• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

光谱方法结合U-NETs在微波乳腺定量成像中的应用。

Application of Spectral Approach Combined with U-NETs for Quantitative Microwave Breast Imaging.

作者信息

Diès Ambroise, Roussel Hélène, Joachimowicz Nadine

机构信息

Sorbonne Université, CNRS, Laboratoire de Génie Electrique et Electronique de Paris, 75252 Paris, France.

Université Paris Cité, F-75006 Paris, France.

出版信息

Sensors (Basel). 2025 Apr 13;25(8):2450. doi: 10.3390/s25082450.

DOI:10.3390/s25082450
PMID:40285140
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12030878/
Abstract

This study focuses on breast imaging. A spectral approach based on the Fourier diffraction theorem is combined with a pair of U-NETs to perform real-time quantitative human breast imaging. The U-NET pair is trained based on the input of an induced current spectrum and the output of a contrast dielectric spectrum. A spectral database is constructed using combinations of anthropomorphic cavities. The weighted mean absolute percentage error (WMAPE) loss is associated with the Adam optimizer to perform optimization. Numerical results are presented to validate the proposed concept to demonstrate the transformation brought about by the U-NETs.

摘要

本研究聚焦于乳腺成像。基于傅里叶衍射定理的光谱方法与一对U-NET相结合，以实现实时定量人体乳腺成像。该对U-NET基于感应电流谱的输入和对比介电谱的输出进行训练。使用拟人化腔体的组合构建了一个光谱数据库。加权平均绝对百分比误差（WMAPE）损失与Adam优化器相关联以进行优化。给出了数值结果以验证所提出的概念，展示U-NET带来的转变。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/71e49ff652bc/sensors-25-02450-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/5fe77edd9483/sensors-25-02450-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/37d342d6eaa3/sensors-25-02450-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/7528c7e7cbbe/sensors-25-02450-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/ead19e8c2f77/sensors-25-02450-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/b15f5f5fbb5d/sensors-25-02450-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/1c9983bf0d31/sensors-25-02450-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/8e962ea8cc4b/sensors-25-02450-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/71e49ff652bc/sensors-25-02450-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/5fe77edd9483/sensors-25-02450-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/37d342d6eaa3/sensors-25-02450-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/7528c7e7cbbe/sensors-25-02450-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/ead19e8c2f77/sensors-25-02450-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/b15f5f5fbb5d/sensors-25-02450-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/1c9983bf0d31/sensors-25-02450-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/8e962ea8cc4b/sensors-25-02450-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8e9e/12030878/71e49ff652bc/sensors-25-02450-g008.jpg

相似文献

1
Application of Spectral Approach Combined with U-NETs for Quantitative Microwave Breast Imaging.光谱方法结合U-NETs在微波乳腺定量成像中的应用。
Sensors (Basel). 2025 Apr 13;25(8):2450. doi: 10.3390/s25082450.
2
An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U-nets.利用 U-Nets 研究脂肪抑制和维度对乳腺 MRI 分割准确性的影响。
Med Phys. 2019 Mar;46(3):1230-1244. doi: 10.1002/mp.13375. Epub 2019 Feb 4.
3
Assessing Patient-Specific Microwave Breast Imaging in Clinical Case Studies.评估临床病例研究中的患者特异性微波乳腺成像。
Sensors (Basel). 2021 Dec 1;21(23):8048. doi: 10.3390/s21238048.
4
Subspace-Based Two-Step Iterative Shrinkage/Thresholding Algorithm for Microwave Tomography Breast Imaging.基于子空间的两步迭代收缩/阈值算法用于微波断层乳腺成像。
Sensors (Basel). 2025 Feb 26;25(5):1429. doi: 10.3390/s25051429.
5
Enhancement of Multimodal Microwave-Ultrasound Breast Imaging Using a Deep-Learning Technique.基于深度学习技术的多模态微波超声乳腺成像增强。
Sensors (Basel). 2019 Sep 19;19(18):4050. doi: 10.3390/s19184050.
6
Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network.采用简化脉冲耦合神经网络的微波成像中自动乳腺病变定位。
PLoS One. 2022 Jul 21;17(7):e0271377. doi: 10.1371/journal.pone.0271377. eCollection 2022.
7
Development of MRI-based axillary numerical models and estimation of axillary lymph node dielectric properties for microwave imaging.基于 MRI 的腋窝数字模型的开发以及用于微波成象的腋窝淋巴结介电特性的估计。
Med Phys. 2021 Oct;48(10):5974-5990. doi: 10.1002/mp.15143. Epub 2021 Aug 18.
8
Experimental feasibility of multistatic holography for breast microwave radar image reconstruction.用于乳腺微波雷达图像重建的多基地全息术的实验可行性
Med Phys. 2016 Aug;43(8):4674. doi: 10.1118/1.4953636.
9
Multimodal Breast Phantoms for Microwave, Ultrasound, Mammography, Magnetic Resonance and Computed Tomography Imaging.多模态乳房体模用于微波、超声、乳腺 X 线摄影、磁共振和计算机断层扫描成像。
Sensors (Basel). 2020 Apr 23;20(8):2400. doi: 10.3390/s20082400.
10
An Effective Framework for Deep-Learning-Enhanced Quantitative Microwave Imaging and Its Potential for Medical Applications.深度学习增强型定量微波成象的有效框架及其在医学中的应用潜力。
Sensors (Basel). 2023 Jan 6;23(2):643. doi: 10.3390/s23020643.

