Low-dose X-ray CT reconstruction via dictionary learning

A Novel Low-Dose Dual-Energy Imaging Method for a Fast-Rotating Gantry-Type CT Scanner

CT scan by use of a beam-filter placed between the x-ray source and the patient allows a single-scan low-dose dual-energy imaging with a minimal hardware modification to the existing CT systems. We have earlier demonstrated the feasibility of such imaging method with a multi-slit beam-filter reciprocating along the direction perpendicular to the CT rotation axis in a cone-beam CT system. However, such method would face mechanical challenges when the beam-filter is supposed to cooperate with a fast-rotating gantry in a diagnostic CT system. In this work, we propose a new scanning method and associated image reconstruction algorithm that can overcome these challenges. We propose to slide a beam-filter that has multi-slit structure with its slits being at a slanted angle with the CT gantry rotation axis during a scan. A streaky pattern would show up in the sinogram domain as a result. Using a notch filter in the Fourier domain of the sinogram, we removed the streaks and reconstructed an image by use of the filtered-backprojection algorithm. The remaining image artifacts were suppressed by applying l₀ norm based smoothing. Using this image as a prior, we have reconstructed low- and high-energy CT images in the iterative reconstruction framework. An image-based material decomposition then followed. We conducted a simulation study to test its feasibility using the XCAT phantom and also an experimental study using the Catphan phantom, a head phantom, an iodine-solution phantom, and a monkey in anesthesia, and showed its successful performance in image reconstruction and in material decomposition.

Efficient radiation dose reduction in whole-brain CT perfusion imaging using a 3D GAN: Performance and clinical feasibility

Dose reduction in cerebral CT perfusion (CTP) imaging is desirable but is accompanied by an increase in noise that can compromise the image quality and the accuracy of image-based haemodynamic modelling used for clinical decision support in acute ischaemic stroke. The few reported methods aimed at denoising low-dose CTP images lack practicality by considering only small sections of the brain or being computationally expensive. Moreover, the prediction of infarct and penumbra size and location - the chief means of decision support for treatment options - from denoised data has not been explored using these approaches. In this work, we present the first application of a 3D generative adversarial network (3D GAN) for predicting normal-dose CTP data from low-dose CTP data. Feasibility of the approach was tested using real data from 30 acute ischaemic stroke patients in conjunction with low dose simulation. The 3D GAN model was applied to 64^3 voxel patches extracted from two different configurations of the CTP data- frame-based and stacked. The method led to whole-brain denoised data being generated for haemodynamic modelling within 90 seconds. Accuracy of the method was evaluated using standard image quality metrics and the extent to which the clinical content and lesion characteristics of the denoised CTP data were preserved. Results showed an average improvement of 5.15-5.32 dB PSNR and 0.025-0.033 SSIM for CTP images and 2.66-3.95 dB PSNR and 0.036-0.067 SSIM for functional maps at 50% and 25% of normal dose using GAN model in conjunction with a stacked data regime for image synthesis. Consequently, the average lesion volumetric error reduced significantly (p-value < 0.05) by 18-29% and dice coefficient improved significantly by 15-22%. We conclude that GAN-based denoising is a promising practical approach for reducing radiation dose in CTP studies and improving lesion characterisation.

LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks

BACKGROUND

Reducing the radiation tracer dose and scanning time during positron emission tomography (PET) imaging can reduce the cost of the tracer, reduce motion artifacts, and increase the efficiency of the scanner. However, the reconstructed images to be noisy. It is very important to reconstruct high-quality images with low-count (LC) data. Therefore, we propose a deep learning method called LCPR-Net, which is used for directly reconstructing full-count (FC) PET images from corresponding LC sinogram data.

METHODS

Based on the framework of a generative adversarial network (GAN), we enforce a cyclic consistency constraint on the least-squares loss to establish a nonlinear end-to-end mapping process from LC sinograms to FC images. In this process, we merge a convolutional neural network (CNN) and a residual network for feature extraction and image reconstruction. In addition, the domain transform (DT) operation sends a priori information to the cycle-consistent GAN (CycleGAN) network, avoiding the need for a large amount of computational resources to learn this transformation.

RESULTS

The main advantages of this method are as follows. First, the network can use LC sinogram data as input to directly reconstruct an FC PET image. The reconstruction speed is faster than that provided by model-based iterative reconstruction. Second, reconstruction based on the CycleGAN framework improves the quality of the reconstructed image.

CONCLUSIONS

Compared with other state-of-the-art methods, the quantitative and qualitative evaluation results show that the proposed method is accurate and effective for FC PET image reconstruction.

DaNet: dose-aware network embedded with dose-level estimation for low-dose CT imaging

Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on low-dose training data without considering dose differences. However, the radiation dose difference has a great impact on the ultimate results, and lower doses increase the difficulty of restoration. Moreover, there is increasing demand to design and estimate acceptable scanning doses for patients in clinical practice, necessitating dose-aware networks embedded with adaptive dose estimation. In this paper, we consider these dose differences of input LDCT images and propose an adaptive dose-aware network. First, considering a large dose distribution range for simulation convenience, we coarsely define five dose levels in advance as lowest, lower, mild, higher and highest radiation dose levels. Instead of directly building the end-to-end mapping function between LDCT images and high-dose CT counterparts, the dose level is primarily estimated in the first stage. In the second stage, the adaptively learned low-dose level is used to guide the image restoration process as the pattern of prior information through the channel feature transform. We conduct experiments on a simulated dataset based on original high dose parts of American Association of Physicists in Medicine challenge datasets from the Mayo Clinic. Ablation studies validate the effectiveness of the dose-level estimation, and the experimental results show that our method is superior to several other DL-based methods. Specifically, our method provides obviously better performance in terms of the peak signal-to-noise ratio and visual quality reflected in subjective scores. Due to the dual-stage process, our method may suffer limitations under more parameters and coarse dose-level definitions, and thus, further improvements in clinical practical applications with different CT equipment vendors are planned in future work.

