人工智能在急性缺血性脑卒中早期ASPECTS评估中的研究进展  

Artificial intelligence in ASPECTS assessment of acute ischemic stroke:a review

作　　者：方婷 杨一风 贾守强 聂生东[1] FANG Ting;YANG Yifeng;JIA Shouqiang;NIE Shengdong(Institute of Medical Imaging Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Department of Imaging,Ji'nan People's Hospital Affiliated to Shandong First Medical University,Ji'nan 271100,China)

机构地区：[1]上海理工大学医学影像工程研究所,上海200093 [2]山东第一医科大学附属济南人民医院影像科,山东济南271100

出　　处：《中国医学物理学杂志》2023年第8期1045-1050,共6页Chinese Journal of Medical Physics

基　　金：国家自然科学基金(81830052);上海市自然科学基金(20ZR1438300)。

摘　　要：急性缺血性脑卒中(AIS)的早期诊断和及时干预对于降低脑卒中的致死致残率具有重要意义。目前,临床上采用阿尔伯塔卒中项目早期计算机断层扫描评分(ASPECTS)来评估AIS的严重程度,但人为评估方法主观性过强且耗时耗力,极易导致漏诊、误诊。因此,近年来涌现了许多基于人工智能算法对AIS进行ASPECTS自动评分的方法研究。本文对此进行综述,以期为进一步研究探索提供参考。首先,简述ASPECTS评分的可靠性;其次,重点介绍目前基于人工智能的脑区提取及脑区评分的方法,证实计算机辅助ASPECTS评分能够有效提高对病情判断的可靠性;最后,总结现有ASPECTS自动评分方法存在的不足,并对其未来的发展趋势进行展望。The early diagnosis and timely intervention of acute ischemic stroke are of great significance to reduce the mortality and disability rate.Alberta stroke program early computed tomography score(ASPECTS)is currently used to assess the severity of acute ischemic stroke in clinic.The human evaluation is subjective and time-consuming,which is easy to lead to missed diagnosis and misdiagnosis.Therefore,many automatic ASPECTS methods based on artificial intelligence algorithms are emerging.The study briefly introduces the reliability of ASPECTS,focuses on the current methods of brain region extraction and brain region scoring based on artificial intelligence for confirming that computer-assisted ASPECTS can effectively improve the reliability of disease judgment,summarizes the existing problems,and discusses the development trends.

关 键 词：ASPECTS评分 急性缺血性脑卒中 人工智能 自动化评分 综述 

分 类 号：R318[医药卫生—生物医学工程] R743.3[医药卫生—基础医学]