Tomographic Image Reconstruction Research Articles

Unsupervised Domain Adaptation for Low-Dose CT Reconstruction via Bayesian Uncertainty Alignment.

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning (DL) is widely used in this problem, but the performance of testing data (also known as target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (also known as source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment (SDA) to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT (NDCT) images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance.

Randomized recursive techniques for image reconstruction in diffuse optical tomography

Randomized recursive techniques for image reconstruction in diffuse optical tomography

Convergent Regularization in Inverse Problems and Linear Plug-and-Play Denoisers

AbstractRegularization is necessary when solving inverse problems to ensure the well-posedness of the solution map. Additionally, it is desired that the chosen regularization strategy is convergent in the sense that the solution map converges to a solution of the noise-free operator equation. This provides an important guarantee that stable solutions can be computed for all noise levels and that solutions satisfy the operator equation in the limit of vanishing noise. In recent years, reconstructions in inverse problems are increasingly approached from a data-driven perspective. Despite empirical success, the majority of data-driven approaches do not provide a convergent regularization strategy. One such popular example is given by iterative plug-and-play (PnP) denoising using off-the-shelf image denoisers. These usually provide only convergence of the PnP iterates to a fixed point, under suitable regularity assumptions on the denoiser, rather than convergence of the method as a regularization technique, thatis under vanishing noise and regularization strength. This paper serves two purposes: first, we provide an overview of the classical regularization theory in inverse problems and survey a few notable recent data-driven methods that are provably convergent regularization schemes. We then continue to discuss PnP algorithms and their established convergence guarantees. Subsequently, we consider PnP algorithms with learned linear denoisers and propose a novel spectral filtering technique of the denoiser to control the strength of regularization. Further, by relating the implicit regularization of the denoiser to an explicit regularization functional, we are the first to rigorously show that PnP with a learned linear denoiser leads to a convergent regularization scheme. The theoretical analysis is corroborated by numerical experiments for the classical inverse problem of tomographic image reconstruction.

Enhanced PET image reconstruction utilizing morphological filtering and MLEM algorithm

Positron Emission Tomography (PET) image reconstruction remains a pivotal area in PET technology, critically influencing clinical diagnostic outcomes. Addressing the need for enhanced image quality, this study introduces a novel algorithm for PET image reconstruction. This algorithm integrates a penalty mechanism, morphological filtering, and the Maximum Likelihood Expectation Maximization (MLEM) algorithm, aiming to improve reconstructed image quality significantly. The operational process of the algorithm within each iteration encompasses two primary phases. Initially, image reconstruction is accomplished via the MLEM algorithm, followed by the application of a morphological filter to attenuate noise in the reconstructed image. Simulation experiments demonstrate that this algorithm effectively mitigates noise while preserving crucial details, such as image edges. Notably, this method presents the dual benefits of straightforward parameter configuration and ease of implementation. The results indicate a substantial enhancement in noise suppression and fine structure preservation in the reconstructed images, marking a significant advancement in PET image reconstruction techniques.

ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection

Objective. This study aims to introduce a novel back projection-induced U-Net-shaped architecture, called ReconU-Net, based on the original U-Net architecture for deep learning-based direct positron emission tomography (PET) image reconstruction. Additionally, our objective is to visualize the behavior of direct PET image reconstruction by comparing the proposed ReconU-Net architecture with the original U-Net architecture and existing DeepPET encoder–decoder architecture without skip connections. Approach. The proposed ReconU-Net architecture uniquely integrates the physical model of the back projection operation into the skip connection. This distinctive feature facilitates the effective transfer of intrinsic spatial information from the input sinogram to the reconstructed image via an embedded physical model. The proposed ReconU-Net was trained using Monte Carlo simulation data from the Brainweb phantom and tested on both simulated and real Hoffman brain phantom data. Main results. The proposed ReconU-Net method provided better reconstructed image in terms of the peak signal-to-noise ratio and contrast recovery coefficient than the original U-Net and DeepPET methods. Further analysis shows that the proposed ReconU-Net architecture has the ability to transfer features of multiple resolutions, especially non-abstract high-resolution information, through skip connections. Unlike the U-Net and DeepPET methods, the proposed ReconU-Net successfully reconstructed the real Hoffman brain phantom, despite limited training on simulated data. Significance. The proposed ReconU-Net can improve the fidelity of direct PET image reconstruction, even with small training datasets, by leveraging the synergistic relationship between data-driven modeling and the physics model of the imaging process.