Anisotropic structure property based image reconstruction method for limited-angle computed tomography

Limited-angle computed tomography (CT) may appear in restricted CT scans. Since the available projection data is incomplete, the images reconstructed by filtered back-projection (FBP) or algebraic reconstruction technique (ART) often encounter shading artifacts. However, using the anisotropy property of the shading artifacts that coincide with the characteristic of limited-angle CT images can reduce the shading artifacts. Considering this concept, we combine the anisotropy property of the shading artifacts with the anisotropic structure property of an image to develop a new algorithm for image reconstruction. Specifically, we propose an image reconstruction method based on adaptive weighted anisotropic total variation (AwATV). This method, termed as AwATV method for short, is designed to preserve image structures and then remove the shading artifacts. It characterizes both of above properties. The anisotropy property of the shading artifacts accounts for reducing artifacts, and the anisotropic structure property of an image accounts for preserving structures. In order to evaluate the performance of AwATV, we use the simulation projection data of FORBILD head phantom and real CT data for image reconstruction. Experimental results show that AwATV can always reconstruct images with higher SSIM and PSNR, and smaller RMSE, which means that AwATV enables to reconstruct images with higher quality in term of artifact reduction and structure preservation.

Tensor Gradient L₀-Norm Minimization-Based Low-Dose CT and Its Application to COVID-19

Methods to recover high-quality computed tomography (CT) images in low-dose cases will be of great benefit. To reach this goal, sparse-data subsampling is one of the common strategies to reduce radiation dose, which is attracting interest among the researchers in the CT community. Since analytic image reconstruction algorithms may lead to severe image artifacts, the iterative algorithms have been developed for reconstructing images from sparsely sampled projection data. In this study, we first develop a tensor gradient L₀-norm minimization (TGLM) for low-dose CT imaging. Then, the TGLM model is optimized by using the split-Bregman method. The Coronavirus Disease 2019 (COVID-19) has been sweeping the globe, and CT imaging has been deployed for detection and assessing the severity of the disease. Finally, we first apply our proposed TGLM method for COVID-19 to achieve low-dose scan by incorporating the 3-D spatial information. Two COVID-19 patients (64 years old female and 56 years old man) were scanned by the [Formula: see text]CT 528 system, and the acquired projections were retrieved to validate and evaluate the performance of the TGLM.

Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a cube-based 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Compared with traditional coding methods in Fourier domain, the proposed method extends the 3D CSC to a straightforward approach based on the pursuit of localized cubes. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods.

Dictionary learning based image-domain material decomposition for spectral CT

The potential huge advantage of spectral computed tomography (CT) is that it can provide accurate material identification and quantitative tissue information by material decomposition. However, material decomposition is a typical inverse problem, where the noise can be magnified. To address this issue, we develop a dictionary learning based image-domain material decomposition (DLIMD) method for spectral CT to achieve accurate material components with better image quality. Specifically, a set of image patches are extracted from the mode-1 unfolding of normalized material images decomposed by direct inversion to train a unified dictionary using the K-SVD technique. Then, the DLIMD model is established to explore the redundant similarities of the material images, where the split-Bregman is employed to optimize the model. Finally, more constraints (i.e. volume conservation and the bounds of each pixel within material maps) are integrated into the DLIMD model. Numerical phantom, physical phantom and preclinical experiments are performed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery.

Analysis of fast structured dictionary learning

Sparsity-based models and techniques have been exploited in many signal processing and imaging applications. Data-driven methods based on dictionary and sparsifying transform learning enable learning rich image features from data and can outperform analytical models. In particular, alternating optimization algorithms have been popular for learning such models. In this work, we focus on alternating minimization for a specific structured unitary sparsifying operator learning problem and provide a convergence analysis. While the algorithm converges to the critical points of the problem generally, our analysis establishes under mild assumptions, the local linear convergence of the algorithm to the underlying sparsifying model of the data. Analysis and numerical simulations show that our assumptions hold for standard probabilistic data models. In practice, the algorithm is robust to initialization.

Multi-energy CT reconstruction using tensor nonlocal similarity and spatial sparsity regularization

Background

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

Methods

A novel MECT reconstruction method was proposed by exploiting the nonlocal tensor similarity among interchannel images and spatial sparsity in single-channel images. Similar patches were initially extracted from the interchannel images in spectral and spatial domains, then stacked into a new three-order tensor. Intrinsic tensor sparsity regularization that combined the Tuker and canonical polyadic (CP) low-rank decomposition techniques were applied to exploit the nonlocal similarity of the formulated tensor. Spatial sparsity in single-channel images was modeled by total variation (TV) regularization that utilizes the compressibility of gradient image. A new MECT reconstruction model was established by simultaneously incorporating the intrinsic tensor sparsity and TV regularizations. The iterative alternating minimization method was utilized to solve the reconstruction model based on a flexible framework.

