiver operating characteristic curve exceeding 0.9 for each complex lesion at the vessel level. Furthermore, the accuracies of CT-QFR and μQFR in the gray zone were 85% and 84%, respectively. CONCLUSIONS: Angiography-derived quantitative flow ratio (CT-QFR and μQFR) demonstrated remarkable diagnostic performance in complex coronary lesions, indicating its pivotal role in the management of patients with coronary artery disease.

目的 探讨冠状动脉CT血管成像(CCTA)图像后处理及冠状动脉病变智能识别的人工智能(AI)系统对冠状动脉旁路移植(CABG)术后患者CCTA的图像后处理、桥血管识别及管腔通畅性判断能力.方法 收集因常规临床复查需求行 CCTA检查的患者临床数据.对比由CCTA-AI对CABG患者CCTA图像中桥血管进行重建及评估的结果与常规影像技师重建、影像诊断医师判读的人工结果,评价 CCTA-AI在临床实际工作中对 CABG患者 CCTA图像的处理能力及诊断准确性.结果 130 例患者共308 支桥血管中,89.6%的桥血管被CCTA-AI准确识别及评估.与经验丰富的诊断医师复核后的人工判断结果相比,CCTA-AI判断桥血管存在的敏感性 84.15%,特异性 100%,准确性 90.4%;CCTA-AI诊断重度狭窄或闭塞桥血管的敏感性 40.5%,特异性98.8%,准确性 90.7%.2 种方法一致性较高(Kappa=0.76).结论 CCTA-AI 能对 CABG患者 CCTA 进行较好的重建及图像判读,扩宽了其在CCTA智能领域的可执行范围.

ObjectiveUsing two three-dimensional U-Net architectures for myocardium structure extraction and a distance transformation algorithm specifically for the left circumflex artery, we have designed a fully automated algorithm for coronary artery labeling in coronary computed tomography angiography (CCTA) images.MethodsIn this retrospective analysis, a cohort of 157 patients who had undergone coronary computed tomography angiography (CCTA) was included. An automated coronary artery labeling algorithm was developed using a distance transformation approach to delineate the anatomical segments along the centerlines extracted from the CCTA images. A total of 16 segments were successfully identified and labeled. The algorithm's outcomes were recorded and reviewed by three experts, and the performance of segment detection and labeling was assessed. Additionally, the level of agreement in manually labeled segments between two experts was quantified.ResultsWhen comparing the labels generated by the experts with those produced by the algorithm, it was necessary to modify or eliminate 117 labels (5.4%) out of 2180 segments assigned by the algorithm. The overall accuracy for label presence was 96.2%, with an average overlap of 94.0% between the expert reference and algorithm-generated labels. Furthermore, the average agreement rate between the two experts stood at 95.0%.ConclusionsBased on the labels of the clinical experts, the proposed deep learning algorithm exhibits high accuracy for automatic labeling. Therefore, our proposed method exhibits promising results for the automatic labeling of the coronary arteries and will alleviate the burden on radiologists in the near future.

Background The interpretation of coronary computed tomography angiography (CCTA) stenosis may be difficult among radiologists of different experience levels. Artificial intelligence (AI) may improve the diagnostic performance. Purpose To investigate whether the diagnostic performance and time efficiency of radiologists with different levels of experience in interpreting CCTA images could be improved by using CCTA with AI assistance (CCTA-AI). Material and Methods This analysis included 200 patients with complete CCTA and invasive coronary angiography (ICA) data, using ICA results as the reference. Eighteen radiologists were divided into three levels based on experience (Levels I, II, and III), and the three levels were divided into groups without (Groups 1, 2, and 3) and with (Groups 4, 5, and 6) AI assistance, totaling six groups (to avoid reader recall bias). The average sensitivity, specificity, NPV, PPV, and AUC were reported for the six groups and CCTA-AI at the patient, vessel, and segment levels. The interpretation time in the groups with and without CCTA-AI was recorded. Results Compared to the corresponding group without CCTA-AI, the Level I group with CCTA-AI had improved sensitivity (75.0% vs. 83.0% on patient-based; P = 0.003). At Level III, the specificity was better with CCTA-AI. The median interpretation times for the groups with and without CCTA-AI were 413 and 615 s, respectively (P < 0.001). Conclusion CCTA-AI could assist with and improve the diagnostic performance of radiologists with different experience levels, with Level I radiologists exhibiting improved sensitivity and Level III radiologists exhibiting improved specificity. The use of CCTA-AI could shorten the training time for radiologists.