Anatomy-guided multi-resolution image reconstruction in PET

Objective. In this paper, we propose positron emission tomography image reconstruction using a multi-resolution triangular mesh. The mesh can be adapted based on patient specific anatomical information that can be in the form of a computed tomography or magnetic resonance imaging image in the hybrid imaging systems. The triangular mesh can be adapted to high resolution in localized anatomical regions of interest (ROI) and made coarser in other regions, leading to an imaging model with high resolution in the ROI with clearly reduced number of degrees of freedom compared to a conventional uniformly dense imaging model. Approach. We compare maximum likelihood expectation maximization reconstructions with the multi-resolution model to reconstructions using a uniformly dense mesh, a sparse mesh and regular rectangular pixel mesh. Two simulated cases are used in the comparison, with the first one using the NEMA image quality phantom and the second the XCAT human phantom. Main results. When compared to the results with the uniform imaging models, the locally refined multi-resolution mesh retains the accuracy of the dense mesh reconstruction in the ROI while being faster to compute than the reconstructions with the uniformly dense mesh. The locally dense multi-resolution model leads also to more accurate reconstruction than the pixel-based mesh or the sparse triangular mesh. Significance. The findings suggest that triangular multi-resolution mesh, which can be made patient and application specific, is a potential alternative for pixel-based reconstruction.

Fourier-Hankel-Abel Nyquist-limited tomography: A spherical harmonic basis function approach to tomographic velocity-map image reconstruction.

A new method for the fully generalized reconstruction of three-dimensional (3D) photoproduct distributions from velocity-map imaging (VMI) projection data is presented. This approach, dubbed Fourier-Hankel-Abel Nyquist-limited TOMography (FHANTOM), builds on recent previous work in tomographic image reconstruction [C. Sparling and D. Townsend, J. Chem. Phys. 157, 114201 (2022)] and takes advantage of the fact that the distributions produced in typical VMI experiments can be simply described as a sum over a small number of spherical harmonic functions. Knowing the solution is constrained in this way dramatically simplifies the reconstruction process and leads to a considerable reduction in the number of projections required for robust tomographic analysis. Our new method significantly extends basis set expansion approaches previously developed for the reconstruction of photoproduct distributions possessing an axis of cylindrical symmetry. FHANTOM, however, can be applied generally to any distribution-cylindrically symmetric or otherwise-that can be suitably described by an expansion in spherical harmonics. Using both simulated and real experimental data, this new approach is tested and benchmarked against other tomographic reconstruction strategies. In particular, the reconstruction of photoelectron angular distributions recorded in a strong-field ionization regime-marked by their extensive expansion in terms of spherical harmonics-serves as a key test of the FHANTOM methodology. With the increasing use of exotic optical polarization geometries in photoionization experiments, it is anticipated that FHANTOM and related reconstruction techniques will provide an easily accessible and relatively low-cost alternative to more advanced 3D-VMI spectrometers.

Electrical impedance tomography image reconstruction for lung monitoring based on ensemble learning algorithms1

AbstractElectrical impedance tomography (EIT) is a promising non‐invasive imaging technique that visualizes the electrical conductivity of an anatomic structure to form based on measured boundary voltages. However, the EIT inverse problem for the image reconstruction is nonlinear and highly ill‐posed. Therefore, in this work, a simulated dataset that mimics the human thorax was generated with boundary voltages based on given conductivity distributions. To overcome the challenges of image reconstruction, an ensemble learning method was proposed. The ensemble method combines several convolutional neural network models, which are the simple Convolutional Neural Network (CNN) model, AlexNet, AlexNet with residual block, and the modified AlexNet model. The ensemble models’ weights selection was based on average technique giving the best coefficient of determination (R2 score). The reconstruction quality is quantitatively evaluated by calculating the root mean square error (RMSE), the coefficient of determination (R2 score), and the image correlation coefficient (ICC). The proposed method's best performance is an RMSE of 0.09404, an R2 score of 0.926186, and an ICC of 0.95783 using an ensemble model. The proposed method is promising as it can construct valuable images for clinical EIT applications and measurements compared to previous studies.

