Iterative Reconstruction Methods Research Articles

Image fast reconstruction for sparse view computed tomography with reduced sampling integration time

Industrial computed tomography (CT) can detect the internal structure of objects nondestructively. Its scanning and image reconstruction are time-consuming, which limits its application in the fast detection field. In this work, we reduce the sampling integration time in sparse view CT to achieve ultra-fast scanning in only 5 s. However, this ultra-fast scanning method produces more noise and streak artifacts in the reconstructed CT images. The existing reconstruction methods cannot effectively reconstruct high quality CT images under this ultra-fast scanning. To solve this issue, a faster and higher quality CT image reconstruction method is proposed in this paper. We construct a novel objective function using multi-directional TV and adaptive non-local means (ANLM), and design a solution algorithm to solve the objective function. The multi-directional TV-norm takes into account the differences in horizontal, vertical, and 45° directional gradients to obtain more image detail information, while the ANLM-norm focuses on noise suppression. Simulation and practical experiments show that the proposed method can reconstruct higher quality CT images under faster CT scanning strategy, and the peak signal to noise ratio (PSNR) is 1.3 dB higher than the optimal baseline algorithm. On the other hand, our method converges faster and achieves a shorter CT image reconstruction time, which is 47 s shorter than the current popular iterative reconstruction methods. This reconstruction method provides a reliable scheme for faster CT scanning and image reconstruction.

Reconstruction method suitable for fast CT imaging

Reconstructing computed tomography (CT) images from an extremely limited set of projections is crucial in practical applications. As the available projections significantly decrease, traditional reconstruction and model-based iterative reconstruction methods become constrained. This work aims to seek a reconstruction method applicable to fast CT imaging when available projections are highly sparse. To minimize the time and cost associated with projections acquisition, we propose a deep learning model, X-CTReNet, which parameterizes a nonlinear mapping function from orthogonal projections to CT volumes for 3D reconstruction. The proposed model demonstrates effective capability in inferring CT volumes from two-view projections compared to baseline methods, highlighting the significant potential for drastically reducing projection acquisition in fast CT imaging.

Iterative Reconstruction of Micro Computed Tomography Scans Using Multiple Heterogeneous GPUs.

Graphics processing units (GPUs) facilitate massive parallelism and high-capacity storage, and thus are suitable for the iterative reconstruction of ultrahigh-resolution micro computed tomography (CT) scans by on-the-fly system matrix (OTFSM) calculation using ordered subsets expectation maximization (OSEM). We propose a finite state automaton (FSA) method that facilitates iterative reconstruction using a heterogeneous multi-GPU platform through parallelizing the matrix calculations derived from a ray tracing system of ordered subsets. The FSAs perform flow control for parallel threading of the heterogeneous GPUs, which minimizes the latency of launching ordered-subsets tasks, reduces the data transfer between the main system memory and local GPU memory, and solves the memory-bound of a single GPU. In the experiments, we compared the operation efficiency of OS-MLTR for three reconstruction environments. The heterogeneous multiple GPUs with job queues for high throughput calculation speed is up to five times faster than the single GPU environment, and that speed up is nine times faster than the heterogeneous multiple GPUs with the FIFO queues of the device scheduling control. Eventually, we proposed an event-triggered FSA method for iterative reconstruction using multiple heterogeneous GPUs that solves the memory-bound issue of a single GPU at ultrahigh resolutions, and the routines of the proposed method were successfully executed on each GPU simultaneously.

Conservation Design of Industrial Heritage based on Nonlinear GA Optimization Algorithm and Three-dimensional Reconstructioneconstruction

In order to understand the industrial heritage protection design of Iterative reconstruction, the author proposes a research on industrial heritage protection design based on GA optimization algorithm and Iterative reconstruction. Firstly, the author establishes the 3D model of industrial heritage through Iterative reconstruction, and optimizes the model parameters through GA algorithm to achieve the purpose of protecting and utilizing industrial heritage. Secondly, the author proposes a method of Iterative reconstruction of industrial heritage based on GA algorithm, uses this method to conduct Iterative reconstruction of industrial heritage, and imports the reconstructed model into the 3D model management system for management. This method solves the problem of high reconstruction cost caused by low model quality in traditional Iterative reconstruction, and makes industrial heritage protection design more practical. Finally, an experimental analysis was conducted using a factory building in a certain city as an example. The results showed that the model optimized using the GA algorithm had significantly better performance than traditional reconstruction methods, and could more accurately reflect the spatial form and structural characteristics of industrial heritage, this provided new ideas and methods for the subsequent protection and utilization of industrial heritage. The GA algorithm optimized 3D model established by the author can effectively evaluate industrial heritage in historical urban areas, not only revealing the value of industrial heritage better, but also providing a certain reference for similar work in the future.

