Low-dose X-ray CT reconstruction via dictionary learning

Discriminative Feature Representation to Improve Projection Data Inconsistency for Low Dose CT Imaging

In low dose computed tomography (LDCT) imaging, the data inconsistency of measured noisy projections can significantly deteriorate reconstruction images. To deal with this problem, we propose here a new sinogram restoration approach, the sinogram- discriminative feature representation (S-DFR) method. Different from other sinogram restoration methods, the proposed method works through a 3-D representation-based feature decomposition of the projected attenuation component and the noise component using a well-designed composite dictionary containing atoms with discriminative features. This method can be easily implemented with good robustness in parameter setting. Its comparison to other competing methods through experiments on simulated and real data demonstrated that the S-DFR method offers a sound alternative in LDCT.

Z-Index Parameterization for Volumetric CT Image Reconstruction via 3-D Dictionary Learning

Despite the rapid developments of X-ray cone-beam CT (CBCT), image noise still remains a major issue for the low dose CBCT. To suppress the noise effectively while retain the structures well for low dose CBCT image, in this paper, a sparse constraint based on the 3-D dictionary is incorporated into a regularized iterative reconstruction framework, defining the 3-D dictionary learning (3-DDL) method. In addition, by analyzing the sparsity level curve associated with different regularization parameters, a new adaptive parameter selection strategy is proposed to facilitate our 3-DDL method. To justify the proposed method, we first analyze the distributions of the representation coefficients associated with the 3-D dictionary and the conventional 2-D dictionary to compare their efficiencies in representing volumetric images. Then, multiple real data experiments are conducted for performance validation. Based on these results, we found: 1) the 3-D dictionary-based sparse coefficients have three orders narrower Laplacian distribution compared with the 2-D dictionary, suggesting the higher representation efficiencies of the 3-D dictionary; 2) the sparsity level curve demonstrates a clear Z-shape, and hence referred to as Z-curve, in this paper; 3) the parameter associated with the maximum curvature point of the Z-curve suggests a nice parameter choice, which could be adaptively located with the proposed Z-index parameterization (ZIP) method; 4) the proposed 3-DDL algorithm equipped with the ZIP method could deliver reconstructions with the lowest root mean squared errors and the highest structural similarity index compared with the competing methods; 5) similar noise performance as the regular dose FDK reconstruction regarding the standard deviation metric could be achieved with the proposed method using (1/2)/(1/4)/(1/8) dose level projections. The contrast-noise ratio is improved by ~2.5/3.5 times with respect to two different cases under the (1/8) dose level compared with the low dose FDK reconstruction. The proposed method is expected to reduce the radiation dose by a factor of 8 for CBCT, considering the voted strongly discriminated low contrast tissues.

Low-Dose Lung CT Image Restoration Using Adaptive Prior Features From Full-Dose Training Database

The valuable structure features in full-dose computed tomography (FdCT) scans can be exploited as prior knowledge for low-dose CT (LdCT) imaging. However, lacking the capability to represent local characteristics of interested structures of the LdCT image adaptively may result in poor preservation of details/textures in LdCT image. This paper aims to explore a novel prior knowledge retrieval and representation paradigm, called adaptive prior features assisted restoration algorithm, for the purpose of better restoration of the low-dose lung CT images by capturing local features from FdCT scans adaptively. The innovation lies in the construction of an offline training database and the online patch-search scheme integrated with the principal components analysis (PCA). Specifically, the offline training database is composed of 3-D patch samples extracted from existing full-dose lung scans. For online patch-search, 3-D patches with structure similar to the noisy target patch are first selected from the database as the training samples. Then, PCA is applied on the training samples to retrieve their local prior principal features adaptively. By employing the principal features to decompose the noisy target patch and using an adaptive coefficient shrinkage technique for inverse transformation, the noise of the target patch can be efficiently removed and the detailed texture can be well preserved. The effectiveness of the proposed algorithm was validated by CT scans of patients with lung cancer. The results show that it can achieve a noticeable gain over some state-of-the-art methods in terms of noise suppression and details/textures preservation.

