Department of Neurology & Neurological Sciences, Stanford University, Stanford, California, USA.
Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Maryland, USA.
J Neurointerv Surg. 2020 Feb;12(2):156-164. doi: 10.1136/neurintsurg-2019-015135. Epub 2019 Oct 8.
Acute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes. This report is a systematic review of AI in acute LVO stroke identification and triage, and characterizes LVO detection software.
A systematic review of acute stroke diagnostic-focused AI studies from January 2014 to February 2019 in PubMed, Medline, and Embase using terms: 'artificial intelligence' or 'machine learning or deep learning' and 'ischemic stroke' or 'large vessel occlusion' was performed.
Variations of AI, including ML methods of random forest learning (RFL) and convolutional neural networks (CNNs), are used to detect LVO strokes. Twenty studies were identified that use ML. Alberta Stroke Program Early CT Score (ASPECTS) commonly used RFL, while LVO detection typically used CNNs. Image feature detection had greater sensitivity with CNN than with RFL, 85% versus 68%. However, AI algorithm performance metrics use different standards, precluding ideal objective comparison. Four current software platforms incorporate ML: Brainomix (greatest validation of AI for ASPECTS, uses CNNs to automatically detect LVOs), General Electric, iSchemaView (largest number of perfusion study validations for thrombectomy), and Viz.ai (uses CNNs to automatically detect LVOs, then automatically activates emergency stroke treatment systems).
AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.
由大血管闭塞（LVOs）引起的急性中风需要通过血管内血栓切除术进行紧急检测和治疗。然而，放射学 LVO 检测和治疗受到可变延迟和人为专业知识的影响，导致发病率增加。使用人工智能（AI）和机器学习（ML）的成像软件，AI 的一个分支，可能会改善 LVO 中风的快速一线检测。本报告是对 AI 在急性 LVO 中风识别和分诊中的应用进行的系统评价，并对 LVO 检测软件进行了特征描述。
在 PubMed、Medline 和 Embase 中使用“人工智能”或“机器学习或深度学习”和“缺血性中风”或“大血管闭塞”等术语，对 2014 年 1 月至 2019 年 2 月期间的急性中风诊断 AI 研究进行了系统评价。
包括随机森林学习（RFL）和卷积神经网络（CNN）在内的各种 AI 方法被用于检测 LVO 中风。确定了 20 项使用 ML 的研究。阿尔伯塔中风计划早期 CT 评分（ASPECTS）通常使用 RFL，而 LVO 检测通常使用 CNN。与 RFL 相比，CNN 对图像特征检测具有更高的敏感性，分别为 85%和 68%。然而，AI 算法性能指标使用不同的标准，因此无法进行理想的客观比较。目前有四个软件平台采用了 ML：Brainomix（对 ASPECTS 的 AI 验证最多，使用 CNN 自动检测 LVOs）、通用电气、iSchemaView（对血栓切除术的灌注研究验证最多）和 Viz.ai（使用 CNN 自动检测 LVOs，然后自动激活紧急中风治疗系统）。
AI 可能会提高 LVO 中风检测和快速分诊的速度，从而加快治疗速度。未来的研究需要对性能评估进行标准化。
