YOLOX目标检测模型用于自动识别数字减影血管造影图中的血管腔内介入器械  

YOLOX target detection model for automatically identifying endovascular interventional instruments on images of digital subtract angiography

作　　者：丰蕊 冯浩 宋超 夏士博 陆清声 FENG Rui;FENG Hao;SONG Chao;XIA Shibo;LU Qingsheng(School of Health Science and Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai Aerospace Energy Co.,Ltd.,Shanghai 201400,China;Department of Vascular Surgery,the First Affiliated Hospital of Naval Medical University,Shanghai 200433,China)

机构地区：[1]上海理工大学健康科学与工程学院,上海200093 [2]上海航天能源股份有限公司,上海201400 [3]海军军医大学第一附属医院血管外科,上海200433

出　　处：《中国介入影像与治疗学》2024年第2期100-104,共5页Chinese Journal of Interventional Imaging and Therapy

基　　金：国家重点研发计划项目(2018AAA0102603)。

摘　　要：目的 观察YOLOX目标检测模型用于自动识别数字减影血管造影(DSA)图中的血管腔内介入器械的价值。方法 收集37例接受腹部血管腔内介入治疗患者的DSA资料,截取4 435幅图像作为数据集,并按照9∶1比例将其分为训练集(n=3 991)与验证集(n=444)。对数据集中的6种介入器械进行标记后,以YOLOX算法对训练集数据进行深度学习训练,构建YOLOX目标检测模型;基于验证集评估该模型自动识别DSA图中的介入器械的效能。结果共对4 435幅DSA图像设置6 668个标签,分别针对Terumo 0.035in泥鳅导丝(n=587)、Cook Lunderquist超硬导丝(n=990)、Optimed 5F带刻度猪尾导管(n=1 680)、Cordis MPA多功能导管(n=667)、Boston Scientific V-18可控导丝(n=1 330)及Terumo 6F长鞘(n=1 414);训练集分别含上述标签527、875、1 466、598、1 185及1 282个,验证集分别含60、115、214、69、145及132个。YOLOX目标检测模型自动识别验证集中上述器械的像素准确率分别为95.23%、97.32%、99.18%、98.97%、97.60%及98.19%,平均像素准确率达97.75%。结论 YOLOX目标检测模型能够自动识别DSA图中的多种血管腔内介入器械。Objective To observe the value of a YOLOX target detection model for automatically identifying endovascular interventional instruments on images of digital subtract angiography(DSA).Methods DSA data of 37 patients who underwent abdominal endovascular interventional therapy were retrospectively analyzed.Totally 4435 DSA images were captured and taken as data set,which were divided into training set(n=3991)and verification set(n=444)at the ratio of 9∶1.Six kinds of endovascular interventional instruments were labeled.YOLOX algorithm was applied for deep learning of data in training set in order to build a target detection model,and the efficacy of the model for automatically identifying endovascular interventional instruments on DSA images was evaluated based on varification set.Results A total of 6668 labels were put on 4435 DSA images,aimed on Terumo 0.035in loach guide wire(n=587),Cook Lunderquist super hard guide wire(n=990),Optimed 5F with graduated pig tail catheter(n=1680),Cordis MPA multi-functional catheter(n=667),Boston Scientific V-18 controllable guide wire(n=1330)and Terumo 6F long sheath(n=1414),respectively.The training set contained 527,875,1466,598,1185 and 1282,while the verification set contained 60,115,214,69,145 and 132 the above labels,respectively.The pixel accuracy of YOLOX target detection model for automatically identifying the above instruments in the verification set was 95.23%,97.32%,99.18%,98.97%,97.60%and 98.19%,respectively,with a mean pixel accuracy of 97.75%.Conclusion YOLOX target detection model could automatically identify endovascular interventional instruments on images of DSA.

关 键 词：血管造影术 数字减影 手术器械 深度学习 自动识别 

分 类 号：R543[医药卫生—心血管疾病] R815[医药卫生—内科学]