arXiv subjects

Yunjie Yang

Publications and source records attributed to Yunjie Yang.

28 records · Page 2Linked to original sources

arXiv2023

Regularized Shallow Image Prior for Electrical Impedance Tomography

Untrained Neural Network Prior (UNNP) based algorithms have gained increasing popularity in tomographic imaging, as they offer superior performance compared to hand-crafted priors and do not require training. UNNP-based methods usually rely on deep architectures which are known for their excellent feature extraction ability compared to shallow ones. Contrary to common UNNP-based approaches, we propose a regularized shallow image prior method that combines UNNP with hand-crafted prior for Electrical Impedance Tomography (EIT). Our approach employs a 3-layer Multi-Layer Perceptron (MLP) as the UNNP in regularizing 2D and 3D EIT inversion. We demonstrate the influence of two typical hand-crafted regularizations when representing the conductivity distribution with shallow MLPs. We show considerably improved EIT image quality compared to conventional regularization algorithms, especially in structure preservation. The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.

eess.IV↗

arXiv2022

A Learning-Based 3D EIT Image Reconstruction Method

Deep learning has been widely employed to solve the Electrical Impedance Tomography (EIT) image reconstruction problem. Most existing physical model-based and learning-based approaches focus on 2D EIT image reconstruction. However, when they are directly extended to the 3D domain, the reconstruction performance in terms of image quality and noise robustness is hardly guaranteed mainly due to the significant increase in dimensionality. This paper presents a learning-based approach for 3D EIT image reconstruction, which is named Transposed convolution with Neurons Network (TN-Net). Simulation and experimental results show the superior performance and generalization ability of TN-Net compared with prevailing 3D EIT image reconstruction algorithms.

eess.IV↗

arXiv2021

Digital Twin of Electrical Tomography for Quantitative Multiphase Flow Imaging

We report a digital twin (DT) framework of electrical tomography (ET) to address the challenge of real-time quantitative multiphase flow imaging based on non-invasive and non-radioactive technologies. Multiphase flow is ubiquitous in nature, industry, and research. Accurate flow imaging is the key to understanding this complex phenomenon. Existing non-radioactive multiphase flow imaging methods based on electrical tomography are limited to providing qualitative images. The proposed DT framework, building upon a synergistic integration of 3D field coupling simulation, model-based deep learning, and edge computing, allows ET to dynamically learn the flow features in the virtual space and implement the model in the physical system, thus providing unprecedented resolution and accuracy. The DT framework is demonstrated on gas-liquid two-phase flow and electrical capacitance tomography (ECT). It can be readily extended to various tomography modalities, scenarios, and scales in biomedical, energy, and aerospace applications as an effective alternative to radioactive solutions for precise flow visualization and characterization.

physics.flu-dyn↗

arXiv2021

Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion

While Electrical Impedance Tomography (EIT) has found many biomedicine applications, a better resolution is needed to provide quantitative analysis for tissue engineering and regenerative medicine. This paper proposes an impedance-optical dual-modal imaging framework, which is mainly aimed at high-quality 3D cell culture imaging and can be extended to other tissue engineering applications. The framework comprises three components, i.e., an impedance-optical dual-modal sensor, the guidance image processing algorithm, and a deep learning model named multi-scale feature cross fusion network (MSFCF-Net) for information fusion. The MSFCF-Net has two inputs, i.e., the EIT measurement and a binary mask image generated by the guidance image processing algorithm, whose input is an RGB microscopic image. The network then effectively fuses the information from the two different imaging modalities and generates the final conductivity image. We assess the performance of the proposed dual-modal framework by numerical simulation and MCF-7 cell imaging experiments. The results show that the proposed method could significantly improve image quality, indicating that impedance-optical joint imaging has the potential to reveal the structural and functional information of tissue-level targets simultaneously.

eess.IV↗

arXiv2021

MMV-Net: A Multiple Measurement Vector Network for Multi-frequency Electrical Impedance Tomography

Multi-frequency Electrical Impedance Tomography (mfEIT) is an emerging biomedical imaging modality to reveal frequency-dependent conductivity distributions in biomedical applications. Conventional model-based image reconstruction methods suffer from low spatial resolution, unconstrained frequency correlation and high computational cost. Deep learning has been extensively applied in solving the EIT inverse problem in biomedical and industrial process imaging. However, most existing learning-based approaches deal with the single-frequency setup, which is inefficient and ineffective when extended to address the multi-frequency setup. In this paper, we present a Multiple Measurement Vector (MMV) model based learning algorithm named MMV-Net to solve the mfEIT image reconstruction problem. MMV-Net takes into account the correlations between mfEIT images and unfolds the update steps of the Alternating Direction Method of Multipliers (ADMM) for the MMV problem. The non-linear shrinkage operator associated with the weighted l2_1 regularization term is generalized with a cascade of a Spatial Self-Attention module and a Convolutional Long Short-Term Memory (ConvLSTM) module to capture intra- and inter-frequency dependencies. The proposed MMVNet was validated on our Edinburgh mfEIT Dataset and a series of comprehensive experiments. All reconstructed results show superior image quality, convergence performance and noise robustness against the state of the art.