Results

The proposed method was applied to the digital phantom and real mouse data to assess its feasibility and reliability. The reconstruction and decomposition results in the mouse data were encouraging and demonstrated the ability of the proposed method in noise suppression while preserving image details, not observed with other methods. Imaging data from the digital phantom illustrated this method as achieving the best intuitive reconstruction and decomposition results among all compared methods. They reduced the root mean square error (RMSE) by 89.75%, 50.75%, and 36.54% on the reconstructed images compared with analytic, TV-based, and tensor-based methods, respectively. This phenomenon was also observed with decomposition results, where the RMSE was also reduced by 97.96%, 67.74%, 72.05%, respectively.

Conclusions

In this study, we proposed a reconstruction method for photon counting detector-based MECT, using the intrinsic tensor sparsity and TV regularizations. Improvements in noise suppression and detail preservation in the digital phantom and real mouse data were validated by the qualitative and quantitative evaluations on the reconstruction and decomposition results, verifying the potential of the proposed method in MECT reconstruction.

Spectral CT Reconstruction via Low-Rank Representation and Region-Specific Texture Preserving Markov Random Field Regularization

Photon-counting spectral computed tomography (CT) is capable of material characterization and can improve diagnostic performance over traditional clinical CT. However, it suffers from photon count starving for each individual energy channel which may cause severe artifacts in the reconstructed images. Furthermore, since the images in different energy channels describe the same object, there are high correlations among different channels. To make full use of the inter-channel correlations and minimize the count starving effect while maintaining clinically meaningful texture information, this paper combines a region-specific texture model with a low-rank correlation descriptor as an a priori regularization to explore a superior texture preserving Bayesian reconstruction of spectral CT. Specifically, the inter-channel correlations are characterized by the low-rank representation, and the inner-channel regional textures are modeled by a texture preserving Markov random field. In other words, this paper integrates the spectral and spatial information into a unified Bayesian reconstruction framework. The widely-used Split-Bregman algorithm is employed to minimize the objective function because of the non-differentiable property of the low-rank representation. To evaluate the tissue texture preserving performance of the proposed method for each channel, three references are built for comparison: one is the traditional CT image from energy integration detection. The second one is spectral images from dual-energy CT. The third one is individual channels images from custom-made photon-counting spectral CT. As expected, the proposed method produced promising results in terms of not only preserving texture features but also suppressing image noise in each channel, comparing to existing methods of total variation (TV), low-rank TV and tensor dictionary learning, by both visual inspection and quantitative indexes of root mean square error, peak signal to noise ratio, structural similarity and feature similarity.

Predicting PET-derived myelin content from multisequence MRI for individual longitudinal analysis in multiple sclerosis

Multiple sclerosis (MS) is a demyelinating and inflammatory disease of the central nervous system (CNS). The demyelination process can be repaired by the generation of a new sheath of myelin around the axon, a process termed remyelination. In MS patients, the demyelination-remyelination cycles are highly dynamic. Over the years, magnetic resonance imaging (MRI) has been increasingly used in the diagnosis of MS and it is currently the most useful paraclinical tool to assess this diagnosis. However, conventional MRI pulse sequences are not specific for pathological mechanisms such as demyelination and remyelination. Recently, positron emission tomography (PET) with radiotracer [¹¹C]PIB has become a promising tool to measure in-vivo myelin content changes which is essential to push forward our understanding of mechanisms involved in the pathology of MS, and to monitor individual patients in the context of clinical trials focused on repair therapies. However, PET imaging is invasive due to the injection of a radioactive tracer. Moreover, it is an expensive imaging test and not offered in the majority of medical centers in the world. In this work, by using multisequence MRI, we thus propose a method to predict the parametric map of [¹¹C]PIB PET, from which we derived the myelin content changes in a longitudinal analysis of patients with MS. The method is based on the proposed conditional flexible self-attention GAN (CF-SAGAN) which is specifically adjusted for high-dimensional medical images and able to capture the relationships between the spatially separated lesional regions during the image synthesis process. Jointly applying the sketch-refinement process and the proposed attention regularization that focuses on the MS lesions, our approach is shown to outperform the state-of-the-art methods qualitatively and quantitatively. Specifically, our method demonstrated a superior performance for the prediction of myelin content at voxel-wise level. More important, our method for the prediction of myelin content changes in patients with MS shows similar clinical correlations to the PET-derived gold standard indicating the potential for clinical management of patients with MS.

Locally linear transform based three-dimensional gradient L 0 -norm minimization for spectral CT reconstruction

PURPOSE

Spectral computed tomography (CT) is proposed by extending the conventional CT along the energy dimension. One newly implementation is to employ an energy-discriminating photon counting detector (PCD), which can distinguish photon energy and divide a whole x-ray spectrum into several energy bins with appropriate post-processing steps. The state-of-the-art PCD-based spectral CT has superior energy resolution and material distinguishability, and it further has a great potential in both medical and industrial applications. To improve the reconstruction quality and decomposition accuracy, in this work, we propose an optimization-based spectral CT reconstruction method with an innovational sparsity constraint.

METHODS

We first employ a locally linear transform to the reconstructed channel images, and the structural similarity along the spectral dimension is effectively converted to a one-dimensional (1D) gradient sparsity. Then, combining the prior knowledge of piecewise constant in the spatial domain (e.g., a two-dimensional (2D) gradient sparsity feature), we unify both spectral and spatial dimensions and establish a joint three-dimensional (3D) gradient sparsity. In addition, we use the L 0 -norm to measure the proposed sparsity and incorporate it as a smoothness constraint to concretize a general optimization framework. Furthermore, we develop the corresponding iterative algorithm to solve the optimization problem.