Abstract Background To investigate the influence of artificial intelligence (AI) based on deep learning on the diagnostic performance and consistency of inexperienced cardiovascular radiologists. Methods We enrolled 196 patents who had undergone both coronary computed tomography angiography (CCTA) and invasive coronary angiography (ICA) within 6 months. Four readers with less cardiovascular experience (Reader 1–Reader 4) and two cardiovascular radiologists (level II, Reader 5 and Reader 6) evaluated all images for ≥ 50% coronary artery stenosis, with ICA as the gold standard. Reader 3 and Reader 4 interpreted with AI system assistance, and the other four readers interpreted without the AI system. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy (area under the receiver operating characteristic curve (AUC)) of the six readers were calculated at the patient and vessel levels. Additionally, we evaluated the interobserver consistency between Reader 1 and Reader 2, Reader 3 and Reader 4, and Reader 5 and Reader 6. Results The AI system had 94% and 78% sensitivity at the patient and vessel levels, respectively, which were higher than that of Reader 5 and Reader 6. AI-assisted Reader 3 and Reader 4 had higher sensitivity (range + 7.2–+ 16.6% and + 5.9–+ 16.1%, respectively) and NPVs (range + 3.7–+ 13.4% and + 2.7–+ 4.2%, respectively) than Reader 1 and Reader 2 without AI. Good interobserver consistency was found between Reader 3 and Reader 4 in interpreting ≥ 50% stenosis (Kappa value = 0.75 and 0.80 at the patient and vessel levels, respectively). Only Reader 1 and Reader 2 showed poor interobserver consistency (Kappa value = 0.25 and 0.37). Reader 5 and Reader 6 showed moderate agreement (Kappa value = 0.55 and 0.61). Conclusions Our study showed that using AI could effectively increase the sensitivity of inexperienced readers and significantly improve the consistency of coronary stenosis diagnosis via CCTA. Trial registration Clinical trial registration number: ChiCTR1900021867. Name of registry: Diagnostic performance of artificial intelligence-assisted coronary computed tomography angiography for the assessment of coronary atherosclerotic stenosis.

Department of Radiology, Beijing Friendship Hospital of Capital Medical University, Beijing 100050, China; Shukun (Beijing) Technology Company Ltd., Beijing 100102, China; Statistics Section, Beijing Friendship Hospital of Capital Medical University, Beijing 100050, China; Department of Radiology, Beijing Anzhen Hospital of Capital Medical University, Beijing 100011, China; Department of Radiology, Beijing Chest Hospital of Capital Medical University, Beijing 100010, China; Department of Cardiology, Beijing Friendship Hospital of Capital Medical University, Beijing 100050, China.

目的:评价人工智能(AI)在冠状动脉CT血管造影(CCTA)对冠心病的诊断价值.方法:对2020年6月至12月,先后行CCTA和有创冠状动脉造影(ICA)的150例患者进行回顾性分析.100例患者的CCTA图像作为训练数据集,使用卷积神经网络(CNN)进行训练,识别斑块类型和冠状动脉狭窄程度.另外50例CAD患者作为测试数据集,以ICA图像为参考标准,采用ROC曲线分析方法,比较CCTA-AI与ICA和传统人工CCTA在评价冠状动脉狭窄和斑块特征方面的差异.结果:在鉴别不同程度冠状动脉狭窄时,CCTA-AI的诊断准确率优于传统人工方法(AUCAI=0.870,AUC传统CCTA=0.781,P＜0.001).在识别斑块类型方面,CCTA-AI的准确度与传统的人工方法相比表现中等(AUC=0.750,P＜0.001).结论:与传统的CCTA相比,CCTA-AI在识别≥50％狭窄和分析斑块类型方面是相对准确的.

[This corrects the article DOI: 10.3389/fcvm.2021.707508.].

The objectives of this study were to develop an automatic algorithm for labeling coronary arteries in coronary computed tomography angiography (CCTA) images and to examine the reliabilities of this method. In total, 157 patients who underwent CCTA scanning were retrospectively included. An automatic coronary artery labeling algorithm based on the distance transformation algorithm is proposed to identify the anatomical segments of the centerlines extracted from CCTA images. Sixteen segments were identified and labeled. The results obtained via the algorithm were recorded and reviewed by three experts. The performance of segment detection and labeling of each segment was evaluated, and the proportion of agreement between the two experts on the manually labeled segments was also calculated. Compared with the labels of the experts, 117 labels (5.37%) (2180 segments) from the algorithm needed to be changed or removed. The overall accuracy of label presence was 96.21%. The average overlap between the expert reference and algorithm labels was 94.03%. The average agreement between the two experts was 94.98%. An automatic labeling algorithm was proposed, and a preliminary evaluation showed a high accuracy of the algorithm labels with respect to the labels from the clinical experts. This method is promising for labeling coronary arteries automatically and alleviating the workload of radiologists in the near future. Clinical Relevance— The automatic labeling algorithm established with the distance to the LA and LV can help improve the segment detection and labeling accuracy for CT imaging. The proposed algorithm can accelerate the report generation process and provide bases for diagnosis.

