Low-dose X-ray CT reconstruction via dictionary learning

Learning low-dose CT degradation from unpaired data with flow-based model

BACKGROUND

There has been growing interest in low-dose computed tomography (LDCT) for reducing the X-ray radiation to patients. However, LDCT always suffers from complex noise in reconstructed images. Although deep learning-based methods have shown their strong performance in LDCT denoising, most of them require a large number of paired training data of normal-dose CT (NDCT) images and LDCT images, which are hard to acquire in the clinic. Lack of paired training data significantly undermines the practicability of supervised deep learning-based methods. To alleviate this problem, unsupervised or weakly supervised deep learning-based methods are required.

PURPOSE

We aimed to propose a method that achieves LDCT denoising without training pairs. Specifically, we first trained a neural network in a weakly supervised manner to simulate LDCT images from NDCT images. Then, simulated training pairs could be used for supervised deep denoising networks.

METHODS

We proposed a weakly supervised method to learn the degradation of LDCT from unpaired LDCT and NDCT images. Concretely, LDCT and normal-dose images were fed into one shared flow-based model and projected to the latent space. Then, the degradation between low-dose and normal-dose images was modeled in the latent space. Finally, the model was trained by minimizing the negative log-likelihood loss with no requirement of paired training data. After training, an NDCT image can be input to the trained flow-based model to generate the corresponding LDCT image. The simulated image pairs of NDCT and LDCT can be further used to train supervised denoising neural networks for test.

RESULTS

Our method achieved much better performance on LDCT image simulation compared with the most widely used image-to-image translation method, CycleGAN, according to the radial noise power spectrum. The simulated image pairs could be used for any supervised LDCT denoising neural networks. We validated the effectiveness of our generated image pairs on a classic convolutional neural network, REDCNN, and a novel transformer-based model, TransCT. Our method achieved mean peak signal-to-noise ratio (PSNR) of 24.43dB, mean structural similarity (SSIM) of 0.785 on an abdomen CT dataset, mean PSNR of 33.88dB, mean SSIM of 0.797 on a chest CT dataset, which outperformed several traditional CT denoising methods, the same network trained by CycleGAN-generated data, and a novel transfer learning method. Besides, our method was on par with the supervised networks in terms of visual effects.

CONCLUSION

We proposed a flow-based method to learn LDCT degradation from only unpaired training data. It achieved impressive performance on LDCT synthesis. Next, we could train neural networks with the generated paired data for LDCT denoising. The denoising results are better than traditional and weakly supervised methods, comparable to supervised deep learning methods.

ERA-WGAT: Edge-enhanced residual autoencoder with a window-based graph attention convolutional network for low-dose CT denoising

Computed tomography (CT) has become a powerful tool for medical diagnosis. However, minimizing X-ray radiation risk for the patient poses significant challenges to obtain suitable low dose CT images. Although various low-dose CT methods using deep learning techniques have produced impressive results, convolutional neural network based methods focus more on local information and hence are very limited for non-local information extraction. This paper proposes ERA-WGAT, a residual autoencoder incorporating an edge enhancement module that performs convolution with eight types of learnable operators providing rich edge information and a window-based graph attention convolutional network that combines static and dynamic attention modules to explore non-local self-similarity. We use the compound loss function that combines MSE loss and multi-scale perceptual loss to mitigate the over-smoothing problem. Compared with current low-dose CT denoising methods, ERA-WGAT confirmed superior noise suppression and perceived image quality.

Synchrotron microtomography image restoration via regularization representation and deep CNN prior

BACKGROUND AND OBJECTIVE

Synchrotron-based X-ray microtomography (S-µCT) is a promising imaging technique that plays an important role in modern medical science. S-µCT systems often cause various artifacts and noises in the reconstructed CT images, such as ring artifacts, quantum noise, and electronic noise. In most situations, such noise and artifacts occur simultaneously, which results in a deterioration in the image quality and affects subsequent research. Due to the complexity of the distribution of these mixed artifacts and noise, it is difficult to restore the corrupted images. To address this issue, we propose a novel algorithm to remove mixed artifacts and noise from S-µCT images simultaneously.

METHODS

There are two important aspects of our method. Regarding ring artifacts, because of their specific structural characteristics, regularization-based methods are more suitable; thus, low-rank tensor decomposition and total variation are utilized to represent their directional and locally piecewise smoothness properties. Moreover, to determine the implicit prior of the random noise, a convolutional neural network (CNN) based method is used. The advantages of traditional regularization and the deep CNN are then combined and embedded in a plug-and-play framework. Hence, an efficient image restoration algorithm is proposed to address the problem of mixed artifacts and noise in S-µCT images.

RESULTS

Our proposed method was assessed by utilizing simulations and real data experiments. The qualitative results showed that the proposed method could effectively remove ring artifacts as well as random noise. The quantitative results demonstrated that the proposed method achieved almost the best results in terms of PSNR, SSIM and MAE compared to other methods.

CONCLUSIONS

The proposed method can serve as an effective tool for restoring corrupted S-µCT images, and it has the potential to promote the application of S-µCT.

Statistical Interior Tomography via L1 Norm Dictionary Learning without Assuming an Object Support

Interior tomography of X-ray computed tomography (CT) has many advantages, such as a lower radiation dose and lower detector hardware cost compared to traditional CT. However, this imaging technique only uses the projection data passing through the region of interest (ROI) for imaging; accordingly, the projection data are truncated at both ends of the detector, so the traditional analytical reconstruction algorithm cannot satisfy the demand of clinical diagnosis. To solve the above limitations, in this paper we propose a high-quality statistical iterative reconstruction algorithm that uses the zeroth-order image moment as novel prior knowledge; the zeroth-order image moment can be estimated in the projection domain using the Helgason–Ludwig consistency condition. Then, the L1norm of sparse representation, in terms of dictionary learning, and the zeroth-order image moment constraints are incorporated into the statistical iterative reconstruction framework to construct an objective function. Finally, the objective function is minimized using an alternating minimization iterative algorithm. The chest CT image simulated and CT real data experimental results demonstrate that the proposed approach can remove shift artifacts effectively and has superior performance in removing noise and persevering fine structures than the total variation (TV)-based approach.

Method for restoration of X-ray absorption fine structure in sparse spectroscopic ptychography

The spectroscopic ptychography method, a technique combining X-ray ptychography imaging and X-ray absorption spectroscopy, is one of the most promising and powerful tools for studying the chemical states and morphological structures of bulk materials at high resolutions. However, this technique still requires long measurement periods because of insufficient coherent X-ray intensity. Although the improvements in hardware represent a critical solution, breakthroughs in software for experiments and analyses are also required. This paper proposes a novel method for restoring the spectrum structures from spectroscopic ptychography measurements with reduced energy points, by utilizing the Kramers–Kronig relationship. First, a numerical simulation is performed of the spectrum restoration for the extended X-ray absorption fine structure (EXAFS) oscillation from the thinned theoretical absorption and phase spectra. Then, this algorithm is extended by binning the noise removal to handle actual experimental spectral data. Spectrum restoration for the experimental EXAFS data obtained from spectroscopic ptychography measurements is also successfully demonstrated. The proposed restoration will help shorten the time required for spectroscopic ptychography single measurements and increase the throughput of the entire experiment under limited time resources.

DIOR: Deep Iterative Optimization-Based Residual-Learning for Limited-Angle CT Reconstruction

Limited-angle CT is a challenging problem in real applications. Incomplete projection data will lead to severe artifacts and distortions in reconstruction images. To tackle this problem, we propose a novel reconstruction framework termed Deep Iterative Optimization-based Residual-learning (DIOR) for limited-angle CT. Instead of directly deploying the regularization term on image space, the DIOR combines iterative optimization and deep learning based on the residual domain, significantly improving the convergence property and generalization ability. Specifically, the asymmetric convolutional modules are adopted to strengthen the feature extraction capacity in smooth regions for deep priors. Besides, in our DIOR method, the information contained in low-frequency and high-frequency components is also evaluated by perceptual loss to improve the performance in tissue preservation. Both simulated and clinical datasets are performed to validate the performance of DIOR. Compared with existing competitive algorithms, quantitative and qualitative results show that the proposed method brings a promising improvement in artifact removal, detail restoration and edge preservation.

