肺癌筛查中基于人工智能的冠状动脉钙化定量的协议一致性与工作流程效率：与半自动和视觉评估的比较

摘要(中文译文)

评估在肺癌筛查中，基于非心电门控低剂量CT的全自动人工智能（AI）冠状动脉钙化（CAC）定量与半自动（SA）评估及视觉评估的一致性及工作流程影响。在这项回顾性单中心研究中，纳入323名接受低剂量CT肺癌筛查的参与者（55.7%为男性；中位年龄61岁；52-79岁）。使用半自动和基于AI的Agatston评分对CAC进行定量。两名阅片者进行视觉分级。采用组内相关系数（ICC）、Spearman相关和Bland-Altman分析评估半自动与AI之间的一致性。使用加权Cohen's κ和诊断指标评估分类一致性（CAD-RADS 2.0斑块负荷）和CAC检出情况。比较CAC处理时间。基于AI与半自动的Agatston评分显示出极好的一致性（ICC 0.96）和强相关性（Spearman r = 0.97），偏倚较小（21.5），一致性界限中等。AI在排除CAC方面达到高诊断性能（敏感性0.97，95%CI 0.92-0.99；特异性0.91，95%CI 0.86-0.94）。AI与半自动之间的分类一致性几乎完美（κ 0.92），且高于半自动与视觉评估之间的一致性（κ 0.84和0.68）。半自动评分所需的处理时间显著长于视觉评估（102.0 ± 95.7秒 vs 15.5 ± 6.0秒和24.2 ± 7.4秒；< 0.001）。基于AI的CAC定量在非心电门控低剂量CT上与半自动评分相比显示出极好的一致性，分类一致性高于视觉评估，且无需手动评分。基于AI的方法可能有助于在肺癌筛查中实现标准化且可扩展的CAC报告，而不增加阅片时间。

Abstract

To evaluate agreement and workflow implications of fully automated AI-based coronary artery calcification (CAC) quantification on non-ECG-gated low-dose CT in lung cancer screening, compared with semi-automated (SA) and visual assessment. In this retrospective single-center study, 323 participants (55.7% male; median age 61 years; 52-79 years) undergoing low-dose CT for lung cancer screening were included. CAC was quantified using SA and AI-based Agatston scoring. Two readers performed visual grading. Agreement between SA and AI was assessed using intraclass correlation coefficient (ICC), Spearman correlation, and Bland-Altman analysis. Categorical agreement (CAD-RADS 2.0 plaque burden) and CAC detection were evaluated using weighted Cohen's κ and diagnostic metrics. CAC processing times for were compared. AI-based and semi-automated Agatston scores showed excellent agreement (ICC 0.96) and strong correlation (Spearman r = 0.97), with a small bias (21.5) and moderate limits of agreement. AI achieved high diagnostic performance for excluding CAC (sensitivity 0.97, 95%-CI, 0.92-0.99; specificity 0.91, 95%-CI, 0.86-0.94). Categorical agreement between AI and SA was almost perfect (κ 0.92) and higher than agreement between SA and visual assessment (κ 0.84 and 0.68). SA scoring required substantially longer processing time (102.0 ± 95.7 s) compared with visual assessment (15.5 ± 6.0 s and 24.2 ± 7.4 s; < 0.001). AI-based CAC quantification on non-ECG-gated low-dose CT demonstrates excellent agreement compared to semi-automated scoring, with higher categorical agreement than visual assessment and no requirement for manual scoring. AI-based approaches may facilitate standardized and scalable CAC reporting in lung cancer screening without additional reading time.

如何引用

European journal of radiology open 的其他文献

• 无心电图冠状动脉CT血管成像的图像质量评估：与传统心电图门控CCTA的比较研究
• 产褥期影像学
• 基于CT的造影放射组学用于预测非小细胞肺癌患者在接受抗PD-1靶向治疗后的3年疾病进展
• 从抵抗到依赖：以人为中心的放射科医生对人工智能信任谱分析
• 用于检测局部晚期癌症的病理完全反应的重启MRI的放射组学分析
• 使用Node-RADS对直肠癌症淋巴结进行MRI和CT的头对头比较：观察者一致性和诊断性能
• 冠状动脉CT血管造影中由体重和管电位确定的造影剂剂量提高了衰减一致性，减少了造影剂剂量