Music curriculum integration and reconstruction model based on advanced music waveform iterative reconstruction algorithm

To improve the effect of intelligent teaching in music classrooms, this paper combines the advanced music waveform iterative reconstruction algorithm to analyze the integration and reconstruction of the music curriculum. Aiming at the problem that the projection matrix occupies a large space and takes a long time to calculate in iterative reconstruction, a fast and real-time incremental method for generating a music wave matrix is proposed. The improved method avoids the judgment and comparison calculations performed by the incremental method when calculating the length and number of each voxel that the ray passes through. The research results show that the music curriculum integration and reconstruction model based on the advanced music waveform iterative reconstruction algorithm can effectively improve the teaching effect of modern music classrooms.

Iterative Reconstruction Algorithms in Magneto-Acousto-Electrical Computed Tomography (MAE-CT) for Image Quality Improvement.

Magneto-acousto-electrical computed tomography (MAE-CT) is a recently developed rotational magneto-acousto-electrical tomography (MAET) method, which can map the conductivity parameter of tissues with high spatial resolution. Since the imaging mode of MAE-CT is similar to that of CT, the reconstruction algorithms for CT are possible to be adopted for MAE-CT. Previous studies have demonstrated that the filtered back-projection (FBP) algorithm, which is one of the most common CT reconstruction algorithms, can be used for MAE-CT reconstruction. However, FBP has some inherent shortcomings of being sensitive to noise and non-uniform distribution of views. In this study, we introduced iterative reconstruction (IR) method in MAE-CT reconstruction and compared its performance with that of the FBP. The numerical simulation, the phantom, and in vitro experiments were performed, and several IR algorithms (ART, SART, SIRT) were used for reconstruction. The results show that the images reconstructed by the FBP and IR are similar when the data is noise-free in the simulation. As the noise level increases, the images reconstructed by SART and SIRT are more robust to the noise than FBP. In the phantom experiment, noise and some stripe artifacts caused by the FBP are removed by SART and SIRT algorithms. In conclusion, the IR method used in CT is applicable in MAE-CT, and it performs better than FBP, which indicates that the state-of-the-art achievements in the CT algorithm can also be adopted for the MAE-CT reconstruction in the future.

An attenuation field network for dedicated cone beam breast CT with short scan and offset detector geometry

The feasibility of full-scan, offset-detector geometry cone-beam CT has been demonstrated for several clinical applications. For full-scan acquisition with offset-detector geometry, data redundancy from complementary views can be exploited during image reconstruction. Envisioning an upright breast CT system, we propose to acquire short-scan data in conjunction with offset-detector geometry. To tackle the resulting incomplete data, we have developed a self-supervised attenuation field network (AFN). AFN leverages the inherent redundancy of cone-beam CT data through coordinate-based representation and known imaging physics. A trained AFN can query attenuation coefficients using their respective coordinates or synthesize projection data including the missing projections. The AFN was evaluated using clinical cone-beam breast CT datasets (n = 50). While conventional analytical and iterative reconstruction methods failed to reconstruct the incomplete data, AFN reconstruction was not statistically different from the reference reconstruction obtained using full-scan, full-detector data in terms of image noise, image contrast, and the full width at half maximum of calcifications. This study indicates the feasibility of a simultaneous short-scan and offset-detector geometry for dedicated breast CT imaging. The proposed AFN technique can potentially be expanded to other cone-beam CT applications.