[Low-dose helical CT projection data restoration using noise estimation]

OBJECTIVE

To build a helical CT projection data restoration model at random low-dose levels.

METHODS

We used a noise estimation module to achieve noise estimation and obtained a low-dose projection noise variance map, which was used to guide projection data recovery by the projection data restoration module. A filtering back-projection algorithm (FBP) was finally used to reconstruct the images. The 3D wavelet group residual dense network (3DWGRDN) was adopted to build the network architecture of the noise estimation and projection data restoration module using asymmetric loss and total variational regularization. For validation of the model, 1/10 and 1/15 of normal dose helical CT images were restored using the proposed model and 3 other restoration models (IRLNet, REDCNN and MWResNet), and the results were visually and quantitatively compared.

RESULTS

Quantitative comparisons of the restored images showed that the proposed helical CT projection data restoration model increased the structural similarity index by 5.79% to 17.46% compared with the other restoration algorithms (P < 0.05). The image quality scores of the proposed method rated by clinical radiologists ranged from 7.19% to 17.38%, significantly higher than the other restoration algorithms (P < 0.05).

CONCLUSION

The proposed method can effectively suppress noises and reduce artifacts in the projection data at different low-dose levels while preserving the integrity of the edges and fine details of the reconstructed CT images.

MRCON-Net: Multiscale reweighted convolutional coding neural network for low-dose CT imaging

BACKGROUND AND OBJECTIVE

Low-dose computed tomography (LDCT) has become increasingly important for alleviating X-ray radiation damage. However, reducing the administered radiation dose may lead to degraded CT images with amplified mottle noise and nonstationary streak artifacts. Previous studies have confirmed that deep learning (DL) is promising for improving LDCT imaging. However, most DL-based frameworks are built intuitively, lack interpretability, and suffer from image detail information loss, which has become a general challenging issue.

METHODS

A multiscale reweighted convolutional coding neural network (MRCON-Net) is developed to address the above problems. MRCON-Net is compact and more explainable than other networks. First, inspired by the learning-based reweighted iterative soft thresholding algorithm (ISTA), we extend traditional convolutional sparse coding (CSC) to its reweighted convolutional learning form. Second, we use dilated convolution to extract multiscale image features, allowing our single model to capture the correlations between features of different scales. Finally, to automatically adjust the elements in the feature code to correct the obtained solution, a channel attention (CA) mechanism is utilized to learn appropriate weights.

RESULTS

The visual results obtained based on the American Association of Physicians in Medicine (AAPM) Challenge and United Image Healthcare (UIH) clinical datasets confirm that the proposed model significantly reduces serious artifact noise while retaining the desired structures. Quantitative results show that the average structural similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) achieved on the AAPM Challenge dataset are 0.9491 and 40.66, respectively, and the SSIM and PSNR achieved on the UIH clinical dataset are 0.915 and 42.44, respectively; these are promising quantitative results.

CONCLUSION

Compared with recent state-of-the-art methods, the proposed model achieves subtle structure-enhanced LDCT imaging. In addition, through ablation studies, the components of the proposed model are validated to achieve performance improvements.

Low-Dose CT Image Post-Processing Based on Learn-Type Sparse Transform

As a detection method, X-ray Computed Tomography (CT) technology has the advantages of clear imaging, short detection time, and low detection cost. This makes it more widely used in clinical disease screening, detection, and disease tracking. This study exploits the ability of sparse representation to learn sparse transformations of information and combines it with image decomposition theory. The structural information of low-dose CT images is separated from noise and artifact information, and the sparse expression of sparse transformation is used to improve the imaging effect. In this paper, two different learned sparse transformations are used. The first covers more organizational information about the scanned object. The other can cover more noise artifacts. Both methods can improve the ability to learn sparse transformations to express various image information. Experimental results show that the algorithm is effective.

Convex optimization algorithms in medical image reconstruction-in the age of AI

The past decade has seen the rapid growth of model based image reconstruction (MBIR) algorithms, which are often applications or adaptations of convex optimization algorithms from the optimization community. We review some state-of-the-art algorithms that have enjoyed wide popularity in medical image reconstruction, emphasize known connections between different algorithms, and discuss practical issues such as computation and memory cost. More recently, deep learning (DL) has forayed into medical imaging, where the latest development tries to exploit the synergy between DL and MBIR to elevate the MBIR's performance. We present existing approaches and emerging trends in DL-enhanced MBIR methods, with particular attention to the underlying role of convexity and convex algorithms on network architecture. We also discuss how convexity can be employed to improve the generalizability and representation power of DL networks in general.

Multi-channel convolutional analysis operator learning for dual-energy CT reconstruction

Objective. Dual-energy computed tomography (DECT) has the potential to improve contrast and reduce artifacts and the ability to perform material decomposition in advanced imaging applications. The increased number of measurements results in a higher radiation dose, and it is therefore essential to reduce either the number of projections for each energy or the source x-ray intensity, but this makes tomographic reconstruction more ill-posed. Approach. We developed the multi-channel convolutional analysis operator learning (MCAOL) method to exploit common spatial features within attenuation images at different energies and we propose an optimization method which jointly reconstructs the attenuation images at low and high energies with mixed norm regularization on the sparse features obtained by pre-trained convolutional filters through the convolutional analysis operator learning (CAOL) algorithm. Main results. Extensive experiments with simulated and real computed tomography data were performed to validate the effectiveness of the proposed methods, and we report increased reconstruction accuracy compared with CAOL and iterative methods with single and joint total variation regularization. Significance. Qualitative and quantitative results on sparse views and low-dose DECT demonstrate that the proposed MCAOL method outperforms both CAOL applied on each energy independently and several existing state-of-the-art model-based iterative reconstruction techniques, thus paving the way for dose reduction.

ADMM-SVNet: An ADMM-Based Sparse-View CT Reconstruction Network

In clinical medical applications, sparse-view computed tomography (CT) imaging is an effective method for reducing radiation doses. The iterative reconstruction method is usually adopted for sparse-view CT. In the process of optimizing the iterative model, the approach of directly solving the quadratic penalty function of the objective function can be expected to perform poorly. Compared with the direct solution method, the alternating direction method of multipliers (ADMM) algorithm can avoid the ill-posed problem associated with the quadratic penalty function. However, the regularization items, sparsity transform, and parameters in the traditional ADMM iterative model need to be manually adjusted. In this paper, we propose a data-driven ADMM reconstruction method that can automatically optimize the above terms that are difficult to choose within an iterative framework. The main contribution of this paper is that a modified U-net represents the sparse transformation, and the prior information and related parameters are automatically trained by the network. Based on a comparison with other state-of-the-art reconstruction algorithms, the qualitative and quantitative results show the effectiveness of our method for sparse-view CT image reconstruction. The experimental results show that the proposed method performs well in streak artifact elimination and detail structure preservation. The proposed network can deal with a wide range of noise levels and has exceptional performance in low-dose reconstruction tasks.

Low-dose computed tomography image reconstruction via a multistage convolutional neural network with autoencoder perceptual loss network

BACKGROUND

Computed tomography (CT) is widely used in medical diagnoses due to its ability to non-invasively detect the internal structures of the human body. However, CT scans with normal radiation doses can cause irreversible damage to patients. The radiation exposure is reduced with low-dose CT (LDCT), although considerable speckle noise and streak artifacts in CT images and even structural deformation may result, significantly undermining its diagnostic capability.

METHODS

This paper proposes a multistage network framework which gradually divides the entire process into 2-staged sub-networks to complete the task of image reconstruction. Specifically, a dilated residual convolutional neural network (DRCNN) was used to denoise the LDCT image. Then, the learned context information was combined with the channel attention subnet, which retains local information, to preserve the structural details and features of the image and textural information. To obtain recognizable characteristic details, we introduced a novel self-calibration module (SCM) between the 2 stages to reweight the local features, which realizes the complementation of information at different stages while refining feature information. In addition, we also designed an autoencoder neural network, using a self-supervised learning scheme to train a perceptual loss neural network specifically for CT images.