RESULTS

Both visual results and quantitative indexes of numerical simulations and phantom experiments demonstrate the proposed method outperform the conventional filtered backprojection (FBP), total variation (TV), 2D L₀ -norm (L₀ ), and TV with low rank (TVLR)-based methods. From the image and ROI comparisons, we find the proposed method performs well in noise suppression, detail maintenance, and decomposition accuracy. However, the FBP suffers severe noise, the TV and L₀ are difficult to work consistently among different energy bins, and the TVLR fails to avoid gray value shift. The image quality assessments, such as peak signal-to-noise ratio (PSNR), normal mean absolute deviation (NMAD). and structural similarity (SSIM), also consistently indicate the proposed method can effectively removing noise and keeping fine structures in both channel-wise reconstructions and material decompositions.

CONCLUSIONS

By employing a locally linear transform, the structural similarity among spectral channel images is converted to a 1D gradient sparsity and the gray value shift is effectively avoided when the difference measurement is minimized. The 3D L₀ -norm jointly and uniformly measures the gradient sparsity in both spectral and spatial dimensions. The cooperation of locally linear transform and 3D L₀ -norm well reinforces the global sparse features and keeps the correlation along spectral dimension without bringing gray-value distortions. The corresponding constraint optimization model is fast and stably solved by using an alternative direction technique. Both numerical simulations and phantom experiments confirm the superior performance of the proposed method in noise suppression, structure maintenance, and accurate decomposition.

Neural networks-based regularization for large-scale medical image reconstruction

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks (NNs) and cascaded NNs have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the application of the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by strictly separating the application of the NN, the regularization of the solution and the consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained NN which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative NNs. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude.

SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network

Computed tomography (CT) is a widely used screening and diagnostic tool that allows clinicians to obtain a high-resolution, volumetric image of internal structures in a non-invasive manner. Increasingly, efforts have been made to improve the image quality of low-dose CT (LDCT) to reduce the cumulative radiation exposure of patients undergoing routine screening exams. The resurgence of deep learning has yielded a new approach for noise reduction by training a deep multi-layer convolutional neural networks (CNN) to map the low-dose to normal-dose CT images. However, CNN-based methods heavily rely on convolutional kernels, which use fixed-size filters to process one local neighborhood within the receptive field at a time. As a result, they are not efficient at retrieving structural information across large regions. In this paper, we propose a novel 3D self-attention convolutional neural network for the LDCT denoising problem. Our 3D self-attention module leverages the 3D volume of CT images to capture a wide range of spatial information both within CT slices and between CT slices. With the help of the 3D self-attention module, CNNs are able to leverage pixels with stronger relationships regardless of their distance and achieve better denoising results. In addition, we propose a self-supervised learning scheme to train a domain-specific autoencoder as the perceptual loss function. We combine these two methods and demonstrate their effectiveness on both CNN-based neural networks and WGAN-based neural networks with comprehensive experiments. Tested on the AAPM-Mayo Clinic Low Dose CT Grand Challenge data set, our experiments demonstrate that self-attention (SA) module and autoencoder (AE) perceptual loss function can efficiently enhance traditional CNNs and can achieve comparable or better results than the state-of-the-art methods.

Generative adversarial network based regularized image reconstruction for PET

Positron emission tomography (PET) is an ill-posed inverse problem and suffers high noise due to limited number of detected events. Prior information can be used to improve the quality of reconstructed PET images. Deep neural networks have also been applied to regularized image reconstruction. One method is to use a pretrained denoising neural network to represent the PET image and to perform a constrained maximum likelihood estimation. In this work, we propose to use a generative adversarial network (GAN) to further improve the network performance. We also modify the objective function to include a data-matching term on the network input. Experimental studies using computer-based Monte Carlo simulations and real patient datasets demonstrate that the proposed method leads to noticeable improvements over the kernel-based and U-net-based regularization methods in terms of lesion contrast recovery versus background noise trade-offs.

Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising

Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of "quadratic-neuron-based deep learning". Our prior theoretical studies have shown important merits of quadratic neurons and networks in representation, efficiency, and interpretability. In this paper, we use quadratic neurons to construct an encoder-decoder structure, referred as the quadratic autoencoder, and apply it to low-dose CT denoising. The experimental results on the Mayo low-dose CT dataset demonstrate the utility and robustness of quadratic autoencoder in terms of image denoising and model efficiency. To our best knowledge, this is the first time that the deep learning approach is implemented with a new type of neurons and demonstrates a significant potential in the medical imaging field.

Radon Inversion via Deep Learning

The Radon transform is widely used in physical and life sciences, and one of its major applications is in medical X-ray computed tomography (CT), which is significantly important in disease screening and diagnosis. In this paper, we propose a novel reconstruction framework for Radon inversion with deep learning (DL) techniques. For simplicity, the proposed framework is denoted as iRadonMAP, i.e., inverse Radon transform approximation. Specifically, we construct an interpretable neural network that contains three dedicated components. The first component is a fully connected filtering (FCF) layer along the rotation angle direction in the sinogram domain, and the second one is a sinusoidal back-projection (SBP) layer, which back-projects the filtered sinogram data into the spatial domain. Next, a common network structure is added to further improve the overall performance. iRadonMAP is first pretrained on a large number of generic images from the ImageNet database and then fine-tuned with clinical patient data. The experimental results demonstrate the feasibility of the proposed iRadonMAP framework for Radon inversion.