Moment preserving tomographic image reconstruction model

Shape descriptors provide valuable prior information in many tomographic image reconstruction methods. Such descriptors include, among others, centroid, circularity, orientation, and elongation. Shape descriptor measures are often analytically expressed as a composition of certain geometric moments. Building upon this fact, this paper suggests preserving the values of a specific geometric moment in the reconstruction process, instead of preserving entire descriptors, as it has been suggested so far. Reconstructions from two natural projection directions (vertical and horizontal) are considered with special attention. The provided theoretical analysis demonstrates that preserving the value of a specific geometric moment, provided as prior information for the reconstruction process, simultaneously ensures the preservation of the true measures of all four abovementioned descriptors. Based on this result, a novel regularized energy minimization reconstruction model is proposed. The minimization task of the new model is solved using gradient-based optimization algorithm. Performance evaluation of the proposed method is supported by experimental results obtained through comparisons with other well-known reconstruction methods.

Influence of deep learning image reconstruction algorithm for reducing radiation dose and image noise compared to iterative reconstruction and filtered back projection for head and chest computed tomography examinations: a systematic review.

The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations. We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines. Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations. DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy.

Enhanced Antenna System for Non-invasive Quality Assessment and Defect Identification in Fruits: Uniting Tomographic Image Reconstruction with FTIR Spectroscopy

Enhanced Antenna System for Non-invasive Quality Assessment and Defect Identification in Fruits: Uniting Tomographic Image Reconstruction with FTIR Spectroscopy

AIRPORT: A Data Consistency Constrained Deep Temporal Extrapolation Method To Improve Temporal Resolution In Contrast Enhanced CT Imaging.

Typical tomographic image reconstruction methods require that the imaged object is static and stationary during the time window to acquire a minimally complete data set. The violation of this requirement leads to temporal-averaging errors in the reconstructed images. For a fixed gantry rotation speed, to reduce the errors, it is desired to reconstruct images using data acquired over a narrower angular range, i.e., with a higher temporal resolution. However, image reconstruction with a narrower angular range violates the data sufficiency condition, resulting in severe data-insufficiency-induced errors. The purpose of this work is to decouple the trade-off between these two types of errors in contrast-enhanced computed tomography (CT) imaging. We demonstrated that using the developed data consistency constrained deep temporal extrapolation method (AIRPORT), the entire time-varying imaged object can be accurately reconstructed with 40 frames-per-second temporal resolution, the time window needed to acquire a single projection view data using a typical C-arm cone-beam CT system. AIRPORT is applicable to general non-sparse imaging tasks using a single short-scan data acquisition.

TSS-ConvNet for electrical impedance tomography image reconstruction

Objective. The objective of this study was to propose a novel data-driven method for solving ill-posed inverse problems, particularly in certain conditions such as time-difference electrical impedance tomography for detecting the location and size of bubbles inside a pipe. Approach. We introduced a new layer architecture composed of three paths: spatial, spectral, and truncated spectral paths. The spatial path processes information locally, whereas the spectral and truncated spectral paths provide the network with a global receptive field. This unique architecture helps eliminate the ill-posedness and nonlinearity inherent in the inverse problem. The three paths were designed to be interconnected, allowing for an exchange of information on different receptive fields with varied learning abilities. Our network has a bottleneck architecture that enables it to recover signal information from noisy redundant measurements. We named our proposed model truncated spatial-spectral convolutional neural network (TSS-ConvNet). Main results. Our model demonstrated superior accuracy with relatively high resolution on both simulation and experimental data. This indicates that our approach offers significant potential for addressing ill-posed inverse problems in complex conditions effectively and accurately. Significance. The TSS-ConvNet overcomes the receptive field limitation found in most existing models that only utilize local information in Euclidean space. We trained the network on a large dataset covering various configurations with random parameters to ensure generalization over the training samples.

Generative-Adversarial-Network-Based Image Reconstruction for the Capacitively Coupled Electrical Impedance Tomography of Stroke.