Iterative Low-Dose CT Reconstruction With Priors Trained by Artificial Neural Network

Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications. Iterative reconstruction algorithms are one of the most promising way to compensate for the increased noise due to reduction of photon flux. Most iterative reconstruction algorithms incorporate manually designed prior functions of the reconstructed image to suppress noises while maintaining structures of the image. These priors basically rely on smoothness constraints and cannot exploit more complex features of the image. The recent development of artificial neural networks and machine learning enabled learning of more complex features of image, which has the potential to improve reconstruction quality. In this letter, K-sparse auto encoder was used for unsupervised feature learning. A manifold was learned from normal-dose images and the distance between the reconstructed image and the manifold was minimized along with data fidelity during reconstruction. Experiments on 2016 Low-dose CT Grand Challenge were used for the method verification, and results demonstrated the noise reduction and detail preservation abilities of the proposed method.

Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network

Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data, whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Especially, our method has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

Discriminative Prior - Prior Image Constrained Compressed Sensing Reconstruction for Low-Dose CT Imaging

X-ray computed tomography (CT) has been widely used to provide patient-specific anatomical information in the forms of tissue attenuation. However, the cumulative radiation induced in CT scan has raised extensive concerns in recently years. How to maintain reconstruction image quality is a major challenge for low-dose CT (LDCT) imaging. Generally, LDCT imaging can be greatly improved by incorporating prior knowledge in some specific forms. A joint estimation framework termed discriminative prior-prior image constrained compressed sensing (DP-PICCS) reconstruction is proposed in this paper. This DP-PICCS algorithm utilizes discriminative prior knowledge via two feature dictionary constraints which built on atoms from the samples of tissue attenuation feature patches and noise-artifacts residual feature patches, respectively. Also, the prior image construction relies on a discriminative feature representation (DFR) processing by two feature dictionary. Its comparison to other competing methods through experiments on low-dose projections acquired from torso phantom simulation study and clinical abdomen study demonstrated that the DP-PICCS method achieved promising improvement in terms of the effectively-suppressed noise and the well-retained structures.

A review of GPU-based medical image reconstruction

Tomographic image reconstruction is a computationally demanding task, even more so when advanced models are used to describe a more complete and accurate picture of the image formation process. Such advanced modeling and reconstruction algorithms can lead to better images, often with less dose, but at the price of long calculation times that are hardly compatible with clinical workflows. Fortunately, reconstruction tasks can often be executed advantageously on Graphics Processing Units (GPUs), which are exploited as massively parallel computational engines. This review paper focuses on recent developments made in GPU-based medical image reconstruction, from a CT, PET, SPECT, MRI and US perspective. Strategies and approaches to get the most out of GPUs in image reconstruction are presented as well as innovative applications arising from an increased computing capacity. The future of GPU-based image reconstruction is also envisioned, based on current trends in high-performance computing.

Deep Convolutional Neural Network for Inverse Problems in Imaging

In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyperparameter selection. The starting point of this paper is the observation that unrolled iterative methods have the form of a CNN (filtering followed by pointwise nonlinearity) when the normal operator (H*H, where H* is the adjoint of the forward imaging operator, H) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 × 512 image on the GPU.

Hybrid spectral CT reconstruction

Current photon counting x-ray detector (PCD) technology faces limitations associated with spectral fidelity and photon starvation. One strategy for addressing these limitations is to supplement PCD data with high-resolution, low-noise data acquired with an energy-integrating detector (EID). In this work, we propose an iterative, hybrid reconstruction technique which combines the spectral properties of PCD data with the resolution and signal-to-noise characteristics of EID data. Our hybrid reconstruction technique is based on an algebraic model of data fidelity which substitutes the EID data into the data fidelity term associated with the PCD reconstruction, resulting in a joint reconstruction problem. Within the split Bregman framework, these data fidelity constraints are minimized subject to additional constraints on spectral rank and on joint intensity-gradient sparsity measured between the reconstructions of the EID and PCD data. Following a derivation of the proposed technique, we apply it to the reconstruction of a digital phantom which contains realistic concentrations of iodine, barium, and calcium encountered in small-animal micro-CT. The results of this experiment suggest reliable separation and detection of iodine at concentrations ≥ 5 mg/ml and barium at concentrations ≥ 10 mg/ml in 2-mm features for EID and PCD data reconstructed with inherent spatial resolutions of 176 μm and 254 μm, respectively (point spread function, FWHM). Furthermore, hybrid reconstruction is demonstrated to enhance spatial resolution within material decomposition results and to improve low-contrast detectability by as much as 2.6 times relative to reconstruction with PCD data only. The parameters of the simulation experiment are based on an in vivo micro-CT experiment conducted in a mouse model of soft-tissue sarcoma. Material decomposition results produced from this in vivo data demonstrate the feasibility of distinguishing two K-edge contrast agents with a spectral separation on the order of the energy resolution of the PCD hardware.