An Exact and Fast CBCT Reconstruction via Pseudo-Polar Fourier Transform based Discrete Grangeat's Formula

The recent application of Fourier Based Iterative Reconstruction Method (FIRM) has made it possible to achieve high-quality 2D images from a fan beam Computed Tomography (CT) scan with a limited number of projections in a fast manner. The proposed methodology in this article is designed to provide 3D Radon space in linogram fashion to facilitate the use of FIRM with cone beam projections (CBP) for the reconstruction of 3D images in a sparse view angles Cone Beam CT (CBCT). For this reason, in the first phase, the 3D Radon space is generated using CBP data after discretization and optimization of the famous Grangeat's formula. The method used in this process involves fast Pseudo Polar Fourier transform (PPFT) based on 2D and 3D Discrete Radon Transformation (DRT) algorithms with no wraparound effects. In the second phase, we describe reconstruction of the objects with available Radon values, using direct inverse of 3D PPFT. The method presented in this section eliminates noises caused by interpolation from polar to Cartesian space and exhibits no thorn, V-shaped and wrinkle artifacts. This method reduces the complexity to for images of size n × n × n The Cone to Radon conversion (Cone2Radon) Toolbox in the first phase and MATLAB/ Python toolbox in the second phase were tested on three digital phantoms and experiments demonstrate fast and accurate cone beam image reconstruction due to proposed.

DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering

Dual-energy computed tomography (DECT) imaging plays an important role in advanced imaging applications due to its material decomposition capability. Image-domain decomposition operates directly on CT images using linear matrix inversion, but the decomposed material images can be severely degraded by noise and artifacts. This paper proposes a new method dubbed DECT-MULTRA for image-domain DECT material decomposition that combines conventional penalized weighted-least squares (PWLS) estimation with regularization based on a mixed union of learned transforms (MULTRA) model. Our proposed approach pre-learns a union of common-material sparsifying transforms from patches extracted from all the basis materials, and a union of cross-material sparsifying transforms from multi-material patches. The common-material transforms capture the common properties among different material images, while the cross-material transforms capture the cross-dependencies. The proposed PWLS formulation is optimized efficiently by alternating between an image update step and a sparse coding and clustering step, with both of these steps having closed-form solutions. The effectiveness of our method is validated with both XCAT phantom and clinical head data. The results demonstrate that our proposed method provides superior material image quality and decomposition accuracy compared to other competing methods.

Low Dose CT Image Reconstruction Based on Structure Tensor Total Variation Using Accelerated Fast Iterative Shrinkage Thresholding Algorithm

Low dose computed tomography (CT) has drawn much attention in the medical imaging field because of its ability to reduce the radiation dose. Recently, statistical iterative reconstruction (SIR) with total variation (TV) penalty has been developed to low dose CT image reconstruction. Nevertheless, the TV penalty has the drawback of creating blocky effects in the reconstructed images. To overcome the limitations of TV, in this paper we firstly introduce the structure tensor total variation (STV₁) penalty into SIR framework for low dose CT image reconstruction. Then, an accelerated fast iterative shrinkage thresholding algorithm (AFISTA) is developed to minimize the objective function. The proposed AFISTA reconstruction algorithm was evaluated using numerical simulated low dose projection based on two CT images and realistic low dose projection data of a sheep lung CT perfusion. The experimental results demonstrated that our proposed STV₁-based algorithm outperform FBP and TV-based algorithm in terms of removing noise and restraining blocky effects.

SPULTRA: Low-Dose CT Image Reconstruction With Joint Statistical and Learned Image Models

Low-dose CT image reconstruction has been a popular research topic in recent years. A typical reconstruction method based on post-log measurements is called penalized weighted-least squares (PWLS). Due to the underlying limitations of the post-log statistical model, the PWLS reconstruction quality is often degraded in low-dose scans. This paper investigates a shifted-Poisson (SP) model based likelihood function that uses the pre-log raw measurements that better represents the measurement statistics, together with a data-driven regularizer exploiting a Union of Learned TRAnsforms (SPULTRA). Both the SP induced data-fidelity term and the regularizer in the proposed framework are nonconvex. The proposed SPULTRA algorithm uses quadratic surrogate functions for the SP induced data-fidelity term. Each iteration involves a quadratic subproblem for updating the image, and a sparse coding and clustering subproblem that has a closed-form solution. The SPULTRA algorithm has a similar computational cost per iteration as its recent counterpart PWLS-ULTRA that uses post-log measurements, and it provides better image reconstruction quality than PWLS-ULTRA, especially in low-dose scans.

Two stage residual CNN for texture denoising and structure enhancement on low dose CT image

BACKGROUND AND OBJECTIVE

X-ray computed tomography (CT) plays an important role in modern medical science. Human health problems caused by CT radiation have attracted the attention of the academic community widely. Reducing radiation dose results in a deterioration in image quality and further affects doctor's diagnosis. Therefore, this paper introduces a new denoise method for low dose CT (LDCT) images, called two stage residual convolutional neural network (TS-RCNN).

METHODS

There are two important parts with respect to our network. 1) The first stage RCNN is proposed for texture denoising via the stationary wavelet transform (SWT) and the perceptual loss. Specifically, SWT is performed on each normal dose CT (NDCT) image and generated four wavelet images are considered as the labels. 2) The second stage RCNN is established for structure enhancement via the average NDCT model on the basis of the first network's result. Finally, the denoised CT image is obtained via inverse SWT.

