{"title":"Common Carotid Artery Wall Localization in B-mode Ultrasound Images for Initialization of Artery Wall Tracking Methods","authors":"Jan Dorazil, K. Říha, M. Dutta","doi":"10.1109/TSP.2019.8769077","DOIUrl":null,"url":null,"abstract":"Analysis of the movement of the common carotid artery (CCA) wall in ultrasound sequences can be used for diagnosis of many cardiovascular diseases. In this paper we introduce a method for localization of the CCA wall contour (approximated by a circle) inside an ultrasound image, which can be used in real-time applications for initialization of an artery wall tracking method. First we detect a rectangular region of interest (ROI) using a recently proposed method based on the Viola-Jones detector. Next we perform an exhaustive search over all possible circles inside the ROI. Circle which maximizes a particular criterion represents the final estimate. Experimental results on a dataset of 145 ultrasound images show that the method outperforms a reference method based on the Hough transform in terms of precision and misdetection rates.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TSP.2019.8769077","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
Analysis of the movement of the common carotid artery (CCA) wall in ultrasound sequences can be used for diagnosis of many cardiovascular diseases. In this paper we introduce a method for localization of the CCA wall contour (approximated by a circle) inside an ultrasound image, which can be used in real-time applications for initialization of an artery wall tracking method. First we detect a rectangular region of interest (ROI) using a recently proposed method based on the Viola-Jones detector. Next we perform an exhaustive search over all possible circles inside the ROI. Circle which maximizes a particular criterion represents the final estimate. Experimental results on a dataset of 145 ultrasound images show that the method outperforms a reference method based on the Hough transform in terms of precision and misdetection rates.