Applications of nonlocal means algorithm in low-dose X-ray CT image processing and reconstruction: A review

Low-dose X-ray computed tomography (LDCT) imaging is highly recommended for use in the clinic because of growing concerns over excessive radiation exposure. However, the CT images reconstructed by the conventional filtered back-projection (FBP) method from low-dose acquisitions may be severely degraded with noise and streak artifacts due to excessive X-ray quantum noise, or with view-aliasing artifacts due to insufficient angular sampling. In 2005, the nonlocal means (NLM) algorithm was introduced as a non-iterative edge-preserving filter to denoise natural images corrupted by additive Gaussian noise, and showed superior performance. It has since been adapted and applied to many other image types and various inverse problems. This paper specifically reviews the applications of the NLM algorithm in LDCT image processing and reconstruction, and explicitly demonstrates its improving effects on the reconstructed CT image quality from low-dose acquisitions. The effectiveness of these applications on LDCT and their relative performance are described in detail.

Direct Reconstruction of CT-based Attenuation Correction Images for PET with Cluster-Based Penalties

Extremely low-dose CT acquisitions used for PET attenuation correction have high levels of noise and potential bias artifacts due to photon starvation. This work explores the use of a priori knowledge for iterative image reconstruction of the CT-based attenuation map. We investigate a maximum a posteriori framework with cluster-based multinomial penalty for direct iterative coordinate decent (dICD) reconstruction of the PET attenuation map. The objective function for direct iterative attenuation map reconstruction used a Poisson log-likelihood data fit term and evaluated two image penalty terms of spatial and mixture distributions. The spatial regularization is based on a quadratic penalty. For the mixture penalty, we assumed that the attenuation map may consist of four material clusters: air+background, lung, soft tissue, and bone. Using simulated noisy sinogram data, dICD reconstruction was performed with different strengths of the spatial and mixture penalties. The combined spatial and mixture penalties reduced the RMSE by roughly 2 times compared to a weighted least square and filtered backprojection reconstruction of CT images. The combined spatial and mixture penalties resulted in only slightly lower RMSE compared to a spatial quadratic penalty alone. For direct PET attenuation map reconstruction from ultra-low dose CT acquisitions, the combination of spatial and mixture penalties offers regularization of both variance and bias and is a potential method to reconstruct attenuation maps with negligible patient dose. The presented results, using a best-case histogram suggest that the mixture penalty does not offer a substantive benefit over conventional quadratic regularization and diminishes enthusiasm for exploring future application of the mixture penalty.

Comparison Between Pre-Log and Post-Log Statistical Models in Ultra-Low-Dose CT Reconstruction

X-ray detectors in clinical computed tomography (CT) usually operate in current-integrating mode. Their complicated signal statistics often lead to intractable likelihood functions for practical use in model-based image reconstruction (MBIR). It is therefore desirable to design simplified statistical models without losing the essential factors. Depending on whether the CT transmission data are logarithmically transformed, pre-log and post-log models are two major categories of choices in CT MBIR. Both being approximations, it remains an open question whether one model can notably improve image quality over the other on real scanners. In this study, we develop and compare several pre-log and post-log MBIR algorithms under a unified framework. Their reconstruction accuracy based on simulation and clinical datasets are evaluated. The results show that pre-log MBIR can achieve notably better quantitative accuracy than post-log MBIR in ultra-low-dose CT, although in less extreme cases, post-log MBIR with handcrafted pre-processing remains a competitive alternative. Pre-log MBIR could play a growing role in emerging ultra-low-dose CT applications.

Discriminative feature representation: an effective postprocessing solution to low dose CT imaging

This paper proposes a concise and effective approach termed discriminative feature representation (DFR) for low dose computerized tomography (LDCT) image processing, which is currently a challenging problem in medical imaging field. This DFR method assumes LDCT images as the superposition of desirable high dose CT (HDCT) 3D features and undesirable noise-artifact 3D features (the combined term of noise and artifact features induced by low dose scan protocols), and the decomposed HDCT features are used to provide the processed LDCT images with higher quality. The target HDCT features are solved via the DFR algorithm using a featured dictionary composed by atoms representing HDCT features and noise-artifact features. In this study, the featured dictionary is efficiently built using physical phantom images collected from the same CT scanner as the target clinical LDCT images to process. The proposed DFR method also has good robustness in parameter setting for different CT scanner types. This DFR method can be directly applied to process DICOM formatted LDCT images, and has good applicability to current CT systems. Comparative experiments with abdomen LDCT data validate the good performance of the proposed approach.