RESULTS

Our proposed TS-RCNN is trained on three groups of simulated LDCT images in 1123 images per group and evaluated on 129 simulated LDCT images for each group. Besides, to demonstrate the clinical application of TS-RCNN, we also test our method on the 2016 Low Dose CT Grand Challenge dataset. Quantitative results show that TS-RCNN almost achieves the best results in terms of MSE, SSIM and PSNR compared to other methods.

CONCLUSIONS

The experimental results and comparisons demonstrate that TS-RCNN not only preserves more texture information, but also enhances structural information on LDCT images.

Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning

The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.

Spectrum Estimation-Guided Iterative Reconstruction Algorithm for Dual Energy CT

X-ray spectrum plays a very important role in dual energy computed tomography (DECT) reconstruction. Because it is difficult to measure x-ray spectrum directly in practice, efforts have been devoted into spectrum estimation by using transmission measurements. These measurement methods are independent of the image reconstruction, which bring extra cost and are time consuming. Furthermore, the estimated spectrum mismatch would degrade the quality of the reconstructed images. In this paper, we propose a spectrum estimation-guided iterative reconstruction algorithm for DECT which aims to simultaneously recover the spectrum and reconstruct the image. The proposed algorithm is formulated as an optimization framework combining spectrum estimation based on model spectra representation, image reconstruction, and regularization for noise suppression. To resolve the multi-variable optimization problem of simultaneously obtaining the spectra and images, we introduce the block coordinate descent (BCD) method into the optimization iteration. Both the numerical simulations and physical phantom experiments are performed to verify and evaluate the proposed method. The experimental results validate the accuracy of the estimated spectra and reconstructed images under different noise levels. The proposed method obtains a better image quality compared with the reconstructed images from the known exact spectra and is robust in noisy data applications.

Usefulness of dictionary learning-based processing for improving image quality of sub-millisievert low-dose chest CT: initial experience

PURPOSE

To develop a dictionary learning (DL)-based processing technique for improving the image quality of sub-millisievert chest computed tomography (CT).

MATERIALS AND METHODS

Standard-dose and sub-millisievert chest CT were acquired in 12 patients. Dictionaries including standard- and low-dose image patches were generated from the CT datasets. For each patient, DL-based processing was performed for low-dose CT using the dictionaries generated from the remaining 11 patients. This procedure was repeated for all 12 patients. Image quality of normal thoracic structures on the processed sub-millisievert CT images was assessed with a 5-point scale (5 = excellent, 1 = very poor). Lung lesion conspicuity was also assessed on a 5-point scale.

RESULTS

Image noise on sub-millisievert CT was significantly decreased with DL-based image processing (48.5 ± 13.7 HU vs 20.4 ± 7.9 HU, p = 0.0005). Image quality of lung structures was significantly improved with DL-based method (middle level of lung, 2.25 ± 0.75 vs 2.92 ± 0.79, p = 0.0078). Lung lesion conspicuity was also significantly improved with DL-based technique (solid nodules, 3.4 ± 0.6 vs 2.7 ± 0.6, p = 0.0273).

CONCLUSION

Image quality and lesion conspicuity on sub-millisievert chest CT images may be improved by DL-based post-processing.

Unpaired Low-Dose CT Denoising Network Based on Cycle-Consistent Generative Adversarial Network with Prior Image Information

The widespread application of X-ray computed tomography (CT) in clinical diagnosis has led to increasing public concern regarding excessive radiation dose administered to patients. However, reducing the radiation dose will inevitably cause server noise and affect radiologists' judgment and confidence. Hence, progressive low-dose CT (LDCT) image reconstruction methods must be developed to improve image quality. Over the past two years, deep learning-based approaches have shown impressive performance in noise reduction for LDCT images. Most existing deep learning-based approaches usually require the paired training dataset which the LDCT images correspond to the normal-dose CT (NDCT) images one-to-one, but the acquisition of well-paired datasets requires multiple scans, resulting the increase of radiation dose. Therefore, well-paired datasets are not readily available. To resolve this problem, this paper proposes an unpaired LDCT image denoising network based on cycle generative adversarial networks (CycleGAN) with prior image information which does not require a one-to-one training dataset. In this method, cyclic loss, an important trick in unpaired image-to-image translation, promises to map the distribution from LDCT to NDCT by using unpaired training data. Furthermore, to guarantee the accurate correspondence of the image content between the output and NDCT, the prior information obtained from the result preprocessed using the LDCT image is integrated into the network to supervise the generation of content. Given the map of distribution through the cyclic loss and the supervision of content through the prior image loss, our proposed method can not only reduce the image noise but also retain critical information. Real-data experiments were carried out to test the performance of the proposed method. The peak signal-to-noise ratio (PSNR) improves by more than 3 dB, and the structural similarity (SSIM) increases when compared with the original CycleGAN without prior information. The real LDCT data experiment demonstrates the superiority of the proposed method according to both visual inspection and quantitative evaluation.

Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging

The wide applications of X-ray computed tomography (CT) bring low-dose CT (LDCT) into a clinical prerequisite, but reducing the radiation exposure in CT often leads to significantly increased noise and artifacts, which might lower the judgment accuracy of radiologists. In this paper, we put forward a domain progressive 3D residual convolution network (DP-ResNet) for the LDCT imaging procedure that contains three stages: sinogram domain network (SD-net), filtered back projection (FBP), and image domain network (ID-net). Though both are based on the residual network structure, the SD-net and ID-net provide complementary effect on improving the final LDCT quality. The experimental results with both simulated and real projection data show that this domain progressive deep-learning network achieves significantly improved performance by combing the network processing in the two domains.

