Traditional Reconstruction Algorithms Research Articles

Stability of the isotropic conductivity reconstruction using magnetic resonance electrical impedance tomography (MREIT)

Magnetic resonance electrical impedance tomography (MREIT) is a high-resolution imaging modality that aims to reconstruct the objects’ conductivity distributions at low frequency using the measurable z-component of the magnetic flux density obtained from an MRI scanner. Traditional reconstruction algorithms in MREIT use two datum subject to two linearly independent current densities. However, the temporal resolution of such a MREIT image is relatively low. Recently, a single current harmonic Bz algorithm has been proposed to improve the temporal resolution. Even though a series of reconstruction algorithms have been proposed in the last two decades, the theoretical studies of MREIT are still quite limited. This paper presents the stability theorems for two datum and a single data-based isotropic conductivity reconstruction using MREIT. Using the regularity theory of elliptic partial differential equations, we prove that the only instability in the inverse problem of MREIT comes from taking the second-order derivative of the measured data Bz , the z-component of the magnetic flux density. To get a stable reconstruction from the noisy Bz data, we note that the edge structure of ∇Bz reveals the edge features in the unknown conductivity and provides an edge-preserving denoising approach for the ∇Bz data. We use a modified Shepp–Logan phantom model to validate the proposed theory and the denoising approach.

An effective point cloud registration method for three-dimensional reconstruction of pressure piping

Abstract At present, industrial scenes with sparse features and weak textures are widely encountered, and the three-dimensional reconstruction of such scenes is a recognized problem. Pressure pipelines have a wide range of applications in fields such as petroleum engineering, chemical engineering, and hydropower station engineering. However, there is no mature solution for the three-dimensional reconstruction of pressure pipes. The main reason is that the typical scenes in which pressure pipes are found also have relatively few features and textures. Traditional three-dimensional reconstruction algorithms based on feature extraction are largely ineffective for such scenes that are lacking in features. In view of the above problems, this paper proposes an improved interframe registration algorithm based on point cloud fitting with cylinder axis vector constraints. By incorporating geometric feature parameters of a cylindrical pressure pipeline, specifically the axis vector of the cylinder, to constrain the traditional iterative closest point algorithm, the accuracy of point cloud registration can be improved in scenarios lacking features and textures, and some environmental uncertainties can be overcome. Finally, using actual laser point cloud data collected from pressure pipelines, the proposed fitting-based point cloud registration algorithm with cylinder axis vector constraints is tested. The experimental results show that under the same conditions, compared with other open-source point cloud registration algorithms, the proposed method can achieve higher registration accuracy. Moreover, integrating this algorithm into an open-source three-dimensional reconstruction algorithm framework can lead to better reconstruction results.

Adaptive coded phase mask design and high-quality image reconstruction for interference-less coded aperture correlation holography.

The interference-less coded aperture correlation holography is a non-scanning, motionless, and incoherent technique for imaging three-dimensional objects without two-wave interference. Nevertheless, a challenge lies in that the coded phase mask encodes the system noise, while traditional reconstruction algorithms often introduce unwanted surplus background components during reconstruction. A deep learning-based method is proposed to mitigate system noise and background components simultaneously. Specifically, this method involves two sub-networks: a coded phase mask design sub-network and an image reconstruction sub-network. The former leverages the object's frequency distribution to generate an adaptive coded phase mask that encodes the object wave-front precisely without being affected by the superfluous system noise. The latter establishes a mapping between the autocorrelations of the hologram and the object, effectively suppresses the background components by embedding a prior physical knowledge and improves the neural network's adaptability and interpretability. Experimental results demonstrate the effectiveness of the proposed method in suppressing system noise and background components, thereby significantly improving the signal-to-noise ratio of the reconstructed images.

Retrieval of chromophore concentration changes in a digital human head model using analytical mean partial pathlengths of photons.