RESULTS

We evaluated the diagnostic quality of the results and performed ablation experiments on the loss function and network structure modules to verify each module's effectiveness in the network. Our proposed network architecture obtained high peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual information fidelity (VIF) values in terms of quantitative evaluation. In the analysis of qualitative results, our network structure maintained a better balance between eliminating image noise and preserving image details. Experimental results showed that our proposed network structure obtained better metrics and visual evaluation.

CONCLUSIONS

This study proposed a new LDCT image reconstruction method by combining autoencoder perceptual loss networks with multistage convolutional neural networks (MSCNN). Experimental results showed that the newly proposed method has performance than other methods.

Combining convolutional sparse coding with total variation for sparse-view CT reconstruction

Conventional dictionary-learning-based computed tomography (CT) reconstruction methods extract patches from an original image to train, ignoring the consistency of pixels in overlapping patches. To address the problem, this paper proposes a method combining convolutional sparse coding (CSC) with total variation (TV) for sparse-view CT reconstruction. The proposed method inherits the advantages of CSC by directly processing the whole image without dividing it into overlapping patches, which preserves more details and reduces artifacts caused by patch aggregation. By introducing a TV regularization term to enhance the constraint of the image domain, the noise can be effectively further suppressed. The alternating direction method of multipliers algorithm is employed to solve the objective function. Numerous experiments are conducted to validate the performance of the proposed method in different views. Qualitative and quantitative results show the superiority of the proposed method in terms of noise suppression, artifact reduction, and image details recovery.

A Limited-View CT Reconstruction Framework Based on Hybrid Domains and Spatial Correlation

Limited-view Computed Tomography (CT) can be used to efficaciously reduce radiation dose in clinical diagnosis, it is also adopted when encountering inevitable mechanical and physical limitation in industrial inspection. Nevertheless, limited-view CT leads to severe artifacts in its imaging, which turns out to be a major issue in the low dose protocol. Thus, how to exploit the limited prior information to obtain high-quality CT images becomes a crucial issue. We notice that almost all existing methods solely focus on a single CT image while neglecting the solid fact that, the scanned objects are always highly spatially correlated. Consequently, there lies bountiful spatial information between these acquired consecutive CT images, which is still largely left to be exploited. In this paper, we propose a novel hybrid-domain structure composed of fully convolutional networks that groundbreakingly explores the three-dimensional neighborhood and works in a “coarse-to-fine” manner. We first conduct data completion in the Radon domain, and transform the obtained full-view Radon data into images through FBP. Subsequently, we employ the spatial correlation between continuous CT images to productively restore them and then refine the image texture to finally receive the ideal high-quality CT images, achieving PSNR of 40.209 and SSIM of 0.943. Besides, unlike other current limited-view CT reconstruction methods, we adopt FBP (and implement it on GPUs) instead of SART-TV to significantly accelerate the overall procedure and realize it in an end-to-end manner.

Framelet tensor sparsity with block matching for spectral CT reconstruction

PURPOSE

Spectral computed tomography (CT) based on the photon-counting detection system has the capability to produce energy-discriminative attenuation maps of objects with a single scan. However, the insufficiency of photons collected into the narrow energy bins results in high quantum noise levels causing low image quality. This work aims to improve spectral CT image quality by developing a novel regularization based on framelet tensor prior.

METHODS

First, similar patches are extracted from highly correlated inter-channel images in spectral and spatial domains, and stacked to form a third-order tensor after vectorization along the energy channels. Second, the framelet tensor nuclear norm (FTNN) is introduced and applied to construct the regularization to exploit the sparsity embedded in nonlocal similarity of spectral images, and thus the reconstruction problem is modeled as a constrained optimization. Third, an iterative algorithm is proposed by utilizing the alternating direction method of multipliers framework in which efficient solvers are developed for each subproblem.

RESULTS

Both numerical simulations and real data verifications were performed to evaluate and validate the proposed FTNN based method. Compared to the analytic, TV-based, and the state-of-the-art tensor-based methods, the proposed method achieves higher numerical accuracy on both reconstructed CT images and decomposed material maps in the mouse data indicating the capability in noise suppression and detail preservation of the proposed method.

CONCLUSIONS

A framelet tensor sparsity-based iterative algorithm is proposed for spectral reconstruction. The qualitative and quantitative comparisons show a promising improvement of image quality, indicating its promising potential in spectral CT imaging. This article is protected by copyright. All rights reserved.

Tensor Dictionary Learning with an Enhanced Sparsity Constraint for Sparse-View Spectral CT Reconstruction

Spectral computed tomography (CT) can divide collected photons into multi-energy channels and gain multi-channel projections synchronously by using photon-counting detectors. However, reconstructed images usually contain severe noise due to the limited number of photons in the corresponding energy channel. Tensor dictionary learning (TDL)-based methods have achieved better performance, but usually lose image edge information and details, especially from an under-sampling dataset. To address this problem, this paper proposes a method termed TDL with an enhanced sparsity constraint for spectral CT reconstruction. The proposed algorithm inherits the superiority of TDL by exploring the correlation of spectral CT images. Moreover, the method designs a regularization using the L0-norm of the image gradient to constrain images and the difference between images and a prior image in each energy channel simultaneously, further improving the ability to preserve edge information and subtle image details. The split-Bregman algorithm has been applied to address the proposed objective minimization model. Several numerical simulations and realistic preclinical mice are studied to assess the effectiveness of the proposed algorithm. The results demonstrate that the proposed method improves the quality of spectral CT images in terms of noise elimination, edge preservation, and image detail recovery compared to the several existing better methods.

The synthesis of high-energy CT images from low-energy CT images using an improved cycle generative adversarial network

Background

The dose of radiation a patient receives when undergoing dual-energy computed tomography (CT) is of significant concern to the medical community, and balancing the tradeoffs between the level of radiation used and the quality of CT images is challenging. This paper proposes a method of synthesizing high-energy CT (HECT) images from low-energy CT (LECT) images using a neural network that achieves an alternative to HECT scanning by employing an LECT scan, which greatly reduces the radiation dose a patient receives.

Methods

In the training phase, the proposed structure cyclically generates HECT and LECT images to improve the accuracy of extracting edge and texture features. Specifically, we combine multiple connection methods with channel attention (CA) and pixel attention (PA) mechanisms to improve the network's mapping ability of image features. In the prediction phase, we use a model consisting of only the network component that synthesizes HECT images from LECT images.

Results

Our proposed method was conducted on clinical hip CT image data sets from Guizhou Provincial People's Hospital. In a comparison with other available methods [a generative adversarial network (GAN), a residual encoder-to-decoder network with a visual geometry group (VGG) pretrained model (RED-VGG), a Wasserstein GAN (WGAN), and CycleGAN] in terms of metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), normalized mean square error (NMSE), and a visual effect evaluation, the proposed method was found to perform better on each of these evaluation criteria. Compared with the results produced by CycleGAN, the proposed method improved the PSNR by 2.44%, the SSIM by 1.71%, and the NMSE by 15.2%. Furthermore, the differences in the statistical indicators are statistically significant, proving the strength of the proposed method.

Conclusions

The proposed method synthesizes high-energy CT images from low-energy CT images, which significantly reduces both the cost of treatment and the radiation dose received by patients. Based on both image quality score metrics and visual effects comparisons, the results of the proposed method are superior to those obtained by other methods.

Artifact-Assisted multi-level and multi-scale feature fusion attention network for low-dose CT denoising

BACKGROUND AND OBJECTIVE

Since low-dose computed tomography (LDCT) images typically have higher noise that may affect accuracy of disease diagnosis, the objective of this study is to develop and evaluate a new artifact-assisted feature fusion attention (AAFFA) network to extract and reduce image artifact and noise in LDCT images.

METHODS

In AAFFA network, a feature fusion attention block is constructed for local multi-scale artifact feature extraction and progressive fusion from coarse to fine. A multi-level fusion architecture based on skip connection and attention modules is also introduced for artifact feature extraction. Specifically, long-range skip connections are used to enhance and fuse artifact features with different depth levels. Then, the fused shallower features enter channel attention for better extraction of artifact features, and the fused deeper features are sent into pixel attention for focusing on the artifact pixel information. Besides, an artifact channel is designed to provide rich artifact features and guide the extraction of noise and artifact features. The AAPM LDCT Challenge dataset is used to train and test the network. The performance is evaluated by using both visual observation and quantitative metrics including peak signal-noise-ratio (PSNR), structural similarity index (SSIM) and visual information fidelity (VIF).

