文献速递神经CT

人工智能驱动的非增强CT大血管闭塞检测:一项多机构研究

Artificial Intelligence-Driven Detection of Large Vessel Occlusions on NCCT: A Multi-Institutional Study.
PubMed 文献 · AJNR Am J Neuroradiol · 2025-12-04

这项多机构研究分析了3家美国综合卒中中心612例疑似急性缺血性卒中患者,评估深度学习算法Triage Stroke在非增强CT上识别前循环大血管闭塞的预测能力。软件敏感度67%、特异度93%、AUC 0.8,敏感度显著高于所有放射科医生组平均值(差值20.5%,CI 8.26-32.78,P=0.001),AUC也显著高于所有读者组(差值11%,CI 4%-17%,P<0.001)和非专家读者组(差值13%,CI 7%-20%,P<0.001)。结合NIHSS后特异度达99%、敏感度65%、阳性预测值91%。

要点

  • Triage Stroke在非增强CT上检测前循环大血管闭塞的敏感度67%、特异度93%、AUC 0.8。
  • 软件敏感度显著高于所有放射科医生组平均值,差值20.5%(CI 8.26-32.78,P=0.001)。
  • 结合NIHSS后特异度99%、敏感度65%、阳性预测值91%,为所有测试模型中最佳阳性预测值。

核心结论

  • Triage Stroke软件在非增强CT上检测前循环大血管闭塞表现出较强的预测能力,优于放射科医生;结合NIHSS可能简化血管内治疗候选者的识别,尤其在资源受限环境中。

研究设计与样本

  • 多机构研究,分析3家美国综合卒中中心612例疑似急性缺血性卒中患者,采用有和无前循环大血管闭塞的连续患者平衡队列,以站点神经放射科医生评估的同期CTA为参考标准。

诊断标准与关键数值

  • Triage Stroke在非增强CT上检测大血管闭塞的敏感度67%、特异度93%、阳性预测值59%、阴性预测值95%、AUC 0.8。
  • 软件敏感度与所有放射科医生组平均值的差值为20.5%(CI 8.26-32.78,P=0.001),分开为普通放射科医生和神经放射科医生亚组后也更高。
  • 非增强CT大血管闭塞的AUC显著高于所有读者组(差值11%,CI 4%-17%,P<0.001)和非专家读者组(差值13%,CI 7%-20%,P<0.001)。
  • 模型加入NIHSS后特异度99%、敏感度65%、阳性预测值91%,为所有测试模型中最佳阳性预测值。

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 AND PURPOSE: Imaging triage of stroke patients is primarily based on perfusion imaging. Simplified triage based on non-contrast CT are limited (NCCT). To evaluate the predictive capability of a deep learning algorithm, "Triage Stroke" (Brainomix 360) in identifying anterior circulation large vessel occlusions (LVO) on NCCT in patients with suspected acute ischemic stroke (AIS).

MATERIALS AND METHODS: This multi-institutional study analyzed 612 patients with suspected AIS at 3 US comprehensive stroke centers. A balanced cohort of consecutive patients with and without anterior circulation LVO was analyzed. Ground truth was based on concurrent CTA evaluated by site neuroradiologists. The primary outcome was predictive performance for LVO detection. The secondary outcomes were 1) prospective comparison of NCCT LVO detection against general radiologists and subspecialty neuroradiologists, and 2) the influence of NIHSS on the model.

RESULTS: Triage Stroke software detected an LVO on NCCT with a 67% sensitivity and 93% specificity. The positive and negative predictive values were 59% and 95%, respectively, with an area under the curve (AUC) of 0.8. The software's sensitivity for LVO detection was significantly higher than the group average of all radiologists (difference = 20.5%; CI, 8.26-32.78; P = .001) and was also higher when separated into general and neuroradiology subgroups. The AUC for NCCT LVO was significantly higher than the group of all readers (difference = 11%; CI, 4%-17%; P < .001), and the nonexpert readers (difference = 13%, CI, 7%-20%; P < .001). The addition of NIHSS to the model yielded a high specificity (99%) and similar sensitivity (65%), resulting in the optimum positive predictive value of all models tested (91%).

CONCLUSIONS: Triage Stroke software demonstrated strong predictive capabilities for NCCT detection of anterior circulation LVOs outperforming radiologists. Coupled with NIHSS it may simplify identification of endovascular candidates especially in resource-constrained environments worldwide.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Rai AT, Al Halak A, Abdalkader M, et al. Artificial Intelligence-Driven Detection of Large Vessel Occlusions on NCCT: A Multi-Institutional Study. AJNR Am J Neuroradiol. 2025. PMID: 41067911. doi:10.3174/ajnr.A8923

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。