Segmentation Based Sparse Reconstruction of Optical Coherence Tomography Images

We demonstrate the usefulness of utilizing a segmentation step for improving the performance of sparsity based image reconstruction algorithms. In specific, we will focus on retinal optical coherence tomography (OCT) reconstruction and propose a novel segmentation based reconstruction framework with sparse representation, termed segmentation based sparse reconstruction (SSR). The SSR method uses automatically segmented retinal layer information to construct layer-specific structural dictionaries. In addition, the SSR method efficiently exploits patch similarities within each segmented layer to enhance the reconstruction performance. Our experimental results on clinical-grade retinal OCT images demonstrate the effectiveness and efficiency of the proposed SSR method for both denoising and interpolation of OCT images.

Low-dose CT via convolutional neural network

In order to reduce the potential radiation risk, low-dose CT has attracted an increasing attention. However, simply lowering the radiation dose will significantly degrade the image quality. In this paper, we propose a new noise reduction method for low-dose CT via deep learning without accessing original projection data. A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion. Qualitative results demonstrate a great potential of the proposed method on artifact reduction and structure preservation. In terms of the quantitative metrics, the proposed method has showed a substantial improvement on PSNR, RMSE and SSIM than the competing state-of-art methods. Furthermore, the speed of our method is one order of magnitude faster than the iterative reconstruction and patch-based image denoising methods.

Data correlation based noise level estimation for cone beam projection data

BACKGROUND

In regularized iterative reconstruction algorithms, the selection of regularization parameter depends on the noise level of cone beam projection data.

OBJECTIVE

Our aim is to propose an algorithm to estimate the noise level of cone beam projection data.

METHODS

We first derived the data correlation of cone beam projection data in the Fourier domain, based on which, the signal and the noise were decoupled. Then the noise was extracted and averaged for estimation. An adaptive regularization parameter selection strategy was introduced based on the estimated noise level. Simulation and real data studies were conducted for performance validation.

RESULTS

There exists an approximately zero-energy double-wedge area in the 3D Fourier domain of cone beam projection data. As for the noise level estimation results, the averaged relative errors of the proposed algorithm in the analytical/MC/spotlight-mode simulation experiments were 0.8%, 0.14% and 0.24%, respectively, and outperformed the homogeneous area based as well as the transformation based algorithms. Real studies indicated that the estimated noise levels were inversely proportional to the exposure levels, i.e., the slopes in the log-log plot were -1.0197 and -1.049 with respect to the short-scan and half-fan modes. The introduced regularization parameter selection strategy could deliver promising reconstructed image qualities.

CONCLUSIONS

Based on the data correlation of cone beam projection data in Fourier domain, the proposed algorithm could estimate the noise level of cone beam projection data accurately and robustly. The estimated noise level could be used to adaptively select the regularization parameter.

Tensor-Based Dictionary Learning for Spectral CT Reconstruction

Spectral computed tomography (CT) produces an energy-discriminative attenuation map of an object, extending a conventional image volume with a spectral dimension. In spectral CT, an image can be sparsely represented in each of multiple energy channels, and are highly correlated among energy channels. According to this characteristics, we propose a tensor-based dictionary learning method for spectral CT reconstruction. In our method, tensor patches are extracted from an image tensor, which is reconstructed using the filtered backprojection (FBP), to form a training dataset. With the Candecomp/Parafac decomposition, a tensor-based dictionary is trained, in which each atom is a rank-one tensor. Then, the trained dictionary is used to sparsely represent image tensor patches during an iterative reconstruction process, and the alternating minimization scheme is adapted for optimization. The effectiveness of our proposed method is validated with both numerically simulated and real preclinical mouse datasets. The results demonstrate that the proposed tensor-based method generally produces superior image quality, and leads to more accurate material decomposition than the currently popular popular methods.

Iterative reconstruction for CT perfusion with a prior-image induced hybrid nonlocal means regularization: Phantom studies

PURPOSE

In computed tomography perfusion (CTP) imaging, an initial phase CT acquired with a high-dose protocol can be used to improve the image quality of later phase CT acquired with a low-dose protocol. For dynamic regions, signals in the later low-dose CT may not be completely recovered if the initial CT heavily regularizes the iterative reconstruction process. The authors propose a hybrid nonlocal means (hNLM) regularization model for iterative reconstruction of low-dose CTP to overcome the limitation of the conventional prior-image induced penalty.