Five-view three-dimensional reconstruction for ultrafast dynamic imaging of pulsed radiation sources

Multiaxial neutron/x-ray imaging and three-dimensional (3D) reconstruction techniques play a crucial role in gaining valuable insights into the generation and evolution mechanisms of pulsed radiation sources. Owing to the short emission time (∼200 ns) and drastic changes of the pulsed radiation source, it is necessary to acquire projection data within a few nanoseconds in order to achieve clear computed tomography 3D imaging. As a consequence, projection data that can be used for computed tomography image reconstruction at a certain moment are often available for only a few angles. Traditional algorithms employed in the process of reconstructing 3D images with extremely incomplete data may introduce significant distortions and artifacts into the final image. In this paper, we propose an iterative image reconstruction method using cylindrical harmonic decomposition and a self-supervised denoising network algorithm based on the deep image prior method. We augment the prior information with a 2D total variation prior and a 3D deep image prior. Single-wire Z-pinch imaging experiments have been carried out at Qin-1 facility in five views and four frames, with a time resolution of 3 ns for each frame and a time interval of 40 ns between adjacent frames. Both numerical simulations and experiments verify that our proposed algorithm can achieve high-quality reconstruction results and obtain the 3D intensity distribution and evolution of extreme ultraviolet and soft x-ray emission from plasma.

SOUL-Net: A Sparse and Low-Rank Unrolling Network for Spectral CT Image Reconstruction.

Spectral computed tomography (CT) is an emerging technology, that generates a multienergy attenuation map for the interior of an object and extends the traditional image volume into a 4-D form. Compared with traditional CT based on energy-integrating detectors, spectral CT can make full use of spectral information, resulting in high resolution and providing accurate material quantification. Numerous model-based iterative reconstruction methods have been proposed for spectral CT reconstruction. However, these methods usually suffer from difficulties such as laborious parameter selection and expensive computational costs. In addition, due to the image similarity of different energy bins, spectral CT usually implies a strong low-rank prior, which has been widely adopted in current iterative reconstruction models. Singular value thresholding (SVT) is an effective algorithm to solve the low-rank constrained model. However, the SVT method requires a manual selection of thresholds, which may lead to suboptimal results. To relieve these problems, in this article, we propose a sparse and low-rank unrolling network (SOUL-Net) for spectral CT image reconstruction, that learns the parameters and thresholds in a data-driven manner. Furthermore, a Taylor expansion-based neural network backpropagation method is introduced to improve the numerical stability. The qualitative and quantitative results demonstrate that the proposed method outperforms several representative state-of-the-art algorithms in terms of detail preservation and artifact reduction.

Towards safer imaging: A comparative study of deep learning-based denoising and iterative reconstruction in intraindividual low-dose CT scans using an in-vivo large animal model

PurposeComputed tomography (CT) scans are a significant source of medically induced radiation exposure. Novel deep learning-based denoising (DLD) algorithms have been shown to enable diagnostic image quality at lower radiation doses than iterative reconstruction (IR) methods. However, most comparative studies employ low-dose simulations due to ethical constraints. We used real intraindividual animal scans to investigate the dose-reduction capabilities of a DLD algorithm in comparison to IR. Materials and methodsFourteen veterinarian-sedated alive pigs underwent 2 CT scans on the same 3rd generation dual-source scanner with two months between each scan. Four additional scans ensued each time, with mAs reduced to 50 %, 25 %, 10 %, and 5 %. All scans were reconstructed ADMIRE levels 2 (IR2) and a novel DLD algorithm, resulting in 280 datasets. Objective image quality (CT numbers stability, noise, and contrast-to-noise ratio) was measured via consistent regions of interest. Three radiologists independently rated all possible dataset combinations per time point for subjective image quality (−1 = inferior, 0 = equal, 1 = superior). The points were averaged for a semiquantitative score, and inter-rater agreement was measured using Spearman's correlation coefficient and adequately corrected mixed-effects modeling analyzed objective and subjective image quality. ResultsNeither dose-reduction nor reconstruction method negatively impacted CT number stability (p > 0.999). In objective image quality assessment, the lowest radiation dose achievable by DLD when comparing noise (p = 0.544) and CNR (p = 0.115) to 100 % IR2 was 25 %. Overall, inter-rater agreement of the subjective image quality ratings was strong (r ≥ 0.69, mean 0.93 ± 0.05, 95 % CI 0.92–0.94; each p < 0.001), and subjective assessments corroborated that DLD at 25 % radiation dose was comparable to 100 % IR2 in image quality, sharpness, and contrast (p ≥ 0.281). ConclusionsThe DLD algorithm can achieve image quality comparable to the standard IR method but with a significant dose reduction of up to 75%. This suggests a promising avenue for lowering patient radiation exposure without sacrificing diagnostic quality.

