Near-Field Microwave Scattering Formulation by A Deep Learning Method.
Near-Field Microwave Scattering Formulation by A Deep Learning Method.
复制标题
DOI：
10.1109/tmtt.2022.3184331
复制
发表时间：
2022-11
影响因子：
4.3
通讯作者：
Zhou, Beibei
中科院分区：
文献类型：
--
作者：
Shao, Wenyi;Zhou, Beibei
关键词：
应用深度学习方法对微波乳腺成像 (MBI) 的电磁 (EM) 散射进行建模。神经网络 (NN) 接受 3 GHz 的 2D 电介质乳房图，并在由 24 个发射器和 24 个接收器组成的天线阵列上生成散射场数据。该神经网络由生成对抗网络 (GAN) 生成的 18,000 个合成数字乳房模型以及通过矩量法 (MOM) 预先计算的分散场数据进行训练。通过将从训练数据中分离出来的 2,000 个神经网络生成的数据集与 MOM 计算的数据进行比较来进行验证。最后，使用NN和MOM生成的数据进行图像重建。重建结果表明，神经网络引起的误差不会显着影响图像结果。但神经网络的计算速度比 MOM 快了近 104 倍，这表明深度学习有潜力被视为电磁散射计算的快速工具。
A deep learning method is applied to modelling electromagnetic (EM) scattering for microwave breast imaging (MBI). The neural network (NN) accepts 2D dielectric breast maps at 3 GHz and produces scattered-field data on an antenna array composed of 24 transmitters and 24 receivers. The NN was trained by 18,000 synthetic digital breast phantoms generated by generative adversarial network (GAN), and the scattered-field data pre-calculated by method of moments (MOM). Validation was performed by comparing the 2,000 NN-produced datasets isolated from the training data with the data computed by MOM. Finally, data generated by NN and MOM were used for image reconstruction. The reconstruction demonstrated that errors caused by NN would not significantly affect the image result. But the computational speed of NN was nearly 104 times faster than the MOM, indicating that deep learning has the potential to be considered as a fast tool for EM scattering computation.
登录
查看更多内容
影响因子：
5.7
作者：
Shao, Wenyi;Zhou, Beibei
通讯作者：
Zhou, Beibei
DOI：
10.1109/tmtt.2013.2255884
发表时间：
2013-05-01
影响因子：
4.3
作者：
Fear, E. C.;Bourqui, J.;Romano, C.
通讯作者：
Romano, C.
影响因子：
4.6
作者：
Sandfort, Veit;Yan, Ke;Summers, Ronald M.
通讯作者：
Summers, Ronald M.
影响因子：
10.6
作者：
Porter, Emily;Bahrami, Hadi;Popovic, Milica
通讯作者：
Popovic, Milica
影响因子：
5.7
作者：
Rubaek, Tonny;Kim, Oleksiy S.;Meincke, Peter
通讯作者：
Meincke, Peter