计算机辅助诊断脑血管病的应用  

Application of computer-aided diagnosis for cerebrovascular diseases

作　　者：周昱汐 贾守强 聂生东[1] ZHOU Yuxi;JIA Shouqiang;NIE Shengdong(Institute of Medical Imaging Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Department of Imaging,Jinan People's Hospital Affiliated to Shandong First Medical University,Jinan 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9期1167-1173,共7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：脑血管病具有高死亡率、高致残率、高复发率的特点,颅内病变的早期确诊是降低其死亡率的关键。临床上,脑血管病的人工诊断效率较低,时常出现漏诊、误诊的现象,而基于人工智能(AI)的计算机辅助诊断技术通过挖掘医学影像中的特征,能够辅助医生快速、准确地定位早期病灶,提高诊断效率。首先,本研究概述了AI辅助鉴别脑卒中类型、确定脑卒中发病时间、判断脑卒中梗死病灶范围方面的应用;然后,针对AI辅助检测颅内动脉瘤、颅内动脉狭窄、脑动静脉畸形3种脑血管病变方面的研究应用分别进行综述;最后,总结AI在脑血管病临床诊断中的挑战,并对该领域的研究方向进行展望。Cerebrovascular disease has the characteristics of high mortality,high disability rate,and high recurrence rate.The key to reducing mortality is the early diagnosis of intracranial lesions.Clinically,the physician diagnosis of cerebrovascular disease is inefficient,and the missed diagnosis and misdiagnosis often occur.The computer-aided diagnosis technology based on artificial intelligence(AI)can assist physicians to localize the early lesions quickly and accurately by obtaining the features in medical images.Here the applications of AI in differentiating stroke types,determining the time of stroke onset,and delineating the stroke infarction lesions are introduced,focusing on the AI-assisted detections of intracranial aneurysm,intracranial artery stenosis and brain arteriovenous malformations.Finally,the challenges faced in the AI-assisted diagnosis of cerebrovascular disease are summarized,and the prospects for future research are put forward.

关 键 词：脑卒中 脑血管病 计算机辅助诊断 人工智能 综述 

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