An iterative 3D human body reconstruction method driven by personalized dimensional prior knowledge

An iterative 3D human body reconstruction method driven by personalized dimensional prior knowledge

Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image assessment approach

Objective. Digital breast tomosynthesis (DBT) is a quasi-three-dimensional breast imaging modality that improves breast cancer screening and diagnosis because it reduces fibroglandular tissue overlap compared with 2D mammography. However, DBT suffers from noise and blur problems that can lower the detectability of subtle signs of cancers such as microcalcifications (MCs). Our goal is to improve the image quality of DBT in terms of image noise and MC conspicuity. Approach. We proposed a model-based deep convolutional neural network (deep CNN or DCNN) regularized reconstruction (MDR) for DBT. It combined a model-based iterative reconstruction (MBIR) method that models the detector blur and correlated noise of the DBT system and the learning-based DCNN denoiser using the regularization-by-denoising framework. To facilitate the task-based image quality assessment, we also proposed two DCNN tools for image evaluation: a noise estimator (CNN-NE) trained to estimate the root-mean-square (RMS) noise of the images, and an MC classifier (CNN-MC) as a DCNN model observer to evaluate the detectability of clustered MCs in human subject DBTs. Main results. We demonstrated the efficacies of CNN-NE and CNN-MC on a set of physical phantom DBTs. The MDR method achieved low RMS noise and the highest detection area under the receiver operating characteristic curve (AUC) rankings evaluated by CNN-NE and CNN-MC among the reconstruction methods studied on an independent test set of human subject DBTs. Significance. The CNN-NE and CNN-MC may serve as a cost-effective surrogate for human observers to provide task-specific metrics for image quality comparisons. The proposed reconstruction method shows the promise of combining physics-based MBIR and learning-based DCNNs for DBT image reconstruction, which may potentially lead to lower dose and higher sensitivity and specificity for MC detection in breast cancer screening and diagnosis.

A data-driven framework for designing microstructure of multifunctional composites with deep-learned diffusion-based generative models

This paper introduces a novel integrated microstructure design methodology that replaces the common existing design approaches for multifunctional composites: 1) reconstruction of microstructures, 2) analyzing and quantifying material properties, and 3) inverse design of materials. The problem of microstructure reconstruction is addressed using the diffusion-based generative model (DGM), which is a state-of-the-art generative model formulated with a Markovian diffusion process. Then, the conditional formulation of DGM is introduced for guidance to the embedded desired material properties with a transformer-based attention mechanism, which enables the inverse design of multifunctional composites. Furthermore, a convolutional neural network (CNN)-based surrogate model is utilized to facilitate the prediction of linear/nonlinear material properties for building microstructure-property linkages. Combined, the proposed artificial intelligence-based design framework enables large data processing and database construction that is often not affordable with resource-intensive finite element method (FEM)-based direct numerical simulation (DNS) or iterative reconstruction methods. It is worth noting that the proposed DGM-based methodology is not susceptible to unstable training or mode collapse, which are common issues in generative models that are often difficult to address even with extensive hyperparameter tuning. An example case is presented to demonstrate the effectiveness of the proposed approach, which is designing mechanoluminescence (ML) particulate composites. The results show that the designed ML microstructure samples with the proposed generative and surrogate models meet the multiple design requirements (e.g., volume fraction, elastic constant, and light sensitivity). This assessment demonstrates that the proposed integrated methodology provides an end-to-end solution for practical material design applications.