METHODS

The hybrid penalty was constructed by combining the NLM of the initial phase high-dose CT in the stationary region and later phase low-dose CT in the dynamic region. The stationary and dynamic regions were determined by the similarity between the initial high-dose scan and later low-dose scan. The similarity was defined as a Gaussian kernel-based distance between the patch-window of the same pixel in the two scans, and its measurement was then used to weigh the influence of the initial high-dose CT. For regions with high similarity (e.g., stationary region), initial high-dose CT played a dominant role for regularizing the solution. For regions with low similarity (e.g., dynamic region), the regularization relied on a low-dose scan itself. This new hNLM penalty was incorporated into the penalized weighted least-squares (PWLS) for CTP reconstruction. Digital and physical phantom studies were performed to evaluate the PWLS-hNLM algorithm.

RESULTS

Both phantom studies showed that the PWLS-hNLM algorithm is superior to the conventional prior-image induced penalty term without considering the signal changes within the dynamic region. In the dynamic region of the Catphan phantom, the reconstruction error measured by root mean square error was reduced by 42.9% in PWLS-hNLM reconstructed image.

CONCLUSIONS

The PWLS-hNLM algorithm can effectively use the initial high-dose CT to reconstruct low-dose CTP in the stationary region while reducing its influence in the dynamic region.

A limit on dose reduction possible with CT reconstruction algorithms without prior knowledge of the scan subject

PURPOSE

To find an upper bound on the maximum dose reduction possible for any reconstruction algorithm, analytic or iterative, that result from the inclusion of the data statistics. The authors do not analyze noise reduction possible from prior knowledge or assumptions about the object.

METHODS

The authors examined the task of estimating the density of a circular lesion in a cross section. Raw data were simulated by forward projection of existing images and numerical phantoms. To assess an upper bound on the achievable dose reduction by any algorithm, the authors assume that both the background and the shape of the lesion are completely known. Under these conditions, the best possible estimate of the density can be determined by solving a weighted least squares problem directly in the raw data domain. Any possible reconstruction algorithm that does not use prior knowledge or make assumptions about the object, including filtered backprojection (FBP) or iterative reconstruction methods with this constraint, must be no better than this least squares solution. The authors simulated 10,000 sets of noisy data and compared the variance in density from the least squares solution with those from FBP. Density was estimated from FBP images using either averaging within a ROI, or streak-adaptive averaging with better noise performance.

RESULTS

The bound on the possible dose reduction depends on the degree to which the observer can read through the possibly streaky noise. For the described low contrast detection task with the signal shape and background known exactly, the average dose reduction possible compared to FBP with streak-adaptive averaging was 42% and it was 64% if only the ROI average is used with FBP. The exact amount of dose reduction also depends on the background anatomy, with statistically inhomogeneous backgrounds showing greater benefits.

CONCLUSIONS

The dose reductions from new, statistical reconstruction methods can be bounded. Larger dose reductions in the density estimation task studied here are only possible with the introduction of prior knowledge, which can introduce bias.

Spectral CT Reconstruction with Image Sparsity and Spectral Mean

Photon-counting detectors can acquire x-ray intensity data in different energy bins. The signal to noise ratio of resultant raw data in each energy bin is generally low due to the narrow bin width and quantum noise. To address this problem, here we propose an image reconstruction approach for spectral CT to simultaneously reconstructs x-ray attenuation coefficients in all the energy bins. Because the measured spectral data are highly correlated among the x-ray energy bins, the intra-image sparsity and inter-image similarity are important prior acknowledge for image reconstruction. Inspired by this observation, the total variation (TV) and spectral mean (SM) measures are combined to improve the quality of reconstructed images. For this purpose, a linear mapping function is used to minimalize image differences between energy bins. The split Bregman technique is applied to perform image reconstruction. Our numerical and experimental results show that the proposed algorithms outperform competing iterative algorithms in this context.