RESULTS

Using AAFFA network improves the averaged PSNR/SSIM/VIF values of AAPM LDCT images from 43.4961, 0.9595, 0.3926 to 48.2513, 0.9859, 0.4589, respectively.

CONCLUSIONS

The proposed AAFFA network is able to effectively reduce noise and artifacts while preserving object edges. Assessment of visual quality and quantitative index demonstrates the significant improvement compared with other image denoising methods.

Sparse angle CT reconstruction based on group sparse representation

OBJECTIVE

In order to solve the problem of image quality degradation of CT reconstruction under sparse angle projection, we propose to develop and test a new sparse angle CT reconstruction method based on group sparse.

METHODS

In this method, the group-based sparse representation is introduced into the statistical iterative reconstruction framework as a regularization term to construct the objective function. The group-based sparse representation no longer takes a single patch as the minimum unit of sparse representation, while it uses Euclidean distance as a similarity measure, thus it divides similar patch into groups as basic units for sparse representation. This method fully considers the local sparsity and non-local self-similarity of image. The proposed method is compared with several commonly used CT image reconstruction methods including FBP, SART, SART-TV and GSR-SART with experiments carried out on Sheep_Logan phantom and abdominal and pelvic images.

RESULTS

In three experiments, the visual effect of the proposed method is the best. Under 64 projection angles, the lowest RMSE is 0.004776 and the highest VIF is 0.948724. FSIM and SSIM are all higher than 0.98. Under 50 projection angles, the index of the proposed method remains achieving the best image quality.

CONCLUSION

Qualitative and quantitative results of this study demonstrate that this new proposed method can not only remove strip artifacts, but also effectively protect image details.

DuDoDR-Net: Dual-domain data consistent recurrent network for simultaneous sparse view and metal artifact reduction in computed tomography

Sparse-view computed tomography (SVCT) aims to reconstruct a cross-sectional image using a reduced number of x-ray projections. While SVCT can efficiently reduce the radiation dose, the reconstruction suffers from severe streak artifacts, and the artifacts are further amplified with the presence of metallic implants, which could adversely impact the medical diagnosis and other downstream applications. Previous methods have extensively explored either SVCT reconstruction without metallic implants, or full-view CT metal artifact reduction (MAR). The issue of simultaneous sparse-view and metal artifact reduction (SVMAR) remains under-explored, and it is infeasible to directly apply previous SVCT and MAR methods to SVMAR which may yield non-ideal reconstruction quality. In this work, we propose a dual-domain data consistent recurrent network, called DuDoDR-Net, for SVMAR. Our DuDoDR-Net aims to reconstruct an artifact-free image by recurrent image domain and sinogram domain restorations. To ensure the metal-free part of acquired projection data is preserved, we also develop the image data consistent layer (iDCL) and sinogram data consistent layer (sDCL) that are interleaved in our recurrent framework. Our experimental results demonstrate that our DuDoDR-Net is able to produce superior artifact-reduced results while preserving the anatomical structures, that outperforming previous SVCT and SVMAR methods, under different sparse-view acquisition settings.

Low-dose CT reconstruction with Noise2Noise network and testing-time fine-tuning

PURPOSE

Deep learning-based image denoising and reconstruction methods demonstrated promising performance on low-dose CT imaging in recent years. However, most existing deep learning-based low-dose CT reconstruction methods require normal-dose images for training. Sometimes such clean images do not exist such as for dynamic CT imaging or very large patients. The purpose of this work is to develop a low-dose CT image reconstruction algorithm based on deep learning which does not need clean images for training.

METHODS

In this paper, we proposed a novel reconstruction algorithm where the image prior was expressed via the Noise2Noise network, whose weights were fine-tuned along with the image during the iterative reconstruction. The Noise2Noise network built a self-consistent loss by projection data splitting and mapping the corresponding filtered backprojection (FBP) results to each other with a deep neural network. Besides, the network weights are optimized along with the image to be reconstructed under an alternating optimization scheme. In the proposed method, no clean image is needed for network training and the testing-time fine-tuning leads to optimization for each reconstruction.

RESULTS

We used the 2016 Low-dose CT Challenge dataset to validate the feasibility of the proposed method. We compared its performance to several existing iterative reconstruction algorithms that do not need clean training data, including total variation, non-local mean, convolutional sparse coding, and Noise2Noise denoising. It was demonstrated that the proposed Noise2Noise reconstruction achieved better RMSE, SSIM and texture preservation compared to the other methods. The performance is also robust against the different noise levels, hyperparameters, and network structures used in the reconstruction. Furthermore, we also demonstrated that the proposed methods achieved competitive results without any pre-training of the network at all, that is, using randomly initialized network weights during testing. The proposed iterative reconstruction algorithm also has empirical convergence with and without network pre-training.

CONCLUSIONS

The proposed Noise2Noise reconstruction method can achieve promising image quality in low-dose CT image reconstruction. The method works both with and without pre-training, and only noisy data are required for pre-training.

MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold space. The experiments show that our proposed method outperforms both the quantitative and qualitative aspects of state-of-the-art methods. In addition, aided by a projection loss component, our proposed method also demonstrates superior performance for semi-supervised learning. The network can remove most noise while maintaining the details of only 10% (40 slices) of the training data labeled.

Noise Conscious Training of Non Local Neural Network Powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising

The explosive rise of the use of Computer tomography (CT) imaging in medical practice has heightened public concern over the patient's associated radiation dose. On the other hand, reducing the radiation dose leads to increased noise and artifacts, which adversely degrades the scan's interpretability. In recent times, the deep learning-based technique has emerged as a promising method for low dose CT(LDCT) denoising. However, some common bottleneck still exists, which hinders deep learning-based techniques from furnishing the best performance. In this study, we attempted to mitigate these problems with three novel accretions. First, we propose a novel convolutional module as the first attempt to utilize neighborhood similarity of CT images for denoising tasks. Our proposed module assisted in boosting the denoising by a significant margin. Next, we moved towards the problem of non-stationarity of CT noise and introduced a new noise aware mean square error loss for LDCT denoising. The loss mentioned above also assisted to alleviate the laborious effort required while training CT denoising network using image patches. Lastly, we propose a novel discriminator function for CT denoising tasks. The conventional vanilla discriminator tends to overlook the fine structural details and focus on the global agreement. Our proposed discriminator leverage self-attention and pixel-wise GANs for restoring the diagnostic quality of LDCT images. Our method validated on a publicly available dataset of the 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge performed remarkably better than the existing state of the art method. The corresponding source code is available at: https://github.com/reach2sbera/ldct_nonlocal.

CT Reconstruction With PDF: Parameter-Dependent Framework for Data From Multiple Geometries and Dose Levels

The current mainstream computed tomography (CT) reconstruction methods based on deep learning usually need to fix the scanning geometry and dose level, which significantly aggravates the training costs and requires more training data for real clinical applications. In this paper, we propose a parameter-dependent framework (PDF) that trains a reconstruction network with data originating from multiple alternative geometries and dose levels simultaneously. In the proposed PDF, the geometry and dose level are parameterized and fed into two multilayer perceptrons (MLPs). The outputs of the MLPs are used to modulate the feature maps of the CT reconstruction network, which condition the network outputs on different geometries and dose levels. The experiments show that our proposed method can obtain competitive performance compared to the original network trained with either specific or mixed geometry and dose level, which can efficiently save extra training costs for multiple geometries and dose levels.

DRONE: Dual-Domain Residual-based Optimization NEtwork for Sparse-View CT Reconstruction

Deep learning has attracted rapidly increasing attention in the field of tomographic image reconstruction, especially for CT, MRI, PET/SPECT, ultrasound and optical imaging. Among various topics, sparse-view CT remains a challenge which targets a decent image reconstruction from very few projections. To address this challenge, in this article we propose a Dual-domain Residual-based Optimization NEtwork (DRONE). DRONE consists of three modules respectively for embedding, refinement, and awareness. In the embedding module, a sparse sinogram is first extended. Then, sparse-view artifacts are effectively suppressed in the image domain. After that, the refinement module recovers image details in the residual data and image domains synergistically. Finally, the results from the embedding and refinement modules in the data and image domains are regularized for optimized image quality in the awareness module, which ensures the consistency between measurements and images with the kernel awareness of compressed sensing. The DRONE network is trained, validated, and tested on preclinical and clinical datasets, demonstrating its merits in edge preservation, feature recovery, and reconstruction accuracy.