Deep learning enables time-efficient soft tissue enhancement in CBCT: Proof-of-concept study for dentomaxillofacial applications

PurposeThe use of iterative and deep learning reconstruction methods, which would allow effective noise reduction, is limited in cone-beam computed tomography (CBCT). As a consequence, the visibility of soft tissues is limited with CBCT. The study aimed to improve this issue through time-efficient deep learning enhancement (DLE) methods. MethodsTwo DLE networks, UNIT and U-Net, were trained with simulated CBCT data. The performance of the networks was tested with three different test data sets. The quantitative evaluation measured the structural similarity index measure (SSIM) and the peak signal-to-noise ratio (PSNR) of the DLE reconstructions with respect to the ground truth iterative reconstruction method. In the second assessment, a dentomaxillofacial radiologist assessed the resolution of hard tissue structures, visibility of soft tissues, and overall image quality of real patient data using the Likert scale. Finally, the technical image quality was determined using modulation transfer function, noise power spectrum, and noise magnitude analyses. ResultsThe study demonstrated that deep learning CBCT denoising is feasible and time efficient. The DLE methods, trained with simulated CBCT data, generalized well, and DLE provided quantitatively (SSIM/PSNR) and visually similar noise-reduction as conventional IR, but with faster processing time. The DLE methods improved soft tissue visibility compared to the conventional Feldkamp-Davis-Kress (FDK) algorithm through noise reduction. However, in hard tissue quantification tasks, the radiologist preferred the FDK over the DLE methods. ConclusionPost-reconstruction DLE allowed feasible reconstruction times while yielding improvements in soft tissue visibility in each dataset.

Optimization of the Reconstruction Settings for Low-Dose Ultra-High-Resolution Photon-Counting Detector CT of the Lungs

Photon-counting detector computed tomography (PCD-CT) yields improved spatial resolution. The combined use of PCD-CT and a modern iterative reconstruction method, known as quantum iterative reconstruction (QIR), has the potential to significantly improve the quality of lung CT images. In this study, we aimed to analyze the impacts of different slice thicknesses and QIR levels on low-dose ultra-high-resolution (UHR) PCD-CT imaging of the lungs. Our study included 51 patients with different lung diseases who underwent unenhanced UHR-PCD-CT scans. Images were reconstructed using three different slice thicknesses (0.2, 0.4, and 1.0 mm) and three QIR levels (2–4). Noise levels were determined in all reconstructions. Three raters evaluated the delineation of anatomical structures and conspicuity of various pulmonary pathologies in the images compared to the clinical reference reconstruction (1.0 mm, QIR-3). The highest QIR level (QIR-4) yielded the best image quality. Reducing the slice thickness to 0.4 mm improved the delineation and conspicuity of pathologies. The 0.2 mm reconstructions exhibited lower image quality due to high image noise. In conclusion, the optimal reconstruction protocol for low-dose UHR-PCD-CT of the lungs includes a slice thickness of 0.4 mm, with the highest QIR level. This optimized protocol might improve the diagnostic accuracy and confidence of lung imaging.

Exit wave function reconstruction from two defocus images using neural network

Wave function reconstruction from one or two defocus images is promising for live atomic resolution imaging in transmission electron microscopy. However, a robust and accurate reconstruction method we still need more attention. Here, we present a neural-network-based wave function reconstruction method, EWR-NN, that enables accurate wave function reconstruction from only two defocus images. Results from both simulated and two different experimental defocus series show that the EWR-NN method has better performance than the widely-used iterative wave function reconstruction (IWFR) method. Influence of image number, defocus deviation, residual image shifts and noise level were considered to validate the performance of EWR-NN under practical conditions. It is seen that these factors will not influence the arrangement of atom columns in the reconstructed phase images, while they can alter the absolute values of all-atom columns and degrade the contrast of the phase images.

Background-oriented Schlieren tomography using gated recurrent unit.

Current Background-oriented schlieren tomography (BOST) methods rely primarily on iterative algorithms for reconstruction. Before reconstruction, a weight projection matrix was generated by performing 3D ray tracing using the projection relationship between the cameras, depending on the camera calibration parameters and large weight projection matrix which introduce artifacts and greatly reduce computational efficiency in the reconstruction. Considering that CT reconstruction uses spatial projection sequences from multiple directions, this study draws inspiration from the Recurrent Neural network(RNN) and utilizes spatial correlation between adjacent projection data to propose a background-oriented schlieren reconstruction method based on a gated recurrent unit (GRU) neural network. First, the model architecture is designed and implemented. Subsequently, numerical simulations were conducted using a methane combustion model to evaluate the proposed method, which achieved an average mean relative error (MRE) of 0.23%. Finally, reconstruction experiments were performed on the actual flow-field data above a candle flame, with a reprojection correlation coefficient of 89% and an average reconstruction time of only 1.04 s per frame. The results demonstrate that the proposed method outperforms traditional iterative reconstruction methods in terms of reconstruction speed and accuracy. This provides a feasible solution for the real-time reconstruction of three-dimensional instantaneous flow fields.

