Carotid Artery Segmentation Using Convolutional Neural Network in Ultrasound Images

IF 0.4 Q4 COMPUTER SCIENCE, INFORMATION SYSTEMS
N. Radovanovic, Lazar Dašić, A. Blagojević, T. Šušteršič, Nenad Filipović
{"title":"Carotid Artery Segmentation Using Convolutional Neural Network in Ultrasound Images","authors":"N. Radovanovic, Lazar Dašić, A. Blagojević, T. Šušteršič, Nenad Filipović","doi":"10.58245/ipsi.tir.22jr.08","DOIUrl":null,"url":null,"abstract":"Cardiovascular disease (CVD) is one of the leading causes of death in urban areas. Carotid artery segmentation is the initial step in the automated diagnosis of carotid artery disease. The segmentation of carotid wall and lumen region boundaries are used as an essential part in assessing plaque morphology. In this paper, two types of Convolutional Neural Network (CNN) architectures are used for segmentation: U-Net and SegNet. The models used in this paper are applied on 257 ultrasound images containing a transverse section of the vessel acquired by ultrasound. Ultrasound imaging is noninvasive, completely unharming for the patient and a low-cost imaging method, but the main challenge when working with this kind of images is a very low signal to noise ratio and the process of imaging is highly dependent on the device operator. Different models are tested for various ranges of hyperparameter values and compared using different metrics. The model presented in this paper achieved over 94% Dice Coefficient for wall and lumen segmentation when trained during 100 epochs.","PeriodicalId":41192,"journal":{"name":"IPSI BgD Transactions on Internet Research","volume":"101 1","pages":""},"PeriodicalIF":0.4000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IPSI BgD Transactions on Internet Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.58245/ipsi.tir.22jr.08","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 1

Abstract

Cardiovascular disease (CVD) is one of the leading causes of death in urban areas. Carotid artery segmentation is the initial step in the automated diagnosis of carotid artery disease. The segmentation of carotid wall and lumen region boundaries are used as an essential part in assessing plaque morphology. In this paper, two types of Convolutional Neural Network (CNN) architectures are used for segmentation: U-Net and SegNet. The models used in this paper are applied on 257 ultrasound images containing a transverse section of the vessel acquired by ultrasound. Ultrasound imaging is noninvasive, completely unharming for the patient and a low-cost imaging method, but the main challenge when working with this kind of images is a very low signal to noise ratio and the process of imaging is highly dependent on the device operator. Different models are tested for various ranges of hyperparameter values and compared using different metrics. The model presented in this paper achieved over 94% Dice Coefficient for wall and lumen segmentation when trained during 100 epochs.
超声图像中基于卷积神经网络的颈动脉分割
心血管疾病是城市地区的主要死亡原因之一。颈动脉分割是颈动脉疾病自动诊断的第一步。颈动脉壁和管腔区域边界的分割是评估斑块形态的重要部分。在本文中,两种类型的卷积神经网络(CNN)架构被用于分割:U-Net和SegNet。本文所使用的模型应用于257张超声图像,其中包含了超声获取的血管横切面。超声成像是非侵入性的,对患者完全无害,是一种低成本的成像方法,但处理这种图像时的主要挑战是信号噪声比非常低,成像过程高度依赖于设备操作员。不同的模型对不同范围的超参数值进行测试,并使用不同的度量进行比较。本文提出的模型在经过100次训练后,对壁腔和腔腔分割的骰子系数达到94%以上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IPSI BgD Transactions on Internet Research
IPSI BgD Transactions on Internet Research COMPUTER SCIENCE, INFORMATION SYSTEMS-
自引率
25.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信