This study investigated the potential of machine-learning-based stroke image reconstruction in capacitively coupled electrical impedance tomography. The quality of brain images reconstructed using the adversarial neural network (cGAN) was examined. The big data required for supervised network training were generated using a two-dimensional numerical simulation. The phantom of an axial cross-section of the head without and with impact lesions was an average of a three-centimeter-thick layer corresponding to the height of the sensing electrodes. Stroke was modeled using regions with characteristic electrical parameters for tissues with reduced perfusion. The head phantom included skin, skull bone, white matter, gray matter, and cerebrospinal fluid. The coupling capacitance was taken into account in the 16-electrode capacitive sensor model. A dedicated ECTsim toolkit for Matlab was used to solve the forward problem and simulate measurements. A conditional generative adversarial network (cGAN) was trained using a numerically generated dataset containing samples corresponding to healthy patients and patients affected by either hemorrhagic or ischemic stroke. The validation showed that the quality of images obtained using supervised learning and cGAN was promising. It is possible to visually distinguish when the image corresponds to the patient affected by stroke, and changes caused by hemorrhagic stroke are the most visible. The continuation of work towards image reconstruction for measurements of physical phantoms is justified.

Adjacent object distorts the organ-of-interest in filtered back-projection tomographic image reconstruction: 'ramp filter' or 'reconstruction' artifact revisited.

To simulate the artifact caused by an adjacent object on organ-of-interest during filtered back-projection (FBP) tomographic reconstruction (the so-called "ramp filter" artifact) and to demonstrate the extent to which an organ-of-interest is influenced by such adjacent hot spot or attenuating object. Two simulations are conducted with two simplified phantoms: "hot spot" and "cardiac." First one is used to visualize effect of hot spot on its periphery. Second one is used to evaluate effect of nearby object (liver) on left ventricle (LV) as organ-of-interest. To generate sinograms, forward projection process is done with and without modeling radiation attenuation. FBP using windowed ramp filter is done. All slices are analyzed by plotting intensity profiles. In tomographic slices, there is a hypo-intense halo around presumed edge of object when compared to background intensity, more noticeable in phantoms with less blurring. Even with ramp filter applied, no halo is visible in FBP without attenuation for cardiac phantom. In contrast, in slices with considering attenuation, zones with different levels of count suppression on both sides of object are visualized instead. The most prominent one is between liver and LV in simulation with higher-attenuating object and higher activity. A single hot spot with sufficient amount of blurring does not distort its surroundings. Hot spots and attenuating objects near organ-of-interest, however, distort myocardial perfusion imaging. Artifactual defects are thus only created when attenuation is modeled during FBP, producing zones of count suppression between organ-of-interest and nearby object or hot spot.

Image reconstruction based on nonlinear diffusion model for limited-angle computed tomography

The problem of limited-angle computed tomography (CT) imaging reconstruction has a wide range of practical applications. Due to various factors such as high x-ray absorption, structural characteristics of the scanned object, and equipment limitations, it is often impractical to obtain a complete angular scan, resulting in limited-angle scan data. In this paper, we propose an iterative image reconstruction algorithm for limited-angle CT. The algorithm carries out a traditional CT reconstruction and a nonlinear diffusion process alternatively. Specifically, a subtle partial differential equation is constructed to guide the nonlinear diffusion process to eliminate limited-angle artifacts in the reconstructed image. Numerical experiments on both analytic data and real data validate the efficacy of the proposed nonlinear diffusion reconstruction algorithm. Furthermore, a linear diffusion reconstruction algorithm which combines a traditional CT reconstruction algorithm and a linear diffusion process is also presented in the paper.

CT image reconstruction via industrial CT fast scanning

In automated manufacturing and safety inspection, there is a high demand for fast computed tomography (CT) scanning and image reconstruction. Currently, faster scanning can be achieved by reducing the X-ray exposure time within sparse view CT. The faster scanning strategy introduces significant streak artefacts and noise during the sampling process. Consequently, streak artefacts and noise need to be simultaneously suppressed, which is poses a challenge for existing reconstruction methods. This paper presents a fast iterative reconstruction algorithm that can simultaneously suppress both streak artefacts and noise. This method can not only reconstruct high-fidelity images from rapidly acquired projection data, but also has a faster reconstruction speed than the existing iterative reconstruction algorithms. First, we present a high-order multi-directional total variation (HOM-TV) method that specifically focuses on preserving edge details of the image. Then, we present a fast iterative reconstruction model by incorporating HOM-TV and non-local means into the objective function. Finally, the effectiveness of the presented reconstruction model is validated by simulation and real experiments. The faster scanning method can complete the scan in only 5 seconds, and the structural similarity index (SSIM) of the CT image reconstructed by our method is 0.9755, which is higher than 0.0175 of the Fast Null Space Reconstruction (FNSR) algorithm. The peak signal-to-noise ratio (PSNR) index is 1.656, which is higher than that of the contrast algorithm. In terms of reconstruction time, our algorithm can achieve reconstruction in as little as 36 seconds, outperforming the baseline algorithms.