Convolutional Sparse Coding for Compressed Sensing CT Reconstruction

Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, the traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. The qualitative and quantitative results demonstrate that the proposed methods achieve better performance than the several existing state-of-the-art methods.

Sparsity promoting regularization for effective noise suppression in SPECT image reconstruction

The purpose of this research is to develop an advanced reconstruction method for low-count, hence high-noise, single-photon emission computed tomography (SPECT) image reconstruction. It consists of a novel reconstruction model to suppress noise while conducting reconstruction and an efficient algorithm to solve the model. A novel regularizer is introduced as the nonconvex denoising term based on the approximate sparsity of the image under a geometric tight frame transform domain. The deblurring term is based on the negative log-likelihood of the SPECT data model. To solve the resulting nonconvex optimization problem a preconditioned fixed-point proximity algorithm (PFPA) is introduced. We prove that under appropriate assumptions, PFPA converges to a local solution of the optimization problem at a global O ( 1 / k ) convergence rate. Substantial numerical results for simulation data are presented to demonstrate the superiority of the proposed method in denoising, suppressing artifacts and reconstruction accuracy. We simulate noisy 2D SPECT data from two phantoms: hot Gaussian spheres on random lumpy warm background, and the anthropomorphic brain phantom, at high- and low-noise levels (64k and 90k counts, respectively), and reconstruct them using PFPA. We also perform limited comparative studies with selected competing state-of-the-art total variation (TV) and higher-order TV (HOTV) transform-based methods, and widely used post-filtered maximum-likelihood expectation-maximization. We investigate imaging performance of these methods using: contrast-to-noise ratio (CNR), ensemble variance images (EVI), background ensemble noise (BEN), normalized mean-square error (NMSE), and channelized hotelling observer (CHO) detectability. Each of the competing methods is independently optimized for each metric. We establish that the proposed method outperforms the other approaches in all image quality metrics except NMSE where it is matched by HOTV. The superiority of the proposed method is especially evident in the CHO detectability tests results. We also perform qualitative image evaluation for presence and severity of image artifacts where it also performs better in terms of suppressing 'staircase' artifacts, as compared to TV methods. However, edge artifacts on high-contrast regions persist. We conclude that the proposed method may offer a powerful tool for detection tasks in high-noise SPECT imaging.

Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning

Tomographic imaging via penetrating waves generates cross-sectional views of the internal anatomy of a living subject. For artefact-free volumetric imaging, projection views from a large number of angular positions are required. Here, we show that a deep-learning model trained to map projection radiographs of a patient to the corresponding 3D anatomy can subsequently generate volumetric tomographic X-ray images of the patient from a single projection view. We demonstrate the feasibility of the approach with upper-abdomen, lung, and head-and-neck computed tomography scans from three patients. Volumetric reconstruction via deep learning could be useful in image-guided interventional procedures such as radiation therapy and needle biopsy, and might help simplify the hardware of tomographic imaging systems.

Computationally efficient deep neural network for computed tomography image reconstruction

PURPOSE

Deep neural network-based image reconstruction has demonstrated promising performance in medical imaging for undersampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is especially challenging to train the reconstruction networks for three-dimensional computed tomography (CT) because of the high resolution of CT images. The purpose of this work is to reduce the memory and time consumption of the training of the reconstruction networks for CT to make it practical for current hardware, while maintaining the quality of the reconstructed images.

METHODS

We unrolled the proximal gradient descent algorithm for iterative image reconstruction to finite iterations and replaced the terms related to the penalty function with trainable convolutional neural networks (CNN). The network was trained greedily iteration by iteration in the image domain on patches, which requires reasonable amount of memory and time on mainstream graphics processing unit (GPU). To overcome the local-minimum problem caused by greedy learning, we used deep UNet as the CNN and incorporated separable quadratic surrogate with ordered subsets for data fidelity, so that the solution could escape from easy local minimums and achieve better image quality.

RESULTS

The proposed method achieved comparable image quality with state-of-the-art neural network for CT image reconstruction on two-dimensional (2D) sparse-view and limited-angle problems on the low-dose CT challenge dataset. The difference in root-mean-square-error (RMSE) and structural similarity index (SSIM) was within [-0.23,0.47] HU and [0,0.001], respectively, with 95% confidence level. For three-dimensional (3D) image reconstruction with ordinary-size CT volume, the proposed method only needed 2 GB graphics processing unit (GPU) memory and 0.45 s per training iteration as minimum requirement, whereas existing methods may require 417 GB and 31 min. The proposed method achieved improved performance compared to total variation- and dictionary learning-based iterative reconstruction for both 2D and 3D problems.

CONCLUSIONS

We proposed a training-time computationally efficient neural network for CT image reconstruction. The proposed method achieved comparable image quality with state-of-the-art neural network for CT reconstruction, with significantly reduced memory and time requirement during training. The proposed method is applicable to 3D image reconstruction problems such as cone-beam CT and tomosynthesis on mainstream GPUs.

Image reconstruction for positron emission tomography based on patch-based regularization and dictionary learning

PURPOSE

Positron emission tomography (PET) is an important tool for nuclear medical imaging. It has been widely used in clinical diagnosis, scientific research, and drug testing. PET is a kind of emission computed tomography. Its basic imaging principle is to use the positron annihilation radiation generated by radionuclide decay to generate gamma photon images. However, in practical applications, due to the low gamma photon counting rate, limited acquisition time, inconsistent detector characteristics, and electronic noise, measured PET projection data often contain considerable noise, which results in ill-conditioned PET images. Therefore, determining how to obtain high-quality reconstructed PET images suitable for clinical applications is a valuable research topic. In this context, this paper presents an image reconstruction algorithm based on patch-based regularization and dictionary learning (DL) called the patch-DL algorithm. Compared to other algorithms, the proposed algorithm can retain more image details while suppressing noise.