Continuous-wave functional near-infrared spectroscopy has proved to be a valuable tool for assessing hemodynamic activity in the human brain in a non-invasively and inexpensive way. However, most of the current processing/analysis methods assume the head is a homogeneous medium, and hence do not appropriately correct for the signal coming from the scalp. This effect can be reduced by considering light propagation in a layered model of the human head, being the Monte Carlo (MC) simulations the gold standard to this end. However, this implies large computation times and demanding hardware capabilities. In this work, we study the feasibility of replacing the homogeneous model and the MC simulations by means of analytical multilayered models, combining in this way, the speed and simplicity of implementation of the former with the robustness and accuracy of the latter. Oxy- and deoxyhemoglobin (HbO and HbR, respectively) concentration changes were proposed in two different layers of a magnetic resonance imaging (MRI)-based meshed model of the human head, and then these changes were retrieved by means of (i)a typical homogeneous reconstruction and (ii)a theoretical layered reconstruction. Results suggest that the use of analytical models of light propagation in layered models outperforms the results obtained using traditional homogeneous reconstruction algorithms, providing much more accurate results for both, the extra- and the cerebral tissues. We also compare the analytical layered reconstruction with MC-based reconstructions, achieving similar degrees of accuracy, especially in the gray matter layer, but much faster (between 4 and 5 orders of magnitude). We have successfully developed, implemented, and validated a method for retrieving chromophore concentration changes in the human brain, combining the simplicity and speed of the traditional homogeneous reconstruction algorithms with robustness and accuracy much more similar to those provided by MC simulations.

Online defect detection on metallic plates using electromagnetic tomography

Metallic samples are widely applied in modern industrial production. Due to non-uniformities in the stress load, such samples may become damaged and produce defects, which can cause unnecessary economic losses. In this paper, an online defect detection method is proposed for the quality monitoring of metallic plates. The research involves the design and optimisation of an electromagnetic tomography (EMT) sensor and the development of a fast tomography algorithm. Specifically, a planar array eddy current sensor is designed for in-situ structural health monitoring of metallic specimens. The parameters of the sensor are optimised using an orthogonal methodology and a response surface methodology to improve the uniformity of the sensitivity field. In addition, a second-order iterative Bregman reconstruction algorithm is investigated to reconstruct the defect image, which can improve the reconstruction speed for this ill-posed problem. Simulation and experimental results indicate that the proposed method can be applied to effectively evaluate the locations and sizes of defects in metallic specimens. The correlation coefficients of the reconstructed images using the proposed method are larger than 0.8. Compared with traditional reconstruction algorithms, the method proposed in this paper shows fast convergence speed and smaller estimation errors.

A novel interpolation-MLP coupled reconstruction method for turbulent natural convection thermal environment reconstruction of MW-class offshore wind turbine nacelles

Localized overheating in the nacelle due to heat loss in high-power offshore wind turbines of 10 MW or more, where localized overheating affects the operation of other components, it is particularly important to visualize the thermal environment in the nacelle accurately and in real time in order to control the start-up and shutdown of cooling methods. However, the complexity of the high turbulence intensity (Rayleigh number (Ra) > 109) thermal environment in the nacelle of high-power units leads to significant errors in existing visualization techniques. Therefore, this paper presents a novel coupled interpolation-MLP reconstruction technique based on a data-driven deep neural network. Based on the interpolation method as primary reconstruction, a secondary reconstruction neural network model is obtained by training the thermal environment parameters (static pressure P, tangential velocity U, normal velocity V and temperature T) of specific computing nodes in the nacelle. The model is used to predict the values of thermal environment parameters at each time point for computing nodes with large gradients. An improved PSO algorithm is used to arrange the positions of a defined number of sensors to save sensor resources during the measurement process and to and ensure computing stability. The above improvements to the traditional interpolation reconstruction algorithms have led to an increase in the accuracy of the thermal environment reconstruction.

A temporal Convolutional Network for EMG compressed sensing reconstruction

Electromyography (EMG) plays a vital role in detecting medical abnormalities and analyzing the biomechanics of human or animal movements. However, long-term EMG signal monitoring will increase the bandwidth requirements and transmission system burden. Compressed sensing (CS) is attractive for resource-limited EMG signal monitoring. However, traditional CS reconstruction algorithms require prior knowledge of the signal, and the reconstruction process is inefficient. To solve this problem, this paper proposed a reconstruction algorithm based on deep learning, which combines the Temporal Convolutional Network (TCN) and the fully connected layer to learn the mapping relationship between the compressed measurement value and the original signal, and it has been verified in the Ninapro database. The results show that, for the same subject, compared with the traditional reconstruction algorithms orthogonal matching pursuit (OMP), basis pursuit (BP), and Modified Compressive Sampling Matching Pursuit (MCo), the reconstruction quality and efficiency of the proposed method is significantly improved under various compression ratios (CR).

