期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 37, 期 10, 页码 2367-2377出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2018.2828303
关键词
Electrical impedance tomography; D-bar methods; deep learning; conductivity imaging
类别
资金
- NVIDIA Corporation
- Isaac Newton Institute for Mathematical Sciences, Cambridge
- EPSRC [EP/K032208/1, EP/R014604/1, EP/M020533/1] Funding Source: UKRI
The mathematical problem for electrical impedance tomography (EIT) is a highly nonlinear ill-posed inverse problem requiring carefully designed reconstruction procedures to ensure reliable image generation. D-bar methods are based on a rigorous mathematical analysis and provide robust direct reconstructions by using a lowpass filtering of the associated nonlinear Fourier data. Similarly to low-pass filtering of linear Fourier data, only using lowfrequencies in the image recoveryprocess results in blurred images lacking sharp features, such as clear organ boundaries. Convolutional neural networks provide a powerful framework for post-processing such convolved direct reconstructions. In this paper, we demonstrate that theseCNN techniques lead to sharp and reliable reconstructions even for the highly nonlinear inverse problem of EIT. The network is trained on data sets of simulated examples and then applied to experimental data without the need to performan additional transfer training. Results for absolute EIT images are presented using experimental EIT data from the ACT4 and KIT4 EIT systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据