Deep Interactive Denoiser (DID) for X-Ray Computed Tomography

Low-dose computed tomography (LDCT) is desirable for both diagnostic imaging and image-guided interventions. Denoisers are widely used to improve the quality of LDCT. Deep learning (DL)-based denoisers have shown state-of-the-art performance and are becoming mainstream methods. However, there are two challenges to using DL-based denoisers: 1) a trained model typically does not generate different image candidates with different noise-resolution tradeoffs, which are sometimes needed for different clinical tasks; and 2) the model's generalizability might be an issue when the noise level in the testing images differs from that in the training dataset. To address these two challenges, in this work, we introduce a lightweight optimization process that can run on top of any existing DL-based denoiser during the testing phase to generate multiple image candidates with different noise-resolution tradeoffs suitable for different clinical tasks in real time. Consequently, our method allows users to interact with the denoiser to efficiently review various image candidates and quickly pick the desired one; thus, we termed this method deep interactive denoiser (DID). Experimental results demonstrated that DID can deliver multiple image candidates with different noise-resolution tradeoffs and shows great generalizability across various network architectures, as well as training and testing datasets with various noise levels.

Unified Supervised-Unsupervised (SUPER) Learning for X-Ray CT Image Reconstruction

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent machine learning methods for image reconstruction typically involve supervised learning or unsupervised learning, both of which have their advantages and disadvantages. In this work, we propose a unified supervised-unsupervised (SUPER) learning framework for X-ray computed tomography (CT) image reconstruction. The proposed learning formulation combines both unsupervised learning-based priors (or even simple analytical priors) together with (supervised) deep network-based priors in a unified MBIR framework based on a fixed point iteration analysis. The proposed training algorithm is also an approximate scheme for a bilevel supervised training optimization problem, wherein the network-based regularizer in the lower-level MBIR problem is optimized using an upper-level reconstruction loss. The training problem is optimized by alternating between updating the network weights and iteratively updating the reconstructions based on those weights. We demonstrate the learned SUPER models' efficacy for low-dose CT image reconstruction, for which we use the NIH AAPM Mayo Clinic Low Dose CT Grand Challenge dataset for training and testing. In our experiments, we studied different combinations of supervised deep network priors and unsupervised learning-based or analytical priors. Both numerical and visual results show the superiority of the proposed unified SUPER methods over standalone supervised learning-based methods, iterative MBIR methods, and variations of SUPER obtained via ablation studies. We also show that the proposed algorithm converges rapidly in practice.

Multilayer residual sparsifying transform (MARS) model for low-dose CT image reconstruction

PURPOSE

Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly successful for the task of object classification and have been recently introduced to image reconstruction. In this work, we develop a new image reconstruction approach based on a novel multilayer model learned in an unsupervised manner by combining both sparse representations and deep models. The proposed framework extends the classical sparsifying transform model for images to a Multilayer residual sparsifying transform (MARS) model, wherein the transform domain data are jointly sparsified over layers. We investigate the application of MARS models learned from limited regular-dose images for low-dose CT reconstruction using penalized weighted least squares (PWLS) optimization.

METHODS

We propose new formulations for multilayer transform learning and image reconstruction. We derive an efficient block coordinate descent algorithm to learn the transforms across layers, in an unsupervised manner from limited regular-dose images. The learned model is then incorporated into the low-dose image reconstruction phase.

RESULTS

Low-dose CT experimental results with both the XCAT phantom and Mayo Clinic data show that the MARS model outperforms conventional methods such as filtered back-projection and PWLS methods based on the edge-preserving (EP) regularizer in terms of two numerical metrics (RMSE and SSIM) and noise suppression. Compared with the single-layer learned transform (ST) model, the MARS model performs better in maintaining some subtle details.

CONCLUSIONS

This work presents a novel data-driven regularization framework for CT image reconstruction that exploits learned multilayer or cascaded residual sparsifying transforms. The image model is learned in an unsupervised manner from limited images. Our experimental results demonstrate the promising performance of the proposed multilayer scheme over single-layer learned sparsifying transforms. Learned MARS models also offer better image quality than typical nonadaptive PWLS methods.

Spatiotemporal structure-aware dictionary learning-based 4D CBCT reconstruction

PURPOSE

Four-dimensional cone-beam computed tomography (4D CBCT) is developed to reconstruct a sequence of phase-resolved images, which could assist in verifying the patient's position and offering information for cancer treatment planning. However, 4D CBCT images suffer from severe streaking artifacts and noise due to the extreme sparse-view CT reconstruction problem for each phase. As a result, it would cause inaccuracy of treatment estimation. The purpose of this paper was to develop a new 4D CBCT reconstruction method to generate a series of high spatiotemporal 4D CBCT images.

METHODS

Considering the advantage of (DL) on representing structural features and correlation between neighboring pixels effectively, we construct a novel DL-based method for the 4D CBCT reconstruction. In this study, both a motion-aware dictionary and a spatially structural 2D dictionary are trained for 4D CBCT by excavating the spatiotemporal correlation among ten phase-resolved images and the spatial information in each image, respectively. Specifically, two reconstruction models are produced in this study. The first one is the motion-aware dictionary learning-based 4D CBCT algorithm, called motion-aware DL based 4D CBCT (MaDL). The second one is the MaDL equipped with a prior knowledge constraint, called pMaDL. Qualitative and quantitative evaluations are performed using a 4D extended cardiac torso (XCAT) phantom, simulated patient data, and two sets of patient data sets. Several state-of-the-art 4D CBCT algorithms, such as the McKinnon-Bates (MKB) algorithm, prior image constrained compressed sensing (PICCS), and the high-quality initial image-guided 4D CBCT reconstruction method (HQI-4DCBCT) are applied for comparison to validate the performance of the proposed MaDL and prior constraint MaDL (pMaDL) pmadl reconstruction frameworks.

RESULTS

Experimental results validate that the proposed MaDL can output the reconstructions with few streaking artifacts but some structural information such as tumors and blood vessels, may still be missed. Meanwhile, the results of the proposed pMaDL demonstrate an improved spatiotemporal resolution of the reconstructed 4D CBCT images. In these improved 4D CBCT reconstructions, streaking artifacts are suppressed primarily and detailed structures are also restored. Regarding the XCAT phantom, quantitative evaluations indicate that an average of 58.70%, 45.25%, and 40.10% decrease in terms of root-mean-square error (RMSE) and an average of 2.10, 1.37, and 1.37 times in terms of structural similarity index (SSIM) are achieved by the proposed pMaDL method when compared with piccs, PICCS, MaDL(2D), and MaDL(2D), respectively. Moreover the proposed pMaDL achieves a comparable performance with HQI-4DCBCT algorithm in terms of RMSE and SSIM metrics. However, pMaDL has a better ability to suppress streaking artifacts than HQI-4DCBCT.

CONCLUSIONS

The proposed algorithm could reconstruct a set of 4D CBCT images with both high spatiotemporal resolution and detailed features preservation. Moreover the proposed pMaDL can effectively suppress the streaking artifacts in the resultant reconstructions, while achieving an overall improved spatiotemporal resolution by incorporating the motion-aware dictionary with a prior constraint into the proposed 4D CBCT iterative framework.

InNetGAN: Inception Network-Based Generative Adversarial Network for Denoising Low-Dose Computed Tomography

Low-dose Computed Tomography (LDCT) has gained a great deal of attention in clinical procedures due to its ability to reduce the patient's risk of exposure to the X-ray radiation. However, reducing the X-ray dose increases the quantum noise and artifacts in the acquired LDCT images. As a result, it produces visually low-quality LDCT images that adversely affect the disease diagnosing and treatment planning in clinical procedures. Deep Learning (DL) has recently become the cutting-edge technology of LDCT denoising due to its high performance and data-driven execution compared to conventional denoising approaches. Although the DL-based models perform fairly well in LDCT noise reduction, some noise components are still retained in denoised LDCT images. One reason for this noise retention is the direct transmission of feature maps through the skip connections of contraction and extraction path-based DL modes. Therefore, in this study, we propose a Generative Adversarial Network with Inception network modules (InNetGAN) as a solution for filtering the noise transmission through skip connections and preserving the texture and fine structure of LDCT images. The proposed Generator is modeled based on the U-net architecture. The skip connections in the U-net architecture are modified with three different inception network modules to filter out the noise in the feature maps passing over them. The quantitative and qualitative experimental results have shown the performance of the InNetGAN model in reducing noise and preserving the subtle structures and texture details in LDCT images compared to the other state-of-the-art denoising algorithms.