METHODS

Expectation-maximization (EM)-like image updating, image smoothing, pixel-by-pixel image fusion, and DL are the four steps of the proposed reconstruction algorithm. We used a two-dimensional (2D) brain phantom to evaluate the proposed algorithm by simulating sinograms that contained random Poisson noise. We also quantitatively compared the patch-DL algorithm with a pixel-based algorithm, a patch-based algorithm, and an adaptive dictionary learning (AD) algorithm.

RESULTS

Through computer simulations, we demonstrated the advantages of the patch-DL method over the pixel-, patch-, and AD-based methods in terms of the tradeoff between noise suppression and detail retention in reconstructed images. Quantitative analysis shows that the proposed method results in a better performance statistically [according to the mean absolute error (MAE), correlation coefficient (CORR), and root mean square error (RMSE)] in considered region of interests (ROI) with two simulated count levels. Additionally, to analyze whether the results among these methods have significant differences, we used one-way analysis of variance (ANOVA) to calculate the corresponding P values. The results show that most of the P < 0.01; some P> 0.01 < 0.05. Therefore, our method can achieve a better quantitative performance than those of traditional methods.

CONCLUSIONS

The results show that the proposed algorithm has the potential to improve the quality of PET image reconstruction. Since the proposed algorithm was validated only with simulated 2D data, it still needs to be further validated with real three-dimensional data. In the future, we intend to explore GPU parallelization technology to further improve the computational efficiency and shorten the computation time.

Convolutional Analysis Operator Learning: Acceleration and Convergence

Convolutional operator learning is gaining attention in many signal processing and computer vision applications. Learning kernels has mostly relied on so-called patch-domain approaches that extract and store many overlapping patches across training signals. Due to memory demands, patch-domain methods have limitations when learning kernels from large datasets - particularly with multi-layered structures, e.g., convolutional neural networks - or when applying the learned kernels to high-dimensional signal recovery problems. The so-called convolution approach does not store many overlapping patches, and thus overcomes the memory problems particularly with careful algorithmic designs; it has been studied within the "synthesis" signal model, e.g., convolutional dictionary learning. This paper proposes a new convolutional analysis operator learning (CAOL) framework that learns an analysis sparsifying regularizer with the convolution perspective, and develops a new convergent Block Proximal Extrapolated Gradient method using a Majorizer (BPEG-M) to solve the corresponding block multi-nonconvex problems. To learn diverse filters within the CAOL framework, this paper introduces an orthogonality constraint that enforces a tight-frame filter condition, and a regularizer that promotes diversity between filters. Numerical experiments show that, with sharp majorizers, BPEG-M significantly accelerates the CAOL convergence rate compared to the state-of-the-art block proximal gradient (BPG) method. Numerical experiments for sparse-view computational tomography show that a convolutional sparsifying regularizer learned via CAOL significantly improves reconstruction quality compared to a conventional edge-preserving regularizer. Using more and wider kernels in a learned regularizer better preserves edges in reconstructed images.

Gradient regularized convolutional neural networks for low-dose CT image enhancement

The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively.

Nanophosphor-Based Contrast Agents for Spectral X-ray Imaging

Lanthanide-based nanophosphors (NPhs) are herein developed as contrast agents for spectral X-ray imaging, highlighting the chemical, macromolecular and structural differences derived from ligand exchange on computed tomography (CT) and solvent dispersibility. Taking advantage of the ability of spectral X-ray imaging with photon-counting detectors to perform image acquisition, analysis, and processing at different energy windows (bins), enhanced signal of our K-edge materials was derived, improving sensitivity of CT imaging, and differentiation between water, tumor-mimic phantoms, and contrast materials. Our results indicate that the most effective of our oleic acid-stabilized K-edge nanoparticles can achieve 2-4x higher contrast than the examined iodinated molecules, making them suitable for deep tissue imaging of tissues or tumors. On the other hand, ligand exchange yielding poly(acrylic acid)-stabilized K-edge nanoparticles allows for high dispersibility and homogeneity in water, but with a lower contrast due to the high density of the polymer grafted, unless further engineering is probed. This is the first well-defined study that manages to correlate NPh grafting density with CT numbers and water dispersibility, laying the groundwork for the development of the next generation CT-guided diagnostic and/or theranostic materials.

Inpainting vs denoising for dose reduction in scanning-beam microscopies

We consider sampling strategies for reducing the radiation dose during image acquisition in scanning-beam microscopies, such as SEM, STEM, and STXM. Our basic assumption is that we may acquire subsampled image data (with some pixels missing) and then inpaint the missing data using a compressed-sensing approach. Our noise model consists of Poisson noise plus random Gaussian noise. We include the possibility of acquiring fully-sampled image data, in which case the inpainting approach reduces to a denoising procedure. We use numerical simulations to compare the accuracy of reconstructed images with the "ground truths." The results generally indicate that, for sufficiently high radiation doses, higher sampling rates achieve greater accuracy, commensurate with well-established literature. However, for very low radiation doses, where the Poisson noise and/or random Gaussian noise begins to dominate, then our results indicate that subsampling/inpainting can result in smaller reconstruction errors. We also present an information-theoretic analysis, which allows us to quantify the amount of information gained through the different sampling strategies and enables some broader discussion of the main results.