超声心动图质量对左心室内膜勾画质量的影响研究  

Influence of echocardiographic image quality on the quality of left ventricular endocardial border delineation

作　　者：刘未央 张培芳 高雨霏 陈煦 林锡祥 杨菲菲[4] 汪安安 何昆仑 LIU Weiyang;ZHANG Peifang;GAO Yufei;CHEN Xu;LIN Xixiang;YANG Feifei;WANG An’an;HE Kunlun(BioMind Tech.Inc.,Beijing 101300,China;National Engineering Research Center of Medical Big Data Application Technology,Beijing 100853,China;Research of Medical Big Data Center,Medical Innovation Research Division,Chinese PLA General Hospital,Beijing 100853,China;Department of Cardiovascular Medicine,the Fourth Medical Center,Chinese PLA General Hospital,Beijing 100048,China)

机构地区：[1]北京安德医智科技有限公司,北京101300 [2]医疗大数据应用技术国家工程研究中心,北京100853 [3]解放军总医院医学创新研究部医学大数据研究中心,北京100853 [4]解放军总医院第四医学中心心内科,北京100048

出　　处：《解放军医学院学报》2022年第8期855-861,共7页Academic Journal of Chinese PLA Medical School

基　　金：中华人民共和国工业和信息化部项目(2020-0103-3-1)。

摘　　要：背景超声是临床上最常用、最经济的影像学检查手段之一,然而超声影像的诊断存在诸多难点,如影像质量偏低、人为差异显著存在、主要依赖高年资医生经验等。基于人工智能(artificial intelligence,AI)技术研发的超声影像智能诊断系统依据高质量的超声影像轮廓勾画数据,是训练AI模型的重要支撑。目的研究超声心动图左心室内膜轮廓勾画的“人为差异”,对其进行客观的定量评估。方法从解放军总医院病例库中随机选取2021年6-8月442例患者的超声心动图心尖二腔(apical 2-chamber,A2C)和心尖四腔切面(apical 4-chamber,A4C)视频。首先由3名三甲医院高年资超声医生选取舒张末和收缩末帧,对舒张末左心室内膜和收缩末左心室内膜分别进行一致轮廓勾画,形成参考标准;然后由4名医学影像分析师对同一切面的舒张末左心室内膜和收缩末左心室内膜进行双盲轮廓勾画;最后,医学影像分析师的勾画质量(衡量其结果与高年资医生的参考标准之间的差异)通过计算内膜轮廓相似度Dice指标、左心室射血分数(left ventricular ejection fraction,LVEF)的差值(即△EF)来量化。超声心动图切面视频按照图像质量被分成好、中、差三组,对比医学影像分析师在两次培训后的勾画质量,定量分析超声心动图轮廓勾画培训的效果。结果医学影像分析师左心室内膜勾画质量的Dice系数随着超声心动图像质量降低而降低,且舒张期末较收缩期末影响更为显著。医学影像分析师勾画的△EF中位数普遍为负值,说明其勾画的EF值普遍较高年资医生的参考标准EF值偏低。轮廓勾画再培训提升了所有4名医学影像分析师与参考标准的△EF,中位数提升3.5%~6.0%。结论超声心动图像质量影响着医学影像分析师对左心室内膜勾画的质量,但通过再培训可缩小其与参考标准的差异。Background Echocardiography is one of the most commonly used and economical radiological examination methods in clinical practice,but there are still many difficulties in the diagnosis of echocardiographic images,such as the low quality of echocardiographic images,significant subjective differences,and dependence on the experience of senior physicians.The ultrasound imaging intelligent diagnosis system based on artificial intelligence(AI)technology is an important support for AI model training based on high-quality ultrasound imaging delineation data.Objective To investigate the“subjective difference”in left ventricular endocardial border delineation by echocardiography,and to perform an objective quantitative evaluation.Methods Echocardiographic apical two-chamber(A2C)and apical four-chamber(A4C)videos were collected from 442 patients in the Chinese PLA General Hospital database who were treated from June to August in 2021.Three senior echocardiographic physicians from grade A tertiary hospitals were invited to select the end-diastolic and end-systolic images and perform left ventricular endocardial border delineation to form a reference standard,then four medical imaging analysts performed double-blind delineation of the end-diastolic and end-systolic left ventricular endocardial border,and finally the quality of delineation by medical imaging analysts(measure the difference between their delineation results and the reference standard of senior physicians)was quantified by calculating the Dice index for contour similarity and the difference of left ventricular ejection fraction(LVEF)(ΔEF).According to image quality,the echocardiographic videos were divided into good-,medium-,and poor-quality groups,and the quality of delineation by medical imaging analysts was compared after two training sessions to quantitatively analyze the efficacy of echocardiographic delineation training.Results The Dice index for the quality of left ventricular endocardial border delineation by medical imaging analysts decreased with

关 键 词：超声心动图 左心室内膜 人工智能 图像质量 图像判读 

分 类 号：R540.45[医药卫生—心血管疾病]