Transfer Deep Learning for Dielectric Profile Reconstruction in Microwave Medical Imaging

IF 3 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE Journal of Electromagnetics RF and Microwaves in Medicine and Biology Pub Date : 2024-03-30 DOI:10.1109/JERM.2024.3402048
Fei Xue;Lei Guo;Alina Bialkowski;Amin M. Abbosh
{"title":"Transfer Deep Learning for Dielectric Profile Reconstruction in Microwave Medical Imaging","authors":"Fei Xue;Lei Guo;Alina Bialkowski;Amin M. Abbosh","doi":"10.1109/JERM.2024.3402048","DOIUrl":null,"url":null,"abstract":"Quantitative medical microwave imaging based on deep learning (DL) faces the overfitting problem due to limited training samples available in the clinic database. In this article, a U-Net-like DL model that can reconstruct the dielectric properties of brain tissue using time-domain signals is presented. A transfer learning approach is employed to alleviate the overfitting problem caused by limited training samples. In the proposed approach, the model is first trained with a dataset of random objects in a defined imaging domain and the corresponding time-domain signals. Subsequently, the pre-trained model is fine-tuned using simulation data from an unhealthy object. The final trained model can accurately reconstruct various tissues and abnormal lesions in an unhealthy object and avoid erroneous reconstruction of unexpected lesions in a healthy image of the object. The method is tested using a 16-antenna head imaging system operating across the band 0.5-2 GHz. The results confirm the superior performance of the method, in imaging both healthy and unhealthy brains, as measured using the root mean squared error, the correlation coefficient, the structural similarity index measure, and the peak signal-to-noise ratio. The presented method is a potential solution to mitigate the problem of erroneously predicting lesions in healthy tissues.","PeriodicalId":29955,"journal":{"name":"IEEE Journal of Electromagnetics RF and Microwaves in Medicine and Biology","volume":"8 4","pages":"344-354"},"PeriodicalIF":3.0000,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Journal of Electromagnetics RF and Microwaves in Medicine and Biology","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10542322/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Quantitative medical microwave imaging based on deep learning (DL) faces the overfitting problem due to limited training samples available in the clinic database. In this article, a U-Net-like DL model that can reconstruct the dielectric properties of brain tissue using time-domain signals is presented. A transfer learning approach is employed to alleviate the overfitting problem caused by limited training samples. In the proposed approach, the model is first trained with a dataset of random objects in a defined imaging domain and the corresponding time-domain signals. Subsequently, the pre-trained model is fine-tuned using simulation data from an unhealthy object. The final trained model can accurately reconstruct various tissues and abnormal lesions in an unhealthy object and avoid erroneous reconstruction of unexpected lesions in a healthy image of the object. The method is tested using a 16-antenna head imaging system operating across the band 0.5-2 GHz. The results confirm the superior performance of the method, in imaging both healthy and unhealthy brains, as measured using the root mean squared error, the correlation coefficient, the structural similarity index measure, and the peak signal-to-noise ratio. The presented method is a potential solution to mitigate the problem of erroneously predicting lesions in healthy tissues.
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
用于微波医学成像中介质剖面重构的传输深度学习
由于临床数据库中的训练样本有限,基于深度学习(DL)的定量医学微波成像技术面临着过拟合问题。本文提出了一种类似 U-Net 的 DL 模型,该模型可以利用时域信号重建脑组织的介电特性。该模型采用迁移学习方法来缓解因训练样本有限而导致的过拟合问题。在所提出的方法中,首先使用定义成像域中的随机对象数据集和相应的时域信号对模型进行训练。随后,利用不健康物体的模拟数据对预训练模型进行微调。最终训练出的模型可以准确地重建不健康物体中的各种组织和异常病变,并避免错误地重建健康物体图像中的意外病变。该方法使用工作频带为 0.5-2 GHz 的 16 天线头部成像系统进行了测试。结果证实,根据均方根误差、相关系数、结构相似性指数测量和峰值信噪比测量,该方法在健康和不健康大脑成像中均表现出色。所提出的方法是缓解错误预测健康组织病变问题的潜在解决方案。
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
CiteScore
5.80
自引率
9.40%
发文量
58
期刊最新文献
2024 Index IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology Vol. 8 Front Cover Table of Contents IEEE Journal of Electromagnetics, RF, and Microwaves in Medicine and Biology About this Journal IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology Publication Information
×
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