引用本文的文献

1
Conformal On-Body Antenna System Integrated with Deep Learning for Non-Invasive Breast Cancer Detection.集成深度学习的保形可穿戴天线系统用于无创乳腺癌检测
Sensors (Basel). 2025 Jul 28;25(15):4670. doi: 10.3390/s25154670.

本文引用的文献

1
Microwave Digital Twin Prototype for Shoulder Injury Detection.用于肩伤检测的微波数字孪生原型。
Sensors (Basel). 2024 Oct 16;24(20):6663. doi: 10.3390/s24206663.
2
Microwave Breast Sensing via Deep Learning for Tumor Spatial Localization by Probability Maps.通过概率图的深度学习实现微波乳腺传感以进行肿瘤空间定位
Bioengineering (Basel). 2023 Oct 2;10(10):1153. doi: 10.3390/bioengineering10101153.
3
An End-to-End Deep Learning Approach for Quantitative Microwave Breast Imaging in Real-Time Applications.一种用于实时应用中乳腺定量微波成像的端到端深度学习方法。
Bioengineering (Basel). 2022 Nov 4;9(11):651. doi: 10.3390/bioengineering9110651.
4
Full 3D Microwave Breast Imaging Using a Deep-Learning Technique.使用深度学习技术的全三维微波乳腺成像
J Imaging. 2020 Aug 11;6(8):80. doi: 10.3390/jimaging6080080.
5
Anthropomorphic Breast and Head Phantoms for Microwave Imaging.用于微波成像的拟人化乳房和头部体模
Diagnostics (Basel). 2018 Dec 18;8(4):85. doi: 10.3390/diagnostics8040085.
6
Anthropomorphic breast model repository for research and development of microwave breast imaging technologies.用于微波乳房成像技术研究和开发的拟人乳房模型库。
Sci Data. 2018 Nov 20;5:180257. doi: 10.1038/sdata.2018.257.
7
MRI-Derived 3-D-Printed Breast Phantom for Microwave Breast Imaging Validation.用于微波乳腺成像验证的磁共振成像衍生的三维打印乳腺体模
IEEE Antennas Wirel Propag Lett. 2012;11:1610-1613. doi: 10.1109/LAWP.2012.2236293.
8
Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method.利用畸变玻恩迭代法重建二维介电常数分布。
IEEE Trans Med Imaging. 1990;9(2):218-25. doi: 10.1109/42.56334.
9
Image quality assessment: from error visibility to structural similarity.图像质量评估：从误差可见性到结构相似性。
IEEE Trans Image Process. 2004 Apr;13(4):600-12. doi: 10.1109/tip.2003.819861.
10
Dielectrical spectroscopy of canine myocardium during acute ischemia and hypoxia at frequency spectrum from 100 kHz to 6 GHz.犬心肌在急性缺血和缺氧期间100kHz至6GHz频谱范围内的介电谱
IEEE Trans Med Imaging. 2002 Jun;21(6):703-7. doi: 10.1109/TMI.2002.800590.