An iterative reconstruction algorithm for unsupervised PET image

Objective. In recent years, convolutional neural networks (CNNs) have shown great potential in positron emission tomography (PET) image reconstruction. However, most of them rely on many low-quality and high-quality reference PET image pairs for training, which are not always feasible in clinical practice. On the other hand, many works improve the quality of PET image reconstruction by adding explicit regularization or optimizing the network structure, which may lead to complex optimization problems. Approach. In this paper, we develop a novel iterative reconstruction algorithm by integrating the deep image prior (DIP) framework, which only needs the prior information (e.g. MRI) and sinogram data of patients. To be specific, we construct the objective function as a constrained optimization problem and utilize the existing PET image reconstruction packages to streamline calculations. Moreover, to further improve both the reconstruction quality and speed, we introduce the Nesterov’s acceleration part and the restart mechanism in each iteration. Main results. 2D experiments on PET data sets based on computer simulations and real patients demonstrate that our proposed algorithm can outperform existing MLEM-GF, KEM and DIPRecon methods. Significance. Unlike traditional CNN methods, the proposed algorithm does not rely on large data sets, but only leverages inter-patient information. Furthermore, we enhance reconstruction performance by optimizing the iterative algorithm. Notably, the proposed method does not require much modification of the basic algorithm, allowing for easy integration into standard implementations.

CGAN-ECT: Reconstruction of Electrical Capacitance Tomography images from capacitance measurements using Conditional Generative Adversarial Networks

Due to the rapid growth of applications of Electrical Capacitance Tomography (ECT) across diverse industrial sectors, there is a pressing demand for swift and high-fidelity methodologies for image reconstruction from raw capacitance measurements. Deep learning, as an effective non-linear mapping tool for complicated functions, has been going viral in many fields including electrical tomography. This paper introduces a pioneering contribution by proposing a Conditional Generative Adversarial Network (CGAN) model explicitly tailored for the purpose of reconstructing ECT images from capacitance measurements. We propose a novel modulator to transform the raw input capacitance measurements into a 2D image. To the best of our knowledge, this is the first time to represent the capacitance measurements in an image form. We have created a new massive ECT dataset of synthetic image-measurements pairs for training and testing purposes of the proposed model. This extensive ECT dataset comprises 320,000 synthetic image-measurement pairs. It forms the basis for evaluating the feasibility and generalizability of the CGAN-ECT model, with assessments conducted on testing data, contaminated data, and flow patterns which are intentionally excluded from the model’s training phase. The evaluation results prove the efficacy of the proposed CGAN model in generating ECT images with heightened accuracy compared to traditional methods and alternative deep learning-based image reconstruction algorithms. The CGAN-ECT model has succeeded in a achieving an average image correlation coefficient exceeding 99.3%, coupled with an average relative image error of approximately 0.07.

Influence of plume arrangement on spray collapsing process in lateral-cylinder-mounted gasoline injectors

Spray collapsing is a major factor that deteriorates combustion performance in gasoline direct-injection (GDI) engines. This study employed three different GDI injectors to investigate plume arrangement influence on spray dynamics. Novel optical diagnostics were applied to analyze complex spray collapse behaviors using LED-based diffusive back-illuminated extinction imaging (DBIEI) and 3D computed tomographic (CT) image reconstruction. The triangular pattern with 6 holes, commonly applied in modern GDI engines, was compared with two newly designed spray patterns: the inversed T pattern with 6 holes and the lambda pattern with 5 holes. Experimental results showed that the base triangular pattern, with plumes enclosed by other plumes, indicated significant spray collapse behavior under various conditions. The inversed T pattern, where plumes were arranged to not have a closed volume, had a robustness against collapse due to an open layout which prevents imbalance of the local pressure field that may causes collapse. The lambda pattern, which had a similar plume arrangement to the triangular pattern, except that one side of the diamond-shape closed volume is opened, also showed good robustness against collapse under most of the test conditions. This study demonstrated that spray collapse can be significantly mitigated by improved plume arrangement and provides spray patterns that can be applied to actual GDI engines with significantly improved spray robustness.