Damage detection of CFRP laminates based on Adamax-INN model for EIT

Carbon fiber reinforced polymer (CFRP) is electrically conductive, making it possible to detect structural damage of CFRP laminates with electrical impedance tomography (EIT). However, the inverse problem of EIT is severely non-linear, ill-posed, and underdetermined, thus limiting the resolution and accuracy of images reconstructed with EIT. This paper solves the inverse problem of EIT based on invertible neural networks (INN) and optimizes INN with Adamax gradient descent algorithm. Simulation and experimental results demonstrated that, compared with traditional EIT image reconstruction algorithms and radial basis function (RBF) neural network algorithm, the Adamax-INN model largely reduced the artifacts in reconstructed images, improved the damage recognition accuracy and edge clarity, and displayed good noise immunity.

A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning

Microstructural analyses of porous media have considerable research value when studying of macroscopic properties,and the accurate reconstruction of a digital microstructure model is an important component of this research. Computational reconstruction algorithms for microstructures have attracted much attention due to their low cost and excellent performance. However, achieving faster and more efficient reconstruction remains a challenge for computational reconstruction algorithms. The bottleneck lies in the computational reconstruction algorithms themselves, which are either too slow (traditional reconstruction algorithms) or not flexible to the training process (deep learning reconstruction algorithms). To address these limitations, we propose a fast and flexible deep learning algorithm using a neural network based on an improved simulated annealing framework (ISAF-NN). The proposed algorithm adopts structural information of the reference image to guide the network design, and uses the description function to extract feature distribution of the reference image as the objective function to complete the network optimization. Benefit from the network structure is simple and flexible, the proposed algorithm can complete training and reconstruction in a short time. By adjusting the input size, the algorithm can also achieve arbitrary sized reconstruction. The proposed algorithm is experimentally applied to several materials to verify its effectiveness and generalizability.

Compressed sensing framework for BCG signals based on the optical fiber sensor.

A compressed sensing (CS) framework is built for ballistocardiography (BCG) signals, which contains two parts of an optical fiber sensor-based heart monitoring system with a CS module and an end-to-end deep learning-based reconstruction algorithm. The heart monitoring system collects BCG data, and then compresses and transmits the data through the CS module at the sensing end. The deep learning-based algorithm reconstructs compressed data at the received end. To evaluate results, three traditional CS reconstruction algorithms and a deep learning method are adopted as references to reconstruct the compressed BCG data with different compression ratios (CRs). Results show that our framework can reconstruct signals successfully when the CR grows from 50% to 95% and outperforms other methods at high CRs. The mean absolute error (MAE) of the estimated heartbeat rate (HR) is lower than 1 bpm when the CR is below 95%. The proposed CS framework for BCG signals can be integrated into the IoMT system, which has great potential in health care for both medical and home use.

End-to-end Wiener–CNN optimization for lensless extended depth of field imaging with phase mask

Extended depth of field (EDoF) has been widely studied in recent years and has many applications in various imaging tasks. Currently, the EDoF imaging system is independently based on either traditional reconstruction algorithms or deep learning. Traditional algorithms, on the other hand, cannot always achieve high image quality or large depth-of-field (DoF) due to their limited model fitting ability, whereas deep learning networks always suffer from low robustness to fabrication errors. In this work, we propose a compact lensless system for EDoF that combines these two methods. First, we build an end-to-end framework based on Wiener deconvolution to optimize the imaging model. On this basis, we develop an end-to-end denoising network based on a convolutional neural network (CNN) and train it to improve the quality of the reconstructed images. The proposed system achieves superior EDoF imaging performance in image quality compared to other lensless systems. Additionally, the proposed system is demonstrated to have high robustness against sensor noise, fabrication errors and quantization errors.