OBJECTIVE:This study aimed at exploring the impact of patient-related, vessel-related, image quality-related and cardiovascular risk factors on coronary computed tomographic angiography (CCTA) interpretability using 256-detector row computed tomography (CT).METHODS:One hundred ten patients who underwent CCTA and Invasive Coronary Angiography (ICA) were consecutively, retrospectively enrolled from January 2018 to October 2018. Using ICA as the reference standard, ≥50% diameter stenosis was defined as the cut-off criterion to detect the diagnostic performance of CCTA. Diagnostic reproducibility was investigated by calculating the interrater reproducibility of CCTA. Multiple logistic regression models were performed to evaluate the impact of 14 objective factors.RESULTS:A total of 1019 segments were evaluated. The per-segment sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CCTA were 76.8%, 93.7%, 91.2%, 67.8%, and 95.9%, respectively. The per-segment diagnostic reproducibility was 0.44 for CCTA. Regarding accuracy, a negative association was found for stenosis severity, calcium load, and hyperlipidaemia. Regarding sensitivity, calcium load and diabetes mellitus (DM) were positively related. Regarding specificity, a negative correlation was observed between stenosis severity and calcium load. Regarding interrater reproducibility, stenosis severity and calcium load were negatively associated, whereas male sex and the signal-to-noise ratio (SNR) were positively related (all p<0.05).CONCLUSION:Per-segment 256-detector row CCTA performance was optimal in stenosis-free or occluded segments. Heavier calcium load was associated with poorer CCTA interpretability. On the one hand, our findings confirmed the rule-out value of CCTA; on the other hand, improvements in calcium subtractions and deep learning-based tools are suggested to improve CCTA diagnostic interpretability.

Background: We pioneered a Deep Learning-based Coronary computed tomography–angiography Automatic Reconstruction and Diagnosis System (D-CARDS) for optimizing the workflow of diagnosis in coronary artery disease. Its efficiency and performance in clinical settings were verified. Method: In the model establishment stage, D-CARDS was trained with coronary computed tomography–angiography (CCTA) imaging data from 10,410 patients divided into training, tuning, and external validation test sets in a ratio of 7:2:1. A total of 685 patients were included in the study of clinical validation. 350 CCTA cases were collected for comparison of time efficiency. Another 335 CCTA cases were selected to reveal the diagnostic performance of D-CARDS with paired invasive coronary angiography (ICA) as the reference standard. Stenosis of 50% was considered to be obstructive and 70% or more to be significantly obstructive. The diagnostic performance of D-CARDS was evaluated as the receiver operating characteristic curve (ROC) and the corresponding area under the curve (AUC) at patient, vascular and segmental bases compared to both unilateral expert and arbitrated expert results. Findings: The average time taken of CCTA procedure after scanning (post-processing and diagnostic reporting) by D-CARDS was decreased by 73.3% from an average of 16.1 min with the conventional approach to 4.3 min (p=0.000). A total of 335 patients with 1,222 vessels and 3,559 segments were included in the final comparison of diagnostic performance. D-CARDS showed greater sensitivity (89.3% and 72.4%) than arbitrated expert results(82.6% and 62.0%)for detecting stenosis at both the 50% and 70% thresholds on patient-base, whereas its specificities were lower on every bases. The AUC showed that its diagnostic performance was equivalent to that of either of a unilateral expert on patient-based analysis, although slightly inferior to the arbitrated expert results. Interpretation: D-CARDS greatly improves the efficiency of CCTA procedure. Its diagnostic performance in detecting coronary stenosis is closer to that of an attending radiologist on patient-based analysis. The system can be used to optimize CCTA workflow.Funding Statement: This study was funded by Beijing science and technology committee. (grant reference number, Z201100005620009).Declaration of Interests: The authors declare no competing interests. Ethics Approval Statement: The study was approved by the Institutional Review Board (IRB)/Ethics Committee. The work was conducted in a manner compliant with the Measures for the Ethical Review of Biomedical Research Involving Humans and was adherent to the tenets of the Declaration of Helsinki.