使用机器学习在急性缺血性卒中患者非增强CT上自动计算ASPECTS
本研究收集257例急性缺血性卒中患者(发病至扫描<8小时)的非增强CT(5mm层厚)及1小时内DWI,以DWI专家ASPECTS读片为参考标准;用157例训练随机森林分类器、100例测试。测试集总ASPECTS的组内相关系数为0.76(95%CI 0.67-0.83),区域水平κ=0.60、敏感度66.2%、特异度91.8%、AUC 0.79;二分类(>4与≤4)κ=0.78、敏感度97.8%、特异度80%、AUC 0.89。作者认为该自动ASPECTS评分方法在NCCT上判断ASPECTS具有合理能力。
要点
- 自动ASPECTS与DWI专家评分总分组内相关系数0.76(95%CI 0.67-0.83)。
- 区域水平κ=0.60、敏感度66.2%、特异度91.8%、AUC 0.79。
- 二分类>4与≤4时敏感度97.8%、特异度80%、AUC 0.89。
核心结论
- 所提出的自动ASPECTS评分方法在急性缺血性卒中患者NCCT图像上判断ASPECTS显示出合理能力。
研究设计与样本
- 研究论文;257例急性缺血性卒中患者(发病至扫描<8小时),采集5mm层厚NCCT,并在1小时内行DWI;以DWI专家ASPECTS读片为参考标准;157例训练随机森林分类器,100例测试。
关键影像表现/征象
- 从每个ASPECTS区域提取纹理特征用于训练随机森林分类器。
- 自动ASPECTS与DWI专家评分总分的Bland-Altman平均差为0.3(一致性界限-3.3、2.6)。
诊断标准与关键数值
- 测试集100例总ASPECTS:自动方法与DWI专家评分的组内相关系数0.76(95%CI 0.67-0.83)。
- 区域水平(100×10个ASPECTS区域):κ=0.60、敏感度66.2%、特异度91.8%、AUC 0.79。
- ASPECTS二分类(>4与≤4):κ=0.78、敏感度97.8%、特异度80%、AUC 0.89。
临床应用与阅片要点
- 作者认为该自动ASPECTS评分方法在NCCT上判断ASPECTS具有合理能力。
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 AND PURPOSE: Alberta Stroke Program Early CT Score (ASPECTS) was devised as a systematic method to assess the extent of early ischemic change on noncontrast CT (NCCT) in patients with acute ischemic stroke (AIS). Our aim was to automate ASPECTS to objectively score NCCT of AIS patients.
MATERIALS AND METHODS: We collected NCCT images with a 5-mm thickness of 257 patients with acute ischemic stroke (<8 hours from onset to scans) followed by a diffusion-weighted imaging acquisition within 1 hour. Expert ASPECTS readings on DWI were used as ground truth. Texture features were extracted from each ASPECTS region of the 157 training patient images to train a random forest classifier. The unseen 100 testing patient images were used to evaluate the performance of the trained classifier. Statistical analyses on the total ASPECTS and region-level ASPECTS were conducted.
RESULTS: For the total ASPECTS of the unseen 100 patients, the intraclass correlation coefficient between the automated ASPECTS method and DWI ASPECTS scores of expert readings was 0.76 (95% confidence interval, 0.67-0.83) and the mean ASPECTS difference in the Bland-Altman plot was 0.3 (limits of agreement, -3.3, 2.6). Individual ASPECTS region-level analysis showed that our method yielded κ = 0.60, sensitivity of 66.2%, specificity of 91.8%, and area under curve of 0.79 for 100 × 10 ASPECTS regions. Additionally, when ASPECTS was dichotomized (>4 and ≤4), κ = 0.78, sensitivity of 97.8%, specificity of 80%, and area under the curve of 0.89 were generated between the proposed method and expert readings on DWI.
CONCLUSIONS: The proposed automated ASPECTS scoring approach shows reasonable ability to determine ASPECTS on NCCT images in patients presenting with acute ischemic stroke.
引用
- Kuang H, Najm M, Chakraborty D, et al. Automated ASPECTS on Noncontrast CT Scans in Patients with Acute Ischemic Stroke Using Machine Learning. AJNR Am J Neuroradiol. 2018. PMID: 30498017. doi:10.3174/ajnr.A5889
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。