Dual-energy CT (DECT) has been increasingly used in imaging applications because of its capability for material differentiation. However, decomposition suffers from magnified noise two images independent scans, leading to severe degradation image quality. Existing algorithms exhibit suboptimal performance they fail fully depict the mapping relationship between DECT and basis materials under noisy conditions. Convolutional neural network exhibits great promise modeling data coupling recently...

Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by geometric space and mechanical structure imaging system, projections can only be collected with scanning range less than 90°. We call this kind serious limited-angle ultra-limited-angle problem, which difficult to effectively alleviate traditional iterative algorithms. With development deep learning, generative adversarial network (GAN)...

The widespread application of X-ray computed tomography (CT) in clinical diagnosis has led to increasing public concern regarding excessive radiation dose administered patients. However, reducing the will inevitably cause server noise and affect radiologists’ judgment confidence. Hence, progressive low-dose CT (LDCT) image reconstruction methods must be developed improve quality. Over past two years, deep learning-based approaches have shown impressive performance reduction for LDCT images....

Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the fields of CT. With development deep learning, generative adversarial network (GAN) perform well restoration by approximating distribution training sample data. In this paper, we proposed an effective GAN-based inpainting method to restore missing sinogram data for limited-angle scanning. To estimate data, design generator and discriminator patch-GAN train learn sinogram. We obtain reconstructed from...

Linear scan computed tomography (CT) is a promising imaging configuration with high scanning efficiency while the data set under-sampled and angularly limited for which quality image reconstruction challenging. In this work, an edge guided

Total generalized variation (TGV)-based computed tomography (CT) image reconstruction, which utilizes high-order derivatives, is superior to total variation-based methods in terms of the preservation edge information and suppression unfavorable staircase effects. However, conventional TGV regularization employs l1-based form, not most direct method for maximizing sparsity prior. In this study, we propose a p-variation (TGpV) model improve exploitation offer efficient solutions few-view CT...

Purpose: Metal artifact reduction (MAR) is a major problem and challenging issue in x‐ray computed tomography (CT) examinations. Iterative reconstruction from sinograms unaffected by metals shows promising potential detail recovery. This has been the subject of much research recent years. However, conventional iterative methods easily introduce new artifacts around metal implants because incomplete data inconsistencies practical acquisition. Hence, this work aims at developing method to...

Multi-energy computed tomography (CT) provides multiple channel-wise reconstructed images, and they can be used for material identification k-edge imaging. Nonetheless, the projection datasets are frequently corrupted by various noises (e.g., electronic, Poisson) in acquisition process, resulting lower signal-noise-ratio (SNR) measurements. CT images have local sparsity, nonlocal self-similarity spatial dimension, correlation spectral dimension.In this paper, we propose an image-spectral...

Spectral computed tomography (CT) provides multispectral X-ray information that can be used for quantitative material-specific imaging compared to the conventional CT. However, low-count photon rate in a single energy bin may lead highly noisy measurements with compromised material contrast and accuracy. Moreover, complicated decomposition process is an ill-posed inverse problem, which sensitive noise. In this work, we develop image-domain method via material-image tensor factorization...

Compared with the conventional 1×1 acquisition mode of projection in computed tomography (CT) image reconstruction, 2×2 improves collection efficiency and reduces x-ray exposure time. However, collected based on has low resolution (LR) reconstructed quality is poor, thus limiting use this CT imaging systems. In study, a novel sinogram-super-resolution (SR) generative adversarial network model proposed to obtain high-resolution (HR) sinograms from LR sinograms, thereby improving...

The presence of metal objects remains a challenge in x-ray computed tomography (CT) imaging. Sinograms passing through metals, called trace, usually provide uncorrected information and are considered missing CT image reconstruction. sparse prior an some appropriate transform domains, defined implicit sparsity, is often used sinogram inpainting methods for trace recovery. However, conventional only employ the sparsity result several artifacts reconstructed images. In this paper, we propose...

