Electrical Impedance Tomography Image Reconstruction With Attention-Based Deep Convolutional Neural Network

Wang, Zichen; Zhang, Xinyu; Fu, Rong; Chen, Xiaoyan; Chen, Xiaoyan; Wang, Huaxiang

doi:10.1109/tim.2023.3265108

Cited by 15 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ren et al, used a large number of training samples to learn the regularized pattern coupling a two-branch residual model to achieve robust EIT shape reconstruction [45]. Wang et al used the Newton-Raphson iterative framework to construct a pre-reconstructor, built a model for encodingdecoding deep CNNs using dual V-Net for shape reconstruction and complex distributing recovery by incorporating dense connections [46] and a channel-coordinate attention [47]. Wang et al proposed an HIHU-Net to achieve high spatial resolution EIT imaging by improving the U-Net backbone with multi-scale spatial information fusion [48].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

HybridDenseU-Net: learning a multi-scale convolution and dense connectivity CNN for inverse imaging problems

Zhang,

Wang,

Chen

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Inverse imaging problems (IIPs) is a cutting-edge technology which is part of the nonlinear inverse problem, the solution approaches to which have placedattention on deep learning recently. This paper proposes a unique learning-based framework for IIPs, referred to as HybridDenseU-Net, which takes U-Net as the backbone and optimizes the encoder as a two-branch feature extraction module. Compared to the direct skip-connection in conventional U-Net, dense connections are introduced to merge features between feature maps with the same dimension and construct multi-scale content in the decoder. The validation of HybridDenseU-Net is carried out by a case study of electrical impedance tomography, which is of typical nonlinear IIP. The results illustrate that HybridDenseU-Net has root mean square error of 3.0867 and structural similarity of 0.9846, which are significantly better than some state-of-the-art deep learning-based frameworks. It has been proven that this work could provide a promising idea for future research on learning-based image reconstruction methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…where we set the λ 0 = 0.1, A is the Jacobian matrix which denotes the differentiation of the measured voltage on the conductivity [47].…”

Section: Datasetsmentioning

confidence: 99%

HybridDenseU-Net: learning a multi-scale convolution and dense connectivity CNN for inverse imaging problems

Zhang,

Wang,

Chen

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is the change in sample size used in 21 randomly selected papers on DL-ET in recent years [ 16 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ]. In Figure 1 , the size of each point represents the size of the sample set used in an article, while different colors are assigned to them for easy distinction.…”

Section: Introductionmentioning

confidence: 99%

Influence on Sample Determination for Deep Learning Electromagnetic Tomography

Zhao,

Liu

2024

Sensors

View full text Add to dashboard Cite

Deep learning (DL) has been frequently applied in the image reconstruction of electromagnetic tomography (EMT) in recent years. It offers the potential to achieve higher-quality image reconstruction. Among these, research on samples is relatively scarce. Samples are the cornerstone for both large and small models, which is easy to ignore. In this paper, a deep learning electromagnetic tomography (DL-EMT) model with nine elements is established. Complete simulation and experimental samples are obtained based on this model. On the sample sets, the reconstruction quality is observed by adjusting the size and configuration of the training set. The Mann–Whitney U test shows that beyond a certain point, the addition of more samples to the training data fed into the deep learning network does not result in an obvious improvement statistically in the quality of the reconstructed images. This paper proposes a CC-building method for optimizing a sample set. This method is based on the Pearson correlation coefficient calculation, aiming to establish a more effective sample base for DL-EMT image reconstruction. The statistical analysis shows that the CC-building method can significantly improve the image reconstruction effect in a small and moderate sample size. This method is also validated by experiments.

show abstract

“…Nonlinear methods are directly applicable to nonlinear EIT problems. In recent years, deep learning has been widely investigated in the EIT domain owing to its proficiency in solving nonlinear problems, which broadly falls into three categories [ 20 , 21 , 22 ]. The first uses an approximation from voltage of conductivity for image mapping [ 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Layered Fusion Reconstruction Based on Fuzzy Features for Multi-Conductivity Electrical Impedance Tomography

Wang,

Li,

Sun

2024

Sensors

View full text Add to dashboard Cite

In medical imaging, detecting tissue anomalies is vital for accurate diagnosis and effective treatment. Electrical impedance tomography (EIT) is a non-invasive technique that monitors the changes in electrical conductivity within tissues in real time. However, the current challenge lies in simply and accurately reconstructing multi-conductivity distributions. This paper introduces a layered fusion framework for EIT to enhance imaging in multi-conductivity scenarios. The method begins with pre-imaging and extracts the main object from the fuzzy image to form one layer. Then, the voltage difference in the other layer, where the local anomaly is located, is estimated. Finally, the corresponding conductivity distribution is established, and multiple layers are fused to reconstruct the multi-conductivity distribution. The simulation and experimental results demonstrate that compared to traditional methods, the proposed method significantly improves multi-conductivity separation, precise anomaly localization, and robustness without adding uncertain parameters. Notably, the proposed method has demonstrated exceptional accuracy in local anomaly detection, with positional errors as low as 1% and size errors as low as 33%, which significantly outperforms the traditional method with respective minimum errors of 9% and 228%. This method ensures a balance between the simplicity and accuracy of the algorithm. At the same time, it breaks the constraints of traditional linear methods, struggling to identify multi-conductivity distributions, thereby providing new perspectives for clinical EIT.

show abstract

Electrical Impedance Tomography Image Reconstruction With Attention-Based Deep Convolutional Neural Network

Cited by 15 publications

References 49 publications

HybridDenseU-Net: learning a multi-scale convolution and dense connectivity CNN for inverse imaging problems

HybridDenseU-Net: learning a multi-scale convolution and dense connectivity CNN for inverse imaging problems

Influence on Sample Determination for Deep Learning Electromagnetic Tomography

Layered Fusion Reconstruction Based on Fuzzy Features for Multi-Conductivity Electrical Impedance Tomography

Contact Info

Product

Resources

About