eess.IV↗

arXiv2021

Flow Regime Transition in Countercurrent Packed Column Monitored by ECT

Vertical packed columns are widely used in absorption, stripping and distillation processes. Flooding will occur in the vertical packed columns as a result of excessive liquid accumulation, which reduces mass transfer efficiency and causes a large pressure drop. Pressure drop measurements are typically used as the hydrodynamic parameter for predicting flooding. They are, however, only indicative of the occurrence of transition of the flow regime across the packed column. They offer limited spatial information to mass transfer packed column operators and designers. In this work, a new method using Electrical Capacitance Tomography (ECT) is implemented for the first time so that real-time flow regime monitoring at different vertical positions is achieved in a countercurrent packed bed column using ECT. Two normalisation methods are implemented to monitor the transition from pre-loading to flooding in a column of 200 mm diameter, 1200 mm height filled with plastic structured packing. Liquid distribution in the column can be qualitatively visualised via reconstructed ECT images. A flooding index is implemented to quantitatively indicate the progression of local flooding. In experiments, the degree of local flooding is quantified at various gas flow rates and locations of ECT sensor. ECT images were compared with pressure drop and visual observation. The experimental results demonstrate that ECT is capable of monitoring liquid distribution, identifying flow regime transitions and predicting local flooding.

physics.flu-dyn↗

arXiv2021

FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging

Inverse problems are essential to imaging applications. In this paper, we propose a model-based deep learning network, named FISTA-Net, by combining the merits of interpretability and generality of the model-based Fast Iterative Shrinkage/Thresholding Algorithm (FISTA) and strong regularization and tuning-free advantages of the data-driven neural network. By unfolding the FISTA into a deep network, the architecture of FISTA-Net consists of multiple gradient descent, proximal mapping, and momentum modules in cascade. Different from FISTA, the gradient matrix in FISTA-Net can be updated during iteration and a proximal operator network is developed for nonlinear thresholding which can be learned through end-to-end training. Key parameters of FISTA-Net including the gradient step size, thresholding value and momentum scalar are tuning-free and learned from training data rather than hand-crafted. We further impose positive and monotonous constraints on these parameters to ensure they converge properly. The experimental results, evaluated both visually and quantitatively, show that the FISTA-Net can optimize parameters for different imaging tasks, i.e. Electromagnetic Tomography (EMT) and X-ray Computational Tomography (X-ray CT). It outperforms the state-of-the-art model-based and deep learning methods and exhibits good generalization ability over other competitive learning-based approaches under different noise levels.

eess.IV↗

arXiv2020

Multi-frequency Electromagnetic Tomography for Acute Stroke Detection Using Frequency Constrained Sparse Bayesian Learning

Imaging the bio-impedance distribution of the brain can provide initial diagnosis of acute stroke. This paper presents a compact and non-radiative tomographic modality, i.e. multi-frequency Electromagnetic Tomography (mfEMT), for the initial diagnosis of acute stroke. The mfEMT system consists of 12 channels of gradiometer coils with adjustable sensitivity and excitation frequency. To solve the image reconstruction problem of mfEMT, we propose an enhanced Frequency-Constrained Sparse Bayesian Learning (FC-SBL) to simultaneously reconstruct the conductivity distribution at all frequencies. Based on the Multiple Measurement Vector (MMV) model in the Sparse Bayesian Learning (SBL) framework, FC-SBL can recover the underlying distribution pattern of conductivity among multiple images by exploiting the frequency constraint information. A realistic 3D head model was established to simulate stroke detection scenarios, showing the capability of mfEMT to penetrate the highly resistive skull and improved image quality with FC-SBL. Both simulations and experiments showed that the proposed FC-SBL method is robust to noisy data for image reconstruction problems of mfEMT compared to the single measurement vector model, which is promising to detect acute strokes in the brain region with enhanced spatial resolution and in a baseline-free manner.

physics.app-ph↗

arXiv2020

Image Reconstruction for Multi-frequency Electromagnetic Tomography based on Multiple Measurement Vector Model

Imaging the bio-impedance distribution of a biological sample can provide understandings about the sample's electrical properties which is an important indicator of physiological status. This paper presents a multi-frequency electromagnetic tomography (mfEMT) technique for biomedical imaging. The system consists of 8 channels of gradiometer coils with adjustable sensitivity and excitation frequency. To exploit the frequency correlation among each measurement, we reconstruct multiple frequency data simultaneously based on the Multiple Measurement Vector (MMV) model. The MMV problem is solved by using a sparse Bayesian learning method that is especially effective for sparse distribution. Both simulations and experiments have been conducted to verify the performance of the method. Results show that by taking advantage of multiple measurements, the proposed method is more robust to noisy data for ill-posed problems compared to the commonly used single measurement vector model.

physics.app-ph↗

arXiv2017

Event generator tuning using Bayesian optimization

Monte Carlo event generators contain a large number of parameters that must be determined by comparing the output of the generator with experimental data. Generating enough events with a fixed set of parameter values to enable making such a comparison is extremely CPU intensive, which prohibits performing a simple brute-force grid-based tuning of the parameters. Bayesian optimization is a powerful method designed for such black-box tuning applications. In this article, we show that Monte Carlo event generator parameters can be accurately obtained using Bayesian optimization and minimal expert-level physics knowledge. A tune of the PYTHIA 8 event generator using $e^+e^-$ events, where 20 parameters are optimized, can be run on a modern laptop in just two days. Combining the Bayesian optimization approach with expert knowledge should enable producing better tunes in the future, by making it faster and easier to study discrepancies between Monte Carlo and experimental data.

physics.data-an↗