Reconstruction of Fetal Head Surface from Few 2D Ultrasound Images Tracked in 3D Space

S. Marcadent, J. Hêches, J. Favre, D. Desseauve, J. Thiran
{"title":"Reconstruction of Fetal Head Surface from Few 2D Ultrasound Images Tracked in 3D Space","authors":"S. Marcadent, J. Hêches, J. Favre, D. Desseauve, J. Thiran","doi":"10.1109/IECBES54088.2022.10079362","DOIUrl":null,"url":null,"abstract":"In this pilot study, we present a new engineering approach to reconstruct a patient-specific model of the fetal head near term. Indeed, 3D visualization of the fetus prominent skull could help the obstetricians in decision-making to overcome dystocia, a delivery complication which results in labour obstruction. The full reconstruction pipeline is based on the recording of a small set of tracked 2D ultrasound images around the transthalamic brain plane. The use of 2D ultrasound images tracked in 3D space would allow to superimpose the fetal head model to other reconstructed organs. The fetal head is large at late pregnancy stages which causes occlusions in the ultrasound images. Moreover, fetal motion may affect the consistency of ultrasound images, in particular if many frames are needed. Therefore, we propose to extrapolate the full fetal head surface from 10 focused frames only. The reconstruction performance was evaluated in simulation based on a MRI dataset of 7 patients at 34-36 weeks of pregnancy; our best method achieves 1.6 mm of average reconstruction error.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IECBES54088.2022.10079362","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

In this pilot study, we present a new engineering approach to reconstruct a patient-specific model of the fetal head near term. Indeed, 3D visualization of the fetus prominent skull could help the obstetricians in decision-making to overcome dystocia, a delivery complication which results in labour obstruction. The full reconstruction pipeline is based on the recording of a small set of tracked 2D ultrasound images around the transthalamic brain plane. The use of 2D ultrasound images tracked in 3D space would allow to superimpose the fetal head model to other reconstructed organs. The fetal head is large at late pregnancy stages which causes occlusions in the ultrasound images. Moreover, fetal motion may affect the consistency of ultrasound images, in particular if many frames are needed. Therefore, we propose to extrapolate the full fetal head surface from 10 focused frames only. The reconstruction performance was evaluated in simulation based on a MRI dataset of 7 patients at 34-36 weeks of pregnancy; our best method achieves 1.6 mm of average reconstruction error.
利用少量二维超声图像在三维空间中进行胎儿头部表面重建
在这项初步研究中,我们提出了一种新的工程方法来重建患者特异性的胎儿头部模型。事实上,胎儿突出颅骨的三维可视化可以帮助产科医生做出决定,以克服难产,难产是一种导致分娩梗阻的分娩并发症。完整的重建管道是基于在丘脑外脑平面周围记录一组跟踪的二维超声图像。利用二维超声图像跟踪三维空间,可以将胎儿头部模型叠加到其他重建器官上。妊娠后期胎儿头部较大,导致超声图像闭塞。此外,胎儿运动可能会影响超声图像的一致性,特别是如果需要许多帧。因此,我们建议仅从10个聚焦帧推断出完整的胎儿头部表面。基于7例怀孕34-36周的患者的MRI数据集,模拟评估重建性能;我们的最佳方法实现了1.6 mm的平均重建误差。
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
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