Low-Dose CT Image Denoising with Improving WGAN and Hybrid Loss Function

The X-ray radiation from computed tomography (CT) brought us the potential risk. Simply decreasing the dose makes the CT images noisy and diagnostic performance compromised. Here, we develop a novel denoising low-dose CT image method. Our framework is based on an improved generative adversarial network coupling with the hybrid loss function, including the adversarial loss, perceptual loss, sharpness loss, and structural similarity loss. Among the loss function terms, perceptual loss and structural similarity loss are made use of to preserve textural details, and sharpness loss can make reconstruction images clear. The adversarial loss can sharp the boundary regions. The results of experiments show the proposed method can effectively remove noise and artifacts better than the state-of-the-art methods in the aspects of the visual effect, the quantitative measurements, and the texture details.

Image quality guided iterative reconstruction for low-dose CT based on CT image statistics

Iterative reconstruction framework shows predominance in low dose and incomplete data situation. In the iterative reconstruction framework, there are two components, i.e., fidelity term aims to maintain the structure details of the reconstructed object, and the regularization term uses prior information to suppress the artifacts such as noise. A regularization parameter balances them, aiming to find a good trade-off between noise and resolution. Currently, the regularization parameters are selected as a rule of thumb or some prior knowledge assumption is required, which limits practical uses. Furthermore, the computation cost of regularization parameter selection is also heavy. In this paper, we address this problem by introducing CT image quality assessment (IQA) into the iterative reconstruction framework. Several steps are involved during the study. First, we analyze the CT image statistics using the dual dictionary method. Regularities are observed and concluded, revealing the relationship among the regularization parameter, iterations, and CT image quality. Second, with derivation and simplification of DDL procedure, a CT IQA metric named SODVAC is designed. The SODVAC locates the optimal regularization parameter that results in the reconstructed image with distinct structures and with no noise or little noise. Third, we introduce SODVAC into the iterative reconstruction framework and then propose a general image-quality-guided iterative reconstruction (QIR) framework and give a specific framework example (sQIR) by introducing SODVAC into the iterative reconstruction framework. sQIR simultaneously optimizes the reconstructed image and the regularization parameter during the iterations. Results confirm the effectiveness of the proposed method. No prior information needed and low computation cost are the advantages of our method compared with existing state-of-theart L-curve and ZIP selection strategies.

Noise2Context: Context-assisted learning 3D thin-layer for low-dose CT

PURPOSE

Computed tomography (CT) has played a vital role in medical diagnosis, assessment, and therapy planning, etc. In clinical practice, concerns about the increase of x-ray radiation exposure attract more and more attention. To lower the x-ray radiation, low-dose CT (LDCT) has been widely adopted in certain scenarios, while it will induce the degradation of CT image quality. In this paper, we proposed a deep learning-based method that can train denoising neural networks without any clean data.

METHODS

In this work, for 3D thin-slice LDCT scanning, we first drive an unsupervised loss function which was equivalent to a supervised loss function with paired noisy and clean samples when the noise in the different slices from a single scan was uncorrelated and zero-mean. Then, we trained the denoising neural network to map one noise LDCT image to its two adjacent LDCT images in a single 3D thin-layer LDCT scanning, simultaneously. In essence, with some latent assumptions, we proposed an unsupervised loss function to train the denoising neural network in an unsupervised manner, which integrated the similarity between adjacent CT slices in 3D thin-layer LDCT.

RESULTS

Further experiments on Mayo LDCT dataset and a realistic pig head were carried out. In the experiments using Mayo LDCT dataset, our unsupervised method can obtain performance comparable to that of the supervised baseline. With the realistic pig head, our method can achieve optimal performance at different noise levels as compared to all the other methods that demonstrated the superiority and robustness of the proposed Noise2Context.

CONCLUSIONS

In this work, we present a generalizable LDCT image denoising method without any clean data. As a result, our method not only gets rid of the complex artificial image priors but also amounts of paired high-quality training datasets.

A balanced total-variation-Chambolle-Pock algorithm for EPR imaging

Total variation (TV) minimization algorithm is an effective algorithm capable of accurately reconstructing images from sparse projection data in a variety of imaging modalities including computed tomography (CT) and electron paramagnetic resonance imaging (EPRI). The data divergence constrained, TV minimization (DDcTV) model and its Chambolle-Pock (CP) solving algorithm have been proposed for CT. However, when the DDcTV-CP algorithm is applied to 3D EPRI, it suffers from slow convergence rate or divergence. We hypothesize that this is due to the magnitude imbalance between the data fidelity term and the TV regularization term. In this work, we propose a balanced TV (bTV) model incorporating a balance parameter and demonstrate its capability to avoid convergence issues for the 3D EPRI application. Simulation and real experiments show that the DDcTV-CP algorithm cannot guarantee convergence but the bTV-CP algorithm may guarantee convergence and achieve fast convergence by use of an appropriate balance parameter. Experiments also show that underweighting the balance parameter leads to slow convergence, whereas overweighting the balance parameter leads to divergence. The iteration-behavior change-law with the variation of the balance parameter is explained by use of the data tolerance ellipse and gradient descent principle. The findings and insights gained in this work may be applied to other imaging modalities and other constrained optimization problems.

Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer

Limited view tomographic reconstruction aims to reconstruct a tomographic image from a limited number of projection views arising from sparse view or limited angle acquisitions that reduce radiation dose or shorten scanning time. However, such a reconstruction suffers from severe artifacts due to the incompleteness of sinogram. To derive quality reconstruction, previous methods use UNet-like neural architectures to directly predict the full view reconstruction from limited view data; but these methods leave the deep network architecture issue largely intact and cannot guarantee the consistency between the sinogram of the reconstructed image and the acquired sinogram, leading to a non-ideal reconstruction. In this work, we propose a cascaded residual dense spatial-channel attention network consisting of residual dense spatial-channel attention networks and projection data fidelity layers. We evaluate our methods on two datasets. Our experimental results on AAPM Low Dose CT Grand Challenge datasets demonstrate that our algorithm achieves a consistent and substantial improvement over the existing neural network methods on both limited angle reconstruction and sparse view reconstruction. In addition, our experimental results on Deep Lesion datasets demonstrate that our method is able to generate high-quality reconstruction for 8 major lesion types.

PWLS-PR: low-dose computed tomography image reconstruction using a patch-based regularization method based on the penalized weighted least squares total variation approach

BACKGROUND

Radiation exposure computed tomography (CT) scans and the associated risk of cancer in patients have been major clinical concerns. Existing research can achieve low-dose CT imaging by reducing the X-ray current and the number of projections per rotation of the human body. However, this method may produce excessive noise and fringe artifacts in the traditional filtered back projection (FBP)-reconstructed image.

METHODS

To solve this problem, iterative image reconstruction is a promising option to obtain high-quality images from low-dose scans. This paper proposes a patch-based regularization method based on penalized weighted least squares total variation (PWLS-PR) for iterative image reconstruction. This method uses neighborhood patches instead of single pixels to calculate the nonquadratic penalty. The proposed regularization method is more robust than the conventional regularization method in identifying random fluctuations caused by sharp edges and noise. Each iteration of the proposed algorithm can be described in the following three steps: image updating via the total variation based on penalized weighted least squares (PWLS-TV), image smoothing, and pixel-by-pixel image fusion.

RESULTS

Simulation and real-world projection experiments show that the proposed PWLS-PR algorithm achieves a higher image reconstruction performance than similar algorithms. Through the qualitative and quantitative evaluation of simulation experiments, the effectiveness of the method is also verified.