Pipeline visualization based on RIR-RepVGG network

Electrical Capacitance Tomography (ECT) is a process tomography technology based on capacitance-sensitive field, which is of vital importance to accelerate the development of industrial intelligence by measuring the required capacitance data through sensors to achieve the flow pattern detection of filled pipes and thus meet the controllability of pipe flow patterns. The traditional ECT flow pattern recognition method has low recognition rate and more complicated operation. In this paper, the detection method of filling pipeline is studied based on electrical capacitance tomography (ECT) technology. Aiming at the low imaging accuracy of traditional ECT reconstruction algorithms, an ECT image reconstruction method based on improved residual neural network was proposed. The RIR-RepVGG residual network structure is proposed and a nonlinear mapping network is designed. The improved residual network is used to establish the mapping relationship between the capacitance vector and the two-phase flow image. Through the static study by filling pipeline simulation experiments and static experiments, it is proved that the ECT image reconstruction method proposed in this paper can reduce the artifacts and deformation of the reconstructed image, improve the reconstruction accuracy, and has a better reconstruction effect for complex flow patterns. Application is of great significance.

Comparative assessment for pressure field reconstruction based on physics-informed neural network

In this paper, a physics-informed neural network (PINN) is used to determine pressure fields from the experimentally measured velocity data. As a novel method of data assimilation, PINN can simultaneously optimize velocity and solve pressure by embedding the Navier–Stokes equations into the loss function. The PINN method is compared with two traditional pressure reconstruction algorithms, i.e., spectral decomposition-based fast pressure integration and irrotation correction on pressure gradient and orthogonal-path integration, and its performance is numerically assessed using two kinds of flow motions, namely, Taylor's decaying vortices and forced isotropic turbulence. In the case of two-dimensional decaying vortices, critical parameters of PINN have been investigated with and without considering measurement errors. Regarding the forced isotropic turbulence, the influence of spatial resolution and out-of-plane motion on pressure reconstruction is assessed. Finally, in an experimental case of a synthetic jet impinging on a solid wall, the PINN is used to determine the pressure from the velocity fields obtained by the planar particle image velocimetry. All results show that the PINN-based pressure reconstruction is superior to other methods even if the velocity fields are significantly contaminated by the measurement errors.

Effective cosmic density field reconstruction with convolutional neural network

ABSTRACT We present a cosmic density field reconstruction method that augments the traditional reconstruction algorithms with a convolutional neural network (CNN). Following previous work, the key component of our method is to use the reconstructed density field as the input to the neural network. We extend this previous work by exploring how the performance of these reconstruction ideas depends on the input reconstruction algorithm, the reconstruction parameters, and the shot noise of the density field, as well as the robustness of the method. We build an eight-layer CNN and train the network with reconstructed density fields computed from the Quijote suite of simulations. The reconstructed density fields are generated by both the standard algorithm and a new iterative algorithm. In real space at z = 0, we find that the reconstructed field is 90 per cent correlated with the true initial density out to $k\sim 0.5 \, \mathrm{ h}\, \rm {Mpc}^{-1}$, a significant improvement over $k\sim 0.2 \, \mathrm{ h}\, \rm {Mpc}^{-1}$ achieved by the input reconstruction algorithms. We find similar improvements in redshift space, including an improved removal of redshift space distortions at small scales. We also find that the method is robust across changes in cosmology. Additionally, the CNN removes much of the variance from the choice of different reconstruction algorithms and reconstruction parameters. However, the effectiveness decreases with increasing shot noise, suggesting that such an approach is best suited to high density samples. This work highlights the additional information in the density field beyond linear scales as well as the power of complementing traditional analysis approaches with machine learning techniques.

Improved Double Regression Nonlinear Image Super Resolution Model

Abstract The existing super resolution reconstruction methods are mainly divided into traditional super resolution reconstruction and deep learning super resolution reconstruction. The main problem faced by traditional super resolution reconstruction algorithms, such as image enlargement and space transformation, is how to establish the mapping relationship between the input image and the target image, and express the pixel value of the target image through the mapping relationship. As a prominent problem, the difficulty of super resolution reconstruction lies in the fact that there is no realizable matrix relationship between one - to - many mapping relationships. Based on the U-Net network framework, this paper improves the jump-connected modules. By using the combination of convolutional layer, activation layer and residual channel block, the overall module operation efficiency is increased by 2.4%, the overall PNSR is increased by 0.49db, and the running speed is increased by 0.3ms on average when processing a single image compared with other classical models.

