Model-based Fully Dense UNet for Image Enhancement in Software-defined Optoacoustic Tomography

M. Gonzalez, L. Vega
{"title":"Model-based Fully Dense UNet for Image Enhancement in Software-defined Optoacoustic Tomography","authors":"M. Gonzalez, L. Vega","doi":"10.1109/ARGENCON55245.2022.9940135","DOIUrl":null,"url":null,"abstract":"A deep neural network architecture for improving the performance of a software-defined optoacoustic tomography device is presented. Our approach is a hybrid one, in the sense that a powerful data-driven architecture (a FD-UNet) is combined with a structure that exploits model-guided information, in the form of the forward and adjoint operators of the acoustic problem. Besides that, the findings of a previous work on the noise and other effects on the measured sinograms are also exploited, in order to make the structure more robust in the task of correcting the artifacts that are typically introduced in the reconstructed images. The proposed solution is numerically trained and evaluated. In terms of the average mean square error over the testing data-set, our approach shows better performance than well-established reconstruction algorithms in the field of optoacustic tomography. A series of examples shows that this superior performance also holds with respect to other reconstruction image quality measures.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ARGENCON55245.2022.9940135","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

A deep neural network architecture for improving the performance of a software-defined optoacoustic tomography device is presented. Our approach is a hybrid one, in the sense that a powerful data-driven architecture (a FD-UNet) is combined with a structure that exploits model-guided information, in the form of the forward and adjoint operators of the acoustic problem. Besides that, the findings of a previous work on the noise and other effects on the measured sinograms are also exploited, in order to make the structure more robust in the task of correcting the artifacts that are typically introduced in the reconstructed images. The proposed solution is numerically trained and evaluated. In terms of the average mean square error over the testing data-set, our approach shows better performance than well-established reconstruction algorithms in the field of optoacustic tomography. A series of examples shows that this superior performance also holds with respect to other reconstruction image quality measures.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
软件定义光声断层成像中基于模型的全密度UNet图像增强
提出了一种用于提高软件定义光声层析成像设备性能的深度神经网络结构。我们的方法是一种混合方法,在某种意义上,一个强大的数据驱动架构(FD-UNet)与一个利用模型引导信息的结构相结合,以声学问题的前向算子和伴随算子的形式。除此之外,为了使结构在校正重建图像中通常引入的伪影的任务中更加鲁棒,还利用了先前关于噪声和对测量的正弦图的其他影响的研究结果。提出的解决方案进行了数值训练和评估。就测试数据集的平均均方误差而言,我们的方法比光声断层成像领域中成熟的重建算法表现出更好的性能。一系列实例表明,这种优越的性能也适用于其他重建图像质量指标。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Propuestas de normativas para la disposición final de equipamientos de un parque eólico al finalizar su vida productiva Proyecto Laboratorios remotos en carreras de ingeniería de la Universidad Nacional de Tucumán Control de un convertidor DC-DC con puentes duales activos para adaptar niveles de tensión en microrredes de DC usando linealización por realimentación Las Competencias Transversales en Ingeniería. El Seminario Taller Como Herramienta Metodológica Procedimiento de sintonizado de tanques resonantes LCC para carga inalámbrica de vehículos eléctricos
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1