CONCLUSIONS

Furthermore, this study shows that the PWLS-PR method reduces the amount of projection data required for repeated CT scans and has the useful potential to reduce the radiation dose in clinical medical applications.

3D reconstruction of dynamic behaviors of vacuum arcs under transverse magnetic fields via computer tomography

The transverse magnetic field (TMF) contacts make the vacuum arcs deviate from the axisymmetric structure, so complete spatiotemporal evolution information of the plasma cannot be obtained by adopting one- or two-dimensional (2D) diagnostic methods. To address the issues, computer tomography was introduced in this paper. First, a multi-angle diagnostic imaging system based on split fiber bundles was proposed, which used a high-speed camera to simultaneously acquire eight angles of the arc image over time. In addition, a tomography algorithm called the maximum likelihood expectation maximum with Split Bregman denoising was proposed to reconstruct the dynamic spatiotemporal characteristics of the arc under complex conditions. Then, the three-dimensional (3D) distribution of Cu i and Cr i particles inside the contact gap was obtained by adopting optical filters. The 3D distribution of the vacuum arc had shown an obvious asymmetrical pattern under the TMF contacts, and there was a ring-like aggregation zone inside the arc, which can cause severe ablation on the anode contacts. According to the reconstructed 3D distribution of Cu i and Cr i, it is found that the metal vapor was mainly concentrated near the electrode surface and showed a clear distribution of non-uniform aggregates, while the concentration of particles in the gap was low. Moreover, on the cathode surface, the cathode spots moved in the form of groups driven by the TMF, while the anode surface was ablated by the electric arc, and the metal vapor existed in the form of bands.

A review on Deep Learning approaches for low-dose Computed Tomography restoration

Computed Tomography (CT) is a widely use medical image modality in clinical medicine, because it produces excellent visualizations of fine structural details of the human body. In clinical procedures, it is desirable to acquire CT scans by minimizing the X-ray flux to prevent patients from being exposed to high radiation. However, these Low-Dose CT (LDCT) scanning protocols compromise the signal-to-noise ratio of the CT images because of noise and artifacts over the image space. Thus, various restoration methods have been published over the past 3 decades to produce high-quality CT images from these LDCT images. More recently, as opposed to conventional LDCT restoration methods, Deep Learning (DL)-based LDCT restoration approaches have been rather common due to their characteristics of being data-driven, high-performance, and fast execution. Thus, this study aims to elaborate on the role of DL techniques in LDCT restoration and critically review the applications of DL-based approaches for LDCT restoration. To achieve this aim, different aspects of DL-based LDCT restoration applications were analyzed. These include DL architectures, performance gains, functional requirements, and the diversity of objective functions. The outcome of the study highlights the existing limitations and future directions for DL-based LDCT restoration. To the best of our knowledge, there have been no previous reviews, which specifically address this topic.

Low-dose CT imaging via cascaded ResUnet with spectrum loss

The suppression of artifact noise in computed tomography (CT) with a low-dose scan protocol is challenging. Conventional statistical iterative algorithms can improve reconstruction but cannot substantially eliminate large streaks and strong noise elements. In this paper, we present a 3D cascaded ResUnet neural network (Ca-ResUnet) strategy with modified noise power spectrum loss for reducing artifact noise in low-dose CT imaging. The imaging workflow consists of four components. The first component is filtered backprojection (FBP) reconstruction via a domain transformation module for suppressing artifact noise. The second is a ResUnet neural network that operates on the CT image. The third is an image compensation module that compensates for the loss of tiny structures, and the last is a second ResUnet neural network with modified spectrum loss for fine-tuning the reconstructed image. Verification results based on American Association of Physicists in Medicine (AAPM) and United Image Healthcare (UIH) datasets confirm that the proposed strategy significantly reduces serious artifact noise while retaining desired structures.

A material decomposition method for dual-energy CT via dual interactive Wasserstein generative adversarial networks

PURPOSE

Dual-energy computed tomography (DECT) is highly promising for material characterization and identification, whereas reconstructed material-specific images are affected by magnified noise and beam-hardening artifacts. Although various DECT material decomposition methods have been proposed to solve this problem, the quality of the decomposed images is still unsatisfactory, particularly in the image edges. In this study, a data-driven approach using dual interactive Wasserstein generative adversarial networks (DIWGAN) is developed to improve DECT decomposition accuracy and perform edge-preserving images.

METHODS

In proposed DIWGAN, two interactive generators are used to synthesize decomposed images of two basis materials by modeling the spatial and spectral correlations from input DECT reconstructed images, and the corresponding discriminators are employed to distinguish the difference between the generated images and labels. The DECT images reconstructed from high- and low-energy bins are sent to two generators separately, and each generator synthesizes one material-specific image, thereby ensuring the specificity of the network modeling. In addition, the information from different energy bins is exploited through the feature sharing of two generators. During decomposition model training, a hybrid loss function including L₁ loss, edge loss, and adversarial loss is incorporated to preserve the texture and edges in the generated images. Additionally, a selector is employed to define the generator that should be trained in each iteration, which can ensure the modeling ability of two different generators and improve the material decomposition accuracy. The performance of the proposed method is evaluated using digital phantom, XCAT phantom, and real data from a mouse.

RESULTS

On the digital phantom, the regions of bone and soft tissue are strictly and accurately separated using the trained decomposition model. The material densities in different bone and soft-tissue regions are near the ground truth, and the error of material densities is lower than 3 mg/ml. The results from XCAT phantom show that the material-specific images generated by directed matrix inversion and iterative decomposition methods have severe noise and artifacts. Regarding to the learning-based methods, the decomposed images of fully convolutional network (FCN) and butterfly network (Butterfly-Net) still contain varying degrees of artifacts, while proposed DIWGAN can yield high quality images. Compared to Butterfly-Net, the root-mean-square error (RMSE) of soft-tissue images generated by the DIWGAN decreased by 0.01 g/ml, whereas the peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the soft-tissue images reached 31.43 dB and 0.9987, respectively. The mass densities of the decomposed materials are nearest to the ground truth when using the DIWGAN method. The noise standard deviation of the decomposition images reduced by 69%, 60%, 33%, and 21% compared with direct matrix inversion, iterative decomposition, FCN, and Butterfly-Net, respectively. Furthermore, the performance of the mouse data indicates the potential of the proposed material decomposition method in real scanned data.

CONCLUSIONS

A DECT material decomposition method based on deep learning is proposed, and the relationship between reconstructed and material-specific images is mapped by training the DIWGAN model. Results from both the simulation phantoms and real data demonstrate the advantages of this method in suppressing noise and beam-hardening artifacts.

Incorporation of residual attention modules into two neural networks for low-dose CT denoising

PURPOSE

The low-dose computed tomography (CT) imaging can reduce the damage caused by x-ray radiation to the human body. However, low-dose CT images have a different degree of artifacts than conventional CT images, and their resolution is lower than that of conventional CT images, which can affect disease diagnosis by clinicians. Therefore, methods for noise-level reduction and resolution improvement in low-dose CT images have inevitably become a research hotspot in the field of low-dose CT imaging.

METHODS

In this paper, residual attention modules (RAMs) are incorporated into the residual encoder-decoder convolutional neural network (RED-CNN) and generative adversarial network with Wasserstein distance (WGAN) to learn features that are beneficial to improving the performances of denoising networks, and developed models are denoted as RED-CNN-RAM and WGAN-RAM, respectively. In detail, RAM is composed of a multi-scale convolution module and an attention module built on the residual network architecture, where the attention module consists of a channel attention module and a spatial attention module. The residual network architecture solves the problem of network degradation with increased network depth. The function of the attention module is to learn which features are beneficial to reduce the noise level of low-dose CT images to reduce the loss of detail in the final denoising images, which is also the key point of the proposed algorithms.

RESULTS

To develop a robust network for low-dose CT image denoising, multidose-level torso phantom images provided by a cooperating equipment vendor are used to train the network, which can improve the network's adaptability to clinical application. In addition, a clinical dataset is used to test the network's migration capabilities and clinical applicability. The experimental results demonstrate that these proposed networks can effectively remove noise and artifacts from multidose CT scans. Subjective and objective analyses of multiple groups of comparison experiments show that the proposed networks achieve good noise suppression performance while preserving the image texture details.