Complete Global Total Electron Content Map Dataset based on a Video Imputation Algorithm VISTA

Ionospheric total electron content (TEC) derived from multi-frequency Global Navigation Satellite System (GNSS) signals and the relevant products have become one of the most utilized parameters in the space weather and ionospheric research community. However, there are a couple of challenges in using the global TEC map data including large data gaps over oceans and the potential of losing meso-scale ionospheric structures when applying traditional reconstruction and smoothing algorithms. In this paper, we describe and release a global TEC map database, constructed and completed based on the Madrigal TEC database with a novel video imputation algorithm called VISTA (Video Imputation with SoftImpute, Temporal smoothing and Auxiliary data). The complete TEC maps reveal important large-scale TEC structures and preserve the observed meso-scale structures. Basic ideas and the pipeline of the video imputation algorithm are introduced briefly, followed by discussions on the computational costs and fine tuning of the adopted algorithm. Discussions on potential usages of the complete TEC database are given, together with a concrete example of applying this database.

High-throughput single-molecule localization microscopy: Potential clinical applications.

High-throughput single-molecule localization microscopy: Potential clinical applications.

Comparative Analysis the Super-Resolution Image Generation Performance Based on BigGAN and VQ-VAE-2

Super-resolution image reconstruction has always been a popular research direction in the field of computer vision, which aims to recover high-resolution clear images from low-resolution images. Traditional super-resolution reconstruction algorithms mainly rely on the construction of constraints and the accuracy of registration between images to achieve the reconstruction effect, but their accuracy cannot meet the needs of practical applications with large multiples. Thanks to the rapid development of deep learning field, super-resolution image reconstruction based on deep learning has become the mainstream, and has achieved great success in reconstruction accuracy and speed. According to the different generative models used, the existing super-resolution image reconstruction methods mainly include two categories: GAN-based and VAEs-based. To quantitatively compare the limits of the two approaches' performance, this study selects two representative algorithms, BigGAN and VQ-VAE-2, and introduces the theoretical details and training process of these two methods, respectively. Furthermore, the reconstruction results of BigGAN and VQ-VAE-2 are further compared. Finally, this paper discusses the future development trend of super-resolution picture reconstruction with the current potential problems of BigGAN and VQ-VAE-2.

FBP‐CNN: A Direct PET Image Reconstruction Network for Flow Visualization

AbstractDynamic positron emission tomography (PET) imaging has the potential to address technical challenges that persist in the visualization of optically inaccessible flow fields in integrated systems. However, traditional reconstruction algorithms are unable to reconstruct high‐quality images from dynamic scan data. In this paper, a neural network structure that can reconstruct high‐quality images directly using sinograms as input by combining the filtered back‐projection (FBP) algorithm and denoising convolutional neural network (CNN) is proposed, which is named FBP‐CNN. Computational fluid dynamics (CFD) software and the Monte Carlo simulation platform are used jointly to generate a dataset for the flow around the bluff body problem. The dataset is then used to train, validate, and test the FBP‐CNN network, and the network after completing training is used to reconstruct the real projection data. The results show that FBP‐CNN can reconstruct high‐quality images from both simulated datasets and real projection data.

Machine Learning Diffuse Optical Tomography Using Extreme Gradient Boosting and Genetic Programming.

Diffuse optical tomography (DOT) is a non-invasive method for detecting breast cancer; however, it struggles to produce high-quality images due to the complexity of scattered light and the limitations of traditional image reconstruction algorithms. These algorithms can be affected by boundary conditions and have a low imaging accuracy, a shallow imaging depth, a long computation time, and a high signal-to-noise ratio. However, machine learning can potentially improve the performance of DOT by being better equipped to solve inverse problems, perform regression, classify medical images, and reconstruct biomedical images. In this study, we utilized a machine learning model called "XGBoost" to detect tumors in inhomogeneous breasts and applied a post-processing technique based on genetic programming to improve accuracy. The proposed algorithm was tested using simulated DOT measurements from complex inhomogeneous breasts and evaluated using the cosine similarity metrics and root mean square error loss. The results showed that the use of XGBoost and genetic programming in DOT could lead to more accurate and non-invasive detection of tumors in inhomogeneous breasts compared to traditional methods, with the reconstructed breasts having an average cosine similarity of more than 0.97 ± 0.07 and average root mean square error of around 0.1270 ± 0.0031 compared to the ground truth.