自动ASPECTS评分法在急性缺血性卒中早期影像评估中的应用价值

doi:10.3969/j.issn.1673-5765.2021.05.008

摘要/Abstract

摘要：

目的评价自动ASPECTS评分法在急性缺血性卒中早期影像评估中的实际临床应用价值。方法回顾性分析2020年6-10月在北京天坛医院连续就诊的急性缺血性卒中病例，收集影像归档和通信系统上由RAPID软件评估的基于CT的自动ASPECTS评分，以DWI高信号作为梗死核心标准获得 DWI ASPECTS评分，将自动ASPECTS与DWI ASPECTS评分法进行组内相关系数与Cohen’s kappa分析，并计算自动ASPECTS评分法的敏感度、特异度及准确度。结果分析大脑中动脉供血区急性缺血性卒中病例72例，基于分值的自动ASPECTS与DWI ASPECTS 的组内相关系数为0.746（P <0.001）。在ASPECTS≥6分与ASPECTS＜6分的二分类分析时，自动 ASPECTS与DWI ASPECTS评分系统一致性较高（kappa=0.742）。基于区域分布的自动ASPECTS评分法的敏感度、特异度及准确度分别为53.64%、85.99%及73.33%，其中皮层区分别为47.61%、98.47%、 78.94%；脑深部区分别为62.68%、67.27%、64.93%。结论基于分值的自动ASPECTS评分法可以评估急性缺血性卒中受累范围的大小。基于区域分布的自动ASPECTS评分法的敏感度、特异度及准确度在每个区域存在差异，因此最终诊断需要结合患者临床症状体征综合判断。

文章导读： 基于分值的自动ASPECTS评分系统可以评估急性缺血性卒中受累范围的大小。基于区域分布的自动ASPECTS评分系统的敏感度、特异度及准确度存在差异，需要结合患者临床症状体征综合判断。

关键词: Alberta卒中项目早期CT评分; 计算机断层成像; 缺血性卒中; 机器学习

Abstract:

Objective To assess the application value of automatic ASPECTS scoring in early imaging assessment of acute ischemic stroke (AIS) in the real clinical setting. Methods This retrospective analysis enrolled consecutive AIS patients admitted to Beijing Tiantan Hospital between 2020 June and 2020 October. The data of automated ASPECTS scores extracted by RAPID software were collected, and the DWI ASPECTS scores were obtained based on the hyperintensities (as infarct core standard) on DWI. The automated ASPECTS and DWI ASPECTS were compared by using interclass correlation coefficient (ICC) and Cohen's kappa analysis, then the sensitivity, specificity and accuracy of automated ASPECTS scoring were calculated. Results Seventy-two cases with AIS in middle cerebral artery territory were included. The ICC between score-based automated ASPECTS and DWI ASPECTS was 0.746 (P <0.001). In the dichotomization analysis of ASPECTS ≥6 and ASPECTS <6, the two scoring tools showed good agreement (kappa=0.742). The total sensitivity, specificity and accuracy of region-based automatic ASPECTS scoring were 53.64%, 85.99% and 73.33%, respectively; those were 47.61%, 98.47% and 78.94% in the cortical region, respectively, and those were 62.68%, 67.27%, 64.93% in the deep brain region, respectively. Conclusions The score-based automated ASPECTS scoring can reflect the size of infarct region in AIS. The sensitivity, specificity and accuracy of region-based automatic ASPECTS scoring varied in different brain regions, thereby the involved region in AIS need to be identified by combing clinical symptoms and signs.

Key words: Alberta stroke program early CT score; Computed tomography; Ischemic stroke;Machine learning

荆利娜，高培毅，杜万良，沈宓，秦海强，克德娜，马国锋，周剑. 自动ASPECTS评分法在急性缺血性卒中早期影像评估中的应用价值[J]. 中国卒中杂志, 2021, 16(05): 463-469.

JING Li-Na, GAO Pei-Yi, DU Wan-Liang, SHEN Mi, QIN Hai-Qiang, KE De-Na, MA Guo-Feng, ZHOU Jian. The Value of Automated ASPECTS Scoring in Imaging Assessment of Early Ischemic Changes in Acute Ischemic Stroke[J]. Chinese Journal of Stroke, 2021, 16(05): 463-469.

参考文献

[1] GOYAL M，DEMCHUK A M，MENON B K，et

al. Randomized assessment of rapid endovascular

treatment of ischemic stroke[J]. N Engl J Med，2015，

372（11）：1019-1030.

[2] AUSTEIN F，WODARG F，JURGENSEN N，et al.

Automated versus manual imaging assessment of

early ischemic changes in acute stroke：comparison

of two software packages and expert consensus[J].

Eur Radiol，2019，29（11）：6285-6292.

[3] GOEBEL J，STENZEL E，GUBERINA N，et al.

Automated ASPECT rating：comparison between the

frontier ASPECT score software and the brainomix

software[J]. Neuroradiology，2018，60（12）：1267-

1272.

[4] ALBERS G W，WALD M J，MLYNASH M，et al.

Automated calculation of Alberta stroke program

early CT score：validation in patients with large

hemispheric infarct[J]. Stroke，2019，50（11）：3277-

3279.

[5] YEW K S，CHENG E M. Diagnosis of acute

stroke[J]. Am Fam Physician，2015，91（8）：528-536.

[6] MAEGERLEIN C，FISCHER J，MONCH S，et

al. Automated calculation of the Alberta stroke

program early CT score：feasibility and reliability[J].

