Contour extraction of fetus' head from echocardiogram using Snakes

Toshiyuki Tanaka, M. Torikai
{"title":"Contour extraction of fetus' head from echocardiogram using Snakes","authors":"Toshiyuki Tanaka, M. Torikai","doi":"10.1109/IEMBS.2002.1106281","DOIUrl":null,"url":null,"abstract":"Summary form only given. We extract a contour of the fetus head from an echocardiogram BPD (biparietal diameter) level at 15-25 pregnancy weeks, without being influenced by the lack of pixels and noise elements, for the diagnostic support of the doctor. As for the contour of the fetus head, it is effective for diagnosis of the pregnancy week and degree of deformity before birth. Various evaluation values were automatically calculated as features from the obtained contour. This research consists of preprocessing, contour extraction, and calculation of the evaluation value. First, as the preprocessing, the noise is reduced from the original image and an indistinct point has been improved by using the contrast emphasis and median filtering. Next, the contour of the fetus head was extracted by using the active contour model Snakes, more highly accurate than a general technique. Finally the OFD (occipitofrontal diameter), BPD, were automatically computed from the obtained contour. The improvement of the extraction accuracy was confirmed by setting the best energy parameters for Snakes in contour extraction. We succeeded in obtaining evaluation values with the same accuracy, compared with those calculated from the contour depicted by the doctor.","PeriodicalId":60385,"journal":{"name":"中国地球物理学会年刊","volume":"9 1","pages":"1070 vol.2-"},"PeriodicalIF":0.0000,"publicationDate":"2003-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国地球物理学会年刊","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.1109/IEMBS.2002.1106281","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Summary form only given. We extract a contour of the fetus head from an echocardiogram BPD (biparietal diameter) level at 15-25 pregnancy weeks, without being influenced by the lack of pixels and noise elements, for the diagnostic support of the doctor. As for the contour of the fetus head, it is effective for diagnosis of the pregnancy week and degree of deformity before birth. Various evaluation values were automatically calculated as features from the obtained contour. This research consists of preprocessing, contour extraction, and calculation of the evaluation value. First, as the preprocessing, the noise is reduced from the original image and an indistinct point has been improved by using the contrast emphasis and median filtering. Next, the contour of the fetus head was extracted by using the active contour model Snakes, more highly accurate than a general technique. Finally the OFD (occipitofrontal diameter), BPD, were automatically computed from the obtained contour. The improvement of the extraction accuracy was confirmed by setting the best energy parameters for Snakes in contour extraction. We succeeded in obtaining evaluation values with the same accuracy, compared with those calculated from the contour depicted by the doctor.
蛇形超声心动图胎儿头部轮廓提取
只提供摘要形式。我们从妊娠15-25周的超声心动图BPD(双顶叶直径)水平中提取胎儿头部轮廓,不受缺乏像素和噪声元素的影响,用于医生的诊断支持。胎儿头部轮廓对产前妊娠周和畸形程度的诊断是有效的。从获得的轮廓线中自动计算出各种评价值作为特征。该研究包括预处理、轮廓提取和评价值计算。首先,在预处理过程中,通过对比度强调和中值滤波对原始图像进行降噪,改善模糊点;其次,利用活动轮廓模型snake提取胎儿头部轮廓,比一般方法的提取精度更高。最后根据得到的轮廓线自动计算枕额直径(OFD),即BPD。通过设置蛇形轮廓提取的最佳能量参数,验证了提取精度的提高。与医生描绘的轮廓计算值相比,我们成功地获得了具有相同精度的评价值。
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
自引率
0.00%
发文量
368
×
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