CONCLUSION

In this study, two deep learning network models are developed using multidose-level CT images acquired from a commercial spiral CT scanner. The two network models can reduce and even remove streaking artifacts, and noise from low-dose CT images confirms the effectiveness of the proposed algorithms.

Refined Locally Linear Transform-Based Spectral-Domain Gradient Sparsity and Its Applications in Spectral CT Reconstruction

Spectral computed tomography (CT) is extension of the conventional single spectral CT (SSCT) along the energy dimension, which achieves superior energy resolution and material distinguishability. However, for the state-of-the-art photon counting detector (PCD) based spectral CT, because the emitted photons with a fixed total number for each X-ray beam are divided into several energy bins, the noise level is increased in each reconstructed channel image, and it further leads to an inaccurate material decomposition. To improve the reconstructed image quality and decomposition accuracy, in this work, we first employ a refined locally linear transform to convert the structural similarity among two-dimensional (2D) spectral CT images to a spectral-dimension gradient sparsity. By combining the gradient sparsity in the spatial domain, a global three-dimensional (3D) gradient sparsity is constructed, then measured with L 1-, L 0- and trace-norm, respectively. For each sparsity measurement, we propose the corresponding optimization model, develop the iterative algorithm, and verify the effectiveness and superiority with real datasets.

Modularized data-driven reconstruction framework for nonideal focal spot effect elimination in computed tomography

PURPOSE

High-performance computed tomography (CT) plays a vital role in clinical decision-making. However, the performance of CT imaging is adversely affected by the nonideal focal spot size of the x-ray source or degraded by an enlarged focal spot size due to aging. In this work, we aim to develop a deep learning-based strategy to mitigate the problem so that high spatial resolution CT images can be obtained even in the case of a nonideal x-ray source.

METHODS

To reconstruct high-quality CT images from blurred sinograms via joint image and sinogram learning, a cross-domain hybrid model is formulated via deep learning into a modularized data-driven reconstruction (MDR) framework. The proposed MDR framework comprises several blocks, and all the blocks share the same network architecture and network parameters. In essence, each block utilizes two sub-models to generate an estimated blur kernel and a high-quality CT image simultaneously. In this way, our framework generates not only a final high-quality CT image but also a series of intermediate images with gradually improved anatomical details, enhancing the visual perception for clinicians through the dynamic process. We used simulated training datasets to train our model in an end-to-end manner and tested our model on both simulated and realistic experimental datasets.

RESULTS

On the simulated testing datasets, our approach increases the information fidelity criterion (IFC) by up to 34.2%, the universal quality index (UQI) by up to 20.3%, the signal-to-noise (SNR) by up to 6.7%, and reduces the root mean square error (RMSE) by up to 10.5% as compared with FBP. Compared with the iterative deconvolution method (NSM), MDR increases IFC by up to 24.7%, UQI by up to 16.7%, SNR by up to 6.0%, and reduces RMSE by up to 9.4%. In the modulation transfer function (MTF) experiment, our method improves the MTF_50% by 34.5% and MTF_10% by 18.7% as compared with FBP, Similarly remarkably, our method improves MTF_50% by 14.3% and MTF_10% by 0.9% as compared with NSM. Also, our method shows better imaging results in the edge of bony structures and other tiny structures in the experiments using phantom consisting of ham and a bottle of peanuts.

CONCLUSIONS

A modularized data-driven CT reconstruction framework is established to mitigate the blurring effect caused by a nonideal x-ray source with relatively large focal spot. The proposed method enables us to obtain high-resolution images with less ideal x-ray source.

Prior-image-based CT reconstruction using attenuation-mismatched priors

Prior-image-based reconstruction (PIBR) methods are powerful tools for reducing radiation doses and improving the image quality of low-dose computed tomography (CT). Apart from anatomical changes, prior and current images can also have different attenuations because they originated from different scanners or from the same scanner but with different x-ray beam qualities (e.g., kVp settings, beam filters) during data acquisition. In such scenarios, with attenuation-mismatched priors, PIBR is challenging. In this work, we investigate a specific PIBR method, called statistical image reconstruction, using normal-dose image-induced nonlocal means regularization (SIR-ndiNLM), to address PIBR with such attenuation-mismatched priors and achieve quantitative low-dose CT imaging. We propose two corrective schemes for the original SIR-ndiNLM method, (1) a global histogram-matching approach and (2) a local attenuation correction approach, to account for the attenuation differences between the prior and current images in PIBR. We validate the efficacy of the proposed schemes using images acquired from dual-energy CT scanners to simulate attenuation mismatches. Meanwhile, we utilize different CT slices to simulate anatomical mismatches or changes between the prior and the current low-dose image. We observe that the original SIR-ndiNLM introduces artifacts to the reconstruction when an attenuation-mismatched prior is used. Furthermore, we find that a larger attenuation mismatch between the prior and current images results in more severe artifacts in the SIR-ndiNLM reconstruction. Our two proposed corrective schemes enable SIR-ndiNLM to effectively handle the attenuation mismatch and anatomical changes between the two images and successfully eliminate the artifacts. We demonstrate that the proposed techniques permit SIR-ndiNLM to leverage the attenuation-mismatched prior and achieve quantitative low-dose CT reconstruction from both low-flux and sparse-view data acquisitions. This work permits robust and reliable PIBR for CT data acquired using different beam settings.

Probabilistic self-learning framework for low-dose CT denoising

PURPOSE

Despite the indispensable role of x-ray computed tomography (CT) in diagnostic medicine, the associated harmful ionizing radiation dose is a major concern, as it may cause genetic diseases and cancer. Decreasing patients' exposure can reduce the radiation dose and hence the related risks, but it would inevitably induce higher quantum noise. Supervised deep learning techniques have been used to train deep neural networks for denoising low-dose CT (LDCT) images, but the success of such strategies requires massive sets of pixel-level paired LDCT and normal-dose CT (NDCT) images, which are rarely available in real clinical practice. Our purpose is to mitigate the data scarcity problem for deep learning-based LDCT denoising.

METHODS

To solve this problem, we devised a shift-invariant property-based neural network that uses only the LDCT images to characterize both the inherent pixel correlations and the noise distribution, shaping into our probabilistic self-learning (PSL) framework. The AAPM Low-dose CT Challenge dataset was used to train the network. Both simulated datasets and real dataset were employed to test the denoising performance as well as the model generalizability. The performance was compared to a conventional method (total variation (TV)-based), a popular self-learning method (noise2void (N2V)), and a well-known unsupervised learning method (CycleGAN) by using both qualitative visual inspection and quantitative metrics including peak signal-noise-ratio (PSNR), structural similarity index (SSIM) and contrast-to-noise-ratio (CNR). The standard deviations (STD) of selected flat regions were also calculated for comparison.

RESULTS

The PSL method can improve the averaged PSNR/SSIM values from 27.61/0.5939 (LDCT) to 30.50/0.6797. By contrast, the averaged PSNR/SSIM values were 31.49/0.7284 (TV), 29.43/0.6699 (N2V), and 29.79/0.6992 (CycleGAN). The averaged STDs of selected flat regions were calculated to be 132.3 HU (LDCT), 25.77 HU (TV), 19.95 HU (N2V), 75.06 HU (CycleGAN), 60.62 HU (PSL) and 57.28 HU (NDCT). As for the low-contrast lesion detectability quantification, the CNR were calculated to be 0.202 (LDCT), 0.356 (TV), 0.372 (N2V), 0.383 (CycleGAN), 0.399 (PSL), and 0.359 (NDCT). By visual inspection, we observed that the proposed PSL method can deliver a noise-suppressed and detail-preserved image, while the TV-based method would lead to the blocky artifact, the N2V method would produce over-smoothed structures and CT value biased effect, and the CycleGAN method would generate slightly noisy results with inaccurate CT values. We also verified the generalizability of the PSL method, which exhibited superior denoising performance among various testing datasets with different data distribution shifts.

CONCLUSIONS

A deep learning-based convolutional neural network can be trained without paired datasets. Qualitatively visual inspection showed the proposed PSL method can achieve superior denoising performance than all the competitors, despite that the employed quantitative metrics in terms of PSNR, SSIM and CNR did not always show consistently better values.