Hybrid Learning-Based Cell Aggregate Imaging With Miniature Electrical Impedance Tomography

Chen, Zhou; Yang, Yunjie; Bagnaninchi, Pierre O.

doi:10.1109/tim.2020.3035384

Cited by 24 publications

(26 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input vector first goes through the mask generator, which generates a binary mask to distinguish objects from the background. Following the work in [23], we use FC-UNet, a cascade of a fully connected layer and a UNet [19] to learn the mapping from boundary voltage measurement to a binary mask. A sigmoid activation function is selected as the last layer of FC-UNet to constrain all values within the range [0,1].…”

Section: Sadb-net For Eit Image Reconstructionmentioning

confidence: 99%

“…To train the FC-UNet as mask generator, the optimization setup is exactly the same as that in previous work [23]. For the rest of the SADB-Net, we use Adam [32] with a batch size of 25 and a base learning rate of 0.0001, which is reduced by a factor of 0.1 with a step size of 25.…”

Section: B Network Trainingmentioning

confidence: 99%

“…The induced-current learning method (ICLM) [22] was further proposed to resemble the inverse scattering problem. Our previous work [23] found the structure of target objects could be accurately estimated in the form of binary masks and facilitate distinguishing the conductivity contrast of multiple targets. However, the conductivity value still could not be precisely estimated due to the error introduced by the linearized EIT model.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, targeting at high-quality cell culture imaging, we propose a regression deep learning model to predict accurately both the geometric structure and conductivity value of multi-object, multi-level conductivity distributions. Inspired by multi-modal learning for activity and context recognition [24] and our previous work in [23], we develop a Structure-Aware Dual-Branch Network (SADB-Net) for EIT image reconstruction. The SADB-Net consists of two branches to learn respectively the structural and conductivity representations in the first place.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Chen

Yang

2021

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

Impedance Tomography (EIT) is an emerging imaging modality to monitor 3D cell culture dynamics through reconstructing the electrical properties of cell clusters.lectrical Impedance Tomography (EIT) is an emerging imaging modality to monitor 3D cell culture dynamics through reconstructing the electrical properties of cell clusters.E Recently, Machine Learning (ML) based approaches have achieved significant gains for the image reconstruction of EIT against conventional physical model based methods. However, continuous, multi-level conductivity distributions, which commonly exists in cell culture imaging, are more rigorous to reconstruct and remains challenging. This paper aims to tackle this challenge by proposing a structure-aware dual-branch deep learning method to predict both structure distribution and conductivity values. The proposed network comprises two independent branches to encode respectively the structure and conductivity features. The two branches are jointed later to make final predictions of conductivity distributions. Numerical and experimental evaluation results demonstrate the superior performance of the proposed method in dealing with the multi-level, continuous conductivity reconstruction problem.

show abstract

Section: Sadb-net For Eit Image Reconstructionmentioning

confidence: 99%

Section: B Network Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Chen

Yang

2021

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Electrical impedance tomography (EIT) is a relatively new technique intended for imaging the electrical conductivity distribution within a human body [15][16][17][18]. EIT could provide variation of conductivity distribution for lung during the breathing process [19], [20].…”

Section: Take Down Policymentioning

confidence: 99%

Exploring Respiratory Motion Tracking Through Electrical Impedance Tomography

Wang

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Motion tracking is an effective approach for the management of respiratory motion during the medical imaging process, which has always been a major concern in diagnostic imaging, interventional, and non-invasive therapy. However, the low imaging speed of traditional medical imaging techniques limits the practical application of real-time motion tracking. Electrical impedance tomography (EIT) is proved to be an effective tool for continuous monitoring of lung activity/status. However, the respiratory motion has never been studied in the medical EIT field before. In this paper, preliminary research of lung movement during the respiratory process is first studied based on EIT. Multi-ring electrode thorax models under different respiratory statuses were constructed to obtain simulation data of EIT. A modified TV algorithm is used for the estimation of lung volume and movement based on 3D EIT images, which improve the quality of reconstruction by approximately 30% and 20% compared with the traditional Tikhonov method and the total variation (TV) method, respectively. Both simulations and experiments were conducted to show the potential of respiratory motion tracking through 3D EIT reconstruction.

show abstract

TSS-ConvNet for electrical impedance tomography image reconstruction

Ameen,

Sack,

Pöschel

2024

Physiol. Meas.

View full text Add to dashboard Cite

In this paper, we present a novel data-driven approach for solving ill-posed inverse problems, such as Electrical Impedance Tomography (EIT). Our approach introduces a new layer architecture composed of three paths: spatial, spectral, and truncated spectral paths. The spatial path processes information locally, while the spectral and truncated spectral paths provide the network with a global receptive field. Such architecture helps eliminate the ill-posedness and nonlinearity of the inverse problem. The three paths are interconnected, allowing for information exchange on different receptive fields with different learning abilities. The network has a bottleneck architecture which enables it to recover signal information from noisy redundant measurements. We call our proposed model Truncated Spatial-Spectral Convolutional neural Network (TSSConvNet). The model overcomes the receptive field limitation of the most existing models which use only the local information in Euclidean space. We trained the network on a large dataset that covers various configurations with random parameters to ensure generalization over the training samples. Our model achieves superior accuracy with relatively high resolution on both simulation and experimental data.

show abstract

Hybrid Learning-Based Cell Aggregate Imaging With Miniature Electrical Impedance Tomography

Cited by 24 publications

References 38 publications

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Structure-Aware Dual-Branch Network for Electrical Impedance Tomography in Cell Culture Imaging

Exploring Respiratory Motion Tracking Through Electrical Impedance Tomography

TSS-ConvNet for electrical impedance tomography image reconstruction

Contact Info

Product

Resources

About