Radiology，2019，291（1）：141-148.

[7] LI L，CHEN Y，BAO Y，et al. Comparison of the

performance between frontier ASPECTS software

and different levels of radiologists on assessing CT

examinations of acute ischaemic stroke patients[J].

Clin Radiol，2020，75（5）：358-365.

[8] HOELTER P，MUEHLEN I，GOELITZ P，et al.

Automated ASPECT scoring in acute ischemic

stroke：comparison of three software tools[J].

Neuroradiology，2020，62（10）：1231-1238.

[9] HERWEH C，RINGLEB P A，RAUCH G，et al.

Performance of e-ASPECTS software in comparison

to that of stroke physicians on assessing CT scans of

acute ischemic stroke patients[J]. Int J Stroke，2016，

11（4）：438-445.

[10] POWERS W J，DERDEYN C P，BILLER J，et al.

2015 American Heart Association/American Stroke

Association focused update of the 2013 guidelines for

the early management of patients with acute ischemic

stroke regarding endovascular treatment：a guideline

for healthcare professionals from the American Heart

Association/American Stroke Association[J]. Stroke，

2015，46（10）：3020-3035.

[11] NAGEL S，SINHA D，DAY D，et al. E-ASPECTS

software is non-inferior to neuroradiologists in

applying the ASPECT score to computed tomography

scans of acute ischemic stroke patients[J]. Int J

Stroke，2017，12（6）：615-622.

[12] GUBERINA N，DIETRICH U，RADBRUCH A，et

al. Detection of early infarction signs with machine

learning-based diagnosis by means of the Alberta

Stroke Program Early CT Score（ASPECTS）in the

clinical routine[J]. Neuroradiology，2018，60（9）：

889-901.

[1]	吴娱倩, 张玉梅, 范小伟, 王安心, 逄文斌. 运动想象-动觉治疗对缺血性卒中患者手功能康复效果的研究[J]. 中国卒中杂志, 2022, 17(12): 1366-1371.
[2]	蒋林, 李靖. 基于知识图谱分析人工智能用于卒中研究的现状及趋势 [J]. 中国卒中杂志, 2022, 17(12): 1372-1380.
[3]	伊珞, 周宏宇, 仇鑫, 李子孝, 王拥军. 动脉粥样硬化性疾病的DNA甲基化改变[J]. 中国卒中杂志, 2022, 17(11): 1163-1170.
[4]	王誉博, 李子孝, 王拥军. 表观遗传学与缺血性卒中后氧化应激的相关性研究进展[J]. 中国卒中杂志, 2022, 17(11): 1171-1177.
[5]	崔凌云, 仇鑫, 周宏宇, 李子孝, 王拥军. DNA甲基化与2型糖尿病的相关性研究进展[J]. 中国卒中杂志, 2022, 17(11): 1183-1188.
[6]	邓宇含, 刘爽, 王子尧, 汪雨欣, 刘宝花. 基于结构化数据和机器学习模型预测普通人群卒中发病风险的系统评价和meta分析 [J]. 中国卒中杂志, 2022, 17(11): 1189-1197.
[7]	刘光亮, 韩凯月, 苏文龙, 张皓. 不同强度有氧踏车训练对不同病程缺血性卒中患者运动和心肺适能的影响 [J]. 中国卒中杂志, 2022, 17(11): 1203-1208.
[8]	徐莹鑫, 张爽, 周晓梅, 袁景林, 赵留庄, 杨海华. 非狭窄性颈动脉斑块与前循环不明原因栓塞性卒中的相关性研究 [J]. 中国卒中杂志, 2022, 17(11): 1233-1237.
[9]	程实, 李静, 郭军平, 胡爱香, 于鑫玮, 韩玮, 梁瑛, 张越巍, 冀瑞俊. 急性卒中患者住院期间感染的临床特征及危险因素分析[J]. 中国卒中杂志, 2022, 17(10): 1065-1070.
[10]	向薇, 徐璐瑶, 张曼曼, 魏红春, 梁志刚. 缺血性卒中急性期磁敏感加权成像不对称突出静脉征的发生率及影响因素分析[J]. 中国卒中杂志, 2022, 17(10): 1097-1102.
[11]	赵永瑞, 刘展会. 弥散张量成像在缺血性卒中患者运动功能预后评估中的研究进展[J]. 中国卒中杂志, 2022, 17(10): 1114-1119.
[12]	张伯煜, 郭玉成, 崔玉霞, 李英丽, 吕雨梅. 急性缺血性卒中患者就医行为决策现状及影响因素研究进展[J]. 中国卒中杂志, 2022, 17(10): 1127-1132.
[13]	吴亭亭, 刘亚飞, 闫世曦, 武一平, 张忠波, 张邯菲, 房娉平. “互联网+”在急性缺血性卒中救治中的应用进展[J]. 中国卒中杂志, 2022, 17(10): 1133-1138.
[14]	徐蔚海, 李顺, 程安琪. 青年卒中的诊治：勿过激[J]. 中国卒中杂志, 2022, 17(09): 915-918.
[15]	张一歌, 张婉, 张璐阳, 王鑫, 丁澜, 王玉莹, 裴璐璐, 方慧, 许予明, 宋波. 责任动脉闭塞与夹层相关缺血性卒中复发的相关性分析[J]. 中国卒中杂志, 2022, 17(09): 932-936.