Iterative Image Reconstruction Methodology in Optical CT Radiochromic Gel Dosimetry

Modern advancements in radiation therapy require paralleled advancements in the dosimetric tools used to verify dose distributions. Optical computed tomography (CT) imaged radiochromic gel dosimeters provide comprehensive, tissue equivalent, 3D dosimetric information with high spatial resolution and low imaging times. Traditional CT image reconstruction methods (filtered backprojection) do not account for light refraction within the optical CT system reducing the image quality. Iterative reconstruction methods make use of a system matrix that describes this light refraction thus, improving the reconstructed image quality. However, use of iterative reconstruction methods is not widespread, largely due to the impractical storage size of the required system matrix. Furthermore, current iterative reconstruction methods do not address the issue of image degradation due to a single detector element collecting light from multiple raypaths. For optical CT radiochromic gel dosimetry to be used effectively as a radiation therapy treatment plan verification tool, the system must be both practical and accurate. Thus, this work has two main objectives: (i) reduce the size of system matrices by means of polar coordinate discretization in lieu of the traditional Cartesian coordinate discretization, and (ii) reduce image degradation due to multiple raypaths by a novel approach to populating the system matrix that accounts for multiple raypaths.

A Locally Weighted Linear Regression Look-Up Table-Based Iterative Reconstruction Method for Dual Spectral CT.

Compared with traditional computed tomography (CT), dual spectral CT (DSCT) exhibits superior material distinguishability and thus has broad prospects in industrial and medical fields. In iterative DSCT algorithms, accurately modeling forward-projection functions is crucial, but it is very difficult to analytically provide accurate functions. In this article, we propose a locally weighted linear regression look-up table-based (LWLR-LUT) iterative reconstruction method for DSCT. First, the proposed method uses LWLR to establish LUTs for the forward-projection functions through calibration phantoms, achieving good local information calibration. Second, the reconstructed images can be iteratively obtained through the established LUTs. The proposed method not only does not require knowledge of the X-ray spectra and the attenuation coefficients, but also implicitly accounts for some scattered radiation while fitting locally the forward-projection functions in the calibration space. Both numerical simulations and real data experiments demonstrate that the proposed method can achieve highly accurate polychromatic forward-projection functions and greatly improve the quality of the images reconstructed from scattering-free and scattering projections. The proposed method is simple and practical, and achieves good material decomposition effects for objects with different complex structures through simple calibration phantoms.

Filtered back projection vs. iterative reconstruction for CBCT: effects on image noise and processing time.

To assess the effect of standard filtered back projection (FBP) and iterative reconstruction (IR) methods on CBCT image noise and processing time (PT), acquired with various acquisition parameters with and without metal artefact reduction (MAR). CBCT scans using the Midmark EIOS unit of a human mandible embedded in soft tissue equivalent material with and without the presence of an implant at mandibular first molar region were acquired at various acquisition settings (milliamperages [4mA-14mA], FOV [5 × 5, 6 × 8, 9 × 10 cm], and resolutions [low, standard, high] and reconstructed using standard FBP and IR, and with and without MAR. The processing time was recorded for each reconstruction. ImageJ was used to analyze specific axial images. Radial transaxial fiducial lines were created relative to the implant site. Standard deviations of the gray density values (image noise) were calculated at fixed distances on the fiducial lines on the buccal and lingual aspects at specific axial levels, and mean values for FBP and IR were compared using paired t-tests. Significance was defined as p < 0.05. The overall mean for image noise (± SD) for FBP was 198.65 ± 55.58 and 99.84 ± 16.28 for IR. IR significantly decreased image noise compared to FBP at all acquisition parameters (p < 0.05). Noise reduction among different scanning protocols ranged between 29.7% (5 × 5 cm FOV) and 58.1% (5mA). IR increased processing time by an average of 35.1 s. IR significantly reduces CBCT image noise compared to standard FBP without substantially increasing processing time.