Dual-energy computed tomography (DECT) provides more anatomical and functional information for image diagnosis. Presently, the popular DECT imaging systems need to scan at least full angle (i.e., 360°). In this study, we propose a using complementary limited-angle (DECT-CL) technology reduce radiation dose compress spatial distribution of system. The dual-energy total is 180°, where low- high-energy range first 90° last 90°, respectively. We describe dual problem as problem, which...

The excessive radiation doses in the application of computed tomography (CT) technology pose a threat to health patients. However, applying low dose CT can result severe artifacts and noise captured images, thus affecting diagnosis. Therefore, this study, we investigate dual residual convolution neural network (DRCNN) for low-dose (LDCT) imaging, whereby images are reconstructed directly from sinogram by integrating analytical domain transformations, reducing loss projection information....

The projection matrix model is used to describe the physical relationship between reconstructed object and projection. Such a has strong influence on backprojection, two vital operations in iterative computed tomographic reconstruction. distance-driven (DDM) state-of-the-art technology that simulates forward back projections. This low computational complexity relatively high spatial resolution; however, it includes only few methods parallel operation with matched scheme. study introduces...

BACKGROUND: Computed tomography (CT) plays an important role in the field of non-destructive testing. However, conventional CT images often have blurred edge and unclear texture, which is not conducive to follow-up medical diagnosis industrial testing work. OBJECTIVE: This study aims generate high-resolution using a new super-resolution reconstruction method combining with sparsity regularization deep learning prior. METHODS: The reconstructs through model incorporating image gradient...

Compared with conventional single-energy computed tomography (CT), dual-energy CT (DECT) provides better material differentiation but most DECT imaging systems require dual full-angle projection data at different X-ray spectra. Relaxing the requirement of acquisition is an attractive research to promote applications in wide range areas and reduce radiation dose as low reasonably achievable. In this work, we design a novel scheme quarter scans propose efficient method reconstruct desired...

The guideline of "as low as reasonably achievable" (ALARA) for radiation dose has attracted attention to sparse-view spectral computed tomography (CT) imaging. Any missing scanning view in any energy will reduce the quality image reconstruction and material decomposition. Recently, a series achievements have been made optimizing CT imaging based on traditional iterative models or deep learning methods. However, these works are independent simply coupled, often neglecting dependency...

A novel fuzzy-neural network, the type-2 GA- TSKfnn (T2GA-TSKfnn), combining a fuzzy logic system (FLS) and genetic algorithm (GA) based Takagi-Sugeno- Kang neural network (GA-TSKfnn), is presented. The rational for this combination that sets are better able to deal with rule uncertainties, while optimal GA-based tuning of T2GA-TSKfnn parameters achieves classification results. However, general computationally very intensive due complexity type-1 reduction. Therefore, we adopt an interval...

The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it usually limited by scanning devices and great expense. Convolutional neural network (CNN)- based methods have achieved promising ability in super-resolution. However, existing mainly focus on super-resolution reconstructed do not fully explored approach from projectiondomain. In this paper, we studied characteristic projection proposed a CNN-based method establish mapping...

With the development of compressive sensing theory, image reconstruction from few-view projections has been paid considerable research attention in field computed tomography (CT). Total variation (TV)-based CT sho

Multi-energy computed tomography (MECT) based on a photon-counting detector is an emerging imaging modality that collects projections at several energy bins with single scan. However, the limited number of photons collected into divided, narrow results in high quantum noise levels reconstructed images. This study aims to improve MECT image quality by minimizing while retaining details.A novel reconstruction method was proposed exploiting nonlocal tensor similarity among interchannel images...

Image reconstruction for realistic medical images under incomplete observation is still one of the core tasks computed tomography (CT). However, stair-case artifacts Total variation (TV) based ones have restricted usage reconstructed images.This work aims to propose and test an accurate efficient algorithm improve quality idea synergy between local nonlocal regularizations.The total combining means filtration proposed alternating direction method multipliers utilized develop algorithm. The...