文献速递脑血管病

深度学习软件在非增强CT上识别大血管闭塞

Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography.
PubMed 文献 · Stroke · 2020-08-26

本研究纳入1453例疑似急性卒中患者,以两名放射科医师的CTA判读为参考,验证深度学习算法MethinksLVO在非增强CT上识别大血管闭塞的效能。结果显示MethinksLVO的AUC为0.87,加入NIHSS评分和发病时间后AUC提升至0.91。软件可快速可靠预测大血管闭塞,有望减少CTA需求并提高卒中网络转诊效率。

要点

  • MethinksLVO在非增强CT上识别LVO的AUC为0.87,敏感性83%,特异性71%。
  • 加入NIHSS评分和发病时间后AUC提升至0.91,特异性升至85%。
  • 软件阳性预测值79%–88%,可辅助生成警报并优化转诊流程。

核心结论

  • 在疑似急性卒中患者中,MethinksLVO软件能快速可靠地在非增强CT上预测大血管闭塞。

研究设计与样本

  • 回顾性验证研究,纳入1453例同时接受非增强CT和CTA的疑似急性卒中患者。
  • 以两名经验丰富放射科医师的CTA判读作为参考标准,比较软件识别LVO的准确性。
  • 采用深度学习算法识别非增强CT上的血栓征象,并训练二分类器判断LVO。
  • 额外评估加入NIHSS评分和发病至扫描时间后模型(MethinksLVO+)的效能。

主要发现

  • 1453例中823例(57%)经参考CTA判读存在LVO。
  • MethinksLVO识别LVO的AUC为0.87,敏感性83%,特异性71%,阳性预测值79%,阴性预测值76%。
  • MethinksLVO+的AUC提升至0.91,敏感性83%,特异性85%,阳性预测值88%,阴性预测值79%。

临床怎么用

  • 可在疑似急性卒中患者非增强CT上快速筛查LVO,辅助识别血管内治疗候选者。
  • 软件结果可生成警报并优化卒中网络内患者转诊流程。
  • 有望减少对CTA的依赖,但需结合临床评分和时间信息综合判断。

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)。

原文

BACKGROUND AND PURPOSE: Reliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT. METHODS: Patients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included. Software detection of LVO (MethinksLVO) on NCCT was tested against the CTA readings of 2 experienced radiologists (NR-CTA). We used a deep learning algorithm to identify clot signs on NCCT. The software image output trained a binary classifier to determine LVO on NCCT. We studied software accuracy when adding National Institutes of Health Stroke Scale and time from onset to the model (MethinksLVO+). RESULTS: From 1453 patients, 823 (57%) had LVO by NR-CTA. The area under the curve for the identification of LVO with MethinksLVO was 0.87 (sensitivity: 83%, specificity: 71%, positive predictive value: 79%, negative predictive value: 76%) and improved to 0.91 with MethinksLVO+ (sensitivity: 83%, specificity: 85%, positive predictive value: 88%, negative predictive value: 79%). CONCLUSIONS: In patients with suspected acute stroke, MethinksLVO software can rapidly and reliably predict LVO. MethinksLVO could reduce the need to perform CTA, generate alarms, and increase the efficiency of patient transfers in stroke networks.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Olive-Gadea M, Crespo C, Granes C, et al. Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography. Stroke. 2020. PMID: 32842922. doi:10.1161/STROKEAHA.120.030326

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。