双能CT肺栓塞人工智能检测的评估
回顾性分析200例CT肺动脉造影(CTPA)检查,分为双能50 keV与70 keV虚拟单能(VMC)系列及单能CTPA组,每组肺栓塞阳性与阴性各半,使用Aidoc肺栓塞检测软件分析。AI在单能组敏感度84.6%、特异度100%,50 keV组敏感度84.3%、特异度100%,70 keV组敏感度87.5%、特异度100%,各组95%CI重叠,敏感度与特异度均无显著差异。结论认为AI肺栓塞检测软件可用于双能VMC CTPA检查。
要点
- AI肺栓塞检测软件在单能CTPA的敏感度为84.6%、特异度为100%。
- AI在双能50 keV VMC系列敏感度84.3%、特异度100%,70 keV系列敏感度87.5%、特异度100%。
- 各组敏感度与特异度的95%CI重叠,双能VMC与单能CTPA间无显著差异。
核心结论
- AI肺栓塞检测软件可用于双能VMC CTPA检查,与单能CTPA相比敏感度与特异度无显著差异。
研究设计与样本
- 回顾性研究分析200例CTPA检查,双能与单能检查各半且肺栓塞阳性与阴性等量分布,共四组,双能组含50 keV与70 keV VMC系列,由Aidoc肺栓塞检测软件分析,影像医师与AI不一致时由两名盲法放射科医师复核确定多数真值。
诊断标准与关键数值
- 单能CTPA肺栓塞阳性组:AI敏感度84.6%、特异度100%。
- 双能50 keV VMC肺栓塞阳性组:AI敏感度84.3%、特异度100%。
- 双能70 keV VMC肺栓塞阳性组:AI敏感度87.5%、特异度100%。
- 各组敏感度与特异度基于重叠的95%置信区间判断,无显著差异。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Dual-energy CT can be utilized on CT pulmonary angiography (CTPA) exams, increasing detection of peripheral PE. Artificial Intelligence (AI) software has emerging applications including the detection of PE; however, these AI models are not exclusively trained on dual-energy data. This study aims to evaluate the diagnostic performance of AI PE detection software on dual-energy virtual monochromatic (VMC) series compared to single-energy CTPA exams.
METHODS: A retrospective study analyzing 200 CTPA exams comprised of dual-energy and single-energy studies with an equal distribution of scans reported as positive and negative for PE creating four groups for analysis. Dual-energy studies consisted of 50 keV and 70 keV VMC series. Each case was analyzed by the Aidoc pulmonary embolism detection software. In cases with a discrepancy between the radiologist and the AI detection software, two blinded radiologists reviewed the scan to establish a majority truth. Sensitivity and specificity analyses was calculated for each of the four groups.
RESULTS: AI PE detection software had an 84.6 % sensitivity and a specificity of 100 % for single-energy PE exams. For the 50 keV dual-energy VMC PE cases the AI software had an 84.3 % sensitivity and a specificity of 100 %. For the 70 keV dual-energy VMC PE cases the AI software had an 87.5 % sensitivity and 100 % specificity. No significant difference was seen in sensitivity or specificity based on overlapping 95 % confidence intervals of groups.
CONCLUSIONS: AI PE detection software can be utilized on dual-energy VMC CTPA exams without a significant difference in sensitivity of specificity when compared to single-energy CTPA exams.
引用
- Schwertner A, McMenamy J, Kerchberger J, et al. Evaluation of artificial intelligence detection of pulmonary embolism in dual-energy computed tomography. Clin Radiol. 2025. PMID: 41270496. doi:10.1016/j.crad.2025.107142
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。