Robust low-dose dynamic cerebral perfusion CT image restoration via coupled dictionary learning scheme

Dynamic cerebral perfusion x-ray computed tomography (PCT) imaging has been advocated to quantitatively and qualitatively assess hemodynamic parameters in the diagnosis of acute stroke or chronic cerebrovascular diseases. However, the associated radiation dose is a significant concern to patients due to its dynamic scan protocol. To address this issue, in this paper we propose an image restoration method by utilizing coupled dictionary learning (CDL) scheme to yield clinically acceptable PCT images with low-dose data acquisition. Specifically, in the present CDL scheme, the 2D background information from the average of the baseline time frames of low-dose unenhanced CT images and the 3D enhancement information from normal-dose sequential cerebral PCT images are exploited to train the dictionary atoms respectively. After getting the two trained dictionaries, we couple them to represent the desired PCT images as spatio-temporal prior in objective function construction. Finally, the low-dose dynamic cerebral PCT images are restored by using a general DL image processing. To get a robust solution, the objective function is solved by using a modified dictionary learning based image restoration algorithm. The experimental results on clinical data show that the present method can yield more accurate kinetic enhanced details and diagnostic hemodynamic parameter maps than the state-of-the-art methods.

Smoothed l0 Norm Regularization for Sparse-View X-Ray CT Reconstruction

Low-dose computed tomography (CT) reconstruction is a challenging problem in medical imaging. To complement the standard filtered back-projection (FBP) reconstruction, sparse regularization reconstruction gains more and more research attention, as it promises to reduce radiation dose, suppress artifacts, and improve noise properties. In this work, we present an iterative reconstruction approach using improved smoothed l₀ (SL0) norm regularization which is used to approximate l₀ norm by a family of continuous functions to fully exploit the sparseness of the image gradient. Due to the excellent sparse representation of the reconstruction signal, the desired tissue details are preserved in the resulting images. To evaluate the performance of the proposed SL0 regularization method, we reconstruct the simulated dataset acquired from the Shepp-Logan phantom and clinical head slice image. Additional experimental verification is also performed with two real datasets from scanned animal experiment. Compared to the referenced FBP reconstruction and the total variation (TV) regularization reconstruction, the results clearly reveal that the presented method has characteristic strengths. In particular, it improves reconstruction quality via reducing noise while preserving anatomical features.

Sparsity Prior Computed Tomography Reconstruction Using a Nonstandard Simultaneous X-ray Acquisition Model

In this article we systematically evaluate the performance of several state-of-the-art, sparsity prior computed tomography (CT) reconstruction algorithms, using a nonstandard simultaneous x-ray acquisition method. Sparsity prior is an efficient strategy in CT reconstruction, relying on iterative algorithms such as the algebraic reconstruction technique to produce a crude reconstruction, based on which sparse approximation is performed. The simultaneous x-ray acquisition model ensures rapid capture of x-rays; however, it captures a significantly fewer number of attenuation measurements, and the projections are nonuniform. We propose a weighted average filter in the reconstruction framework to ensure better quality reconstruction by minimizing the effect of nonuniform projections. The performance of the state-of-the-art algorithms is analyzed with and without weighted averaging before sparse approximation, in simulated and real environments. Experiments in the simulated environment are conducted with and without the presence of noise. From the results, it is evident that sparsity prior algorithms are capable of producing cross-sectional reconstruction using the simultaneous x-ray acquisition model, and better reconstruction quality is achievable with the incorporation of weighted averaging in the reconstruction framework.

An Improved Total Variation Minimization Method Using Prior Images and Split-Bregman Method in CT Reconstruction

Compressive Sensing (CS) theory has great potential for reconstructing Computed Tomography (CT) images from sparse-views projection data and Total Variation- (TV-) based CT reconstruction method is very popular. However, it does not directly incorporate prior images into the reconstruction. To improve the quality of reconstructed images, this paper proposed an improved TV minimization method using prior images and Split-Bregman method in CT reconstruction, which uses prior images to obtain valuable previous information and promote the subsequent imaging process. The images obtained asynchronously were registered via Locally Linear Embedding (LLE). To validate the method, two studies were performed. Numerical simulation using an abdomen phantom has been used to demonstrate that the proposed method enables accurate reconstruction of image objects under sparse projection data. A real dataset was used to further validate the method.

Spectral prior image constrained compressed sensing (spectral PICCS) for photon-counting computed tomography

Photon-counting computed tomography (PCCT) is an emerging imaging technique that enables multi-energy imaging with only a single scan acquisition. To enable multi-energy imaging, the detected photons corresponding to the full x-ray spectrum are divided into several subgroups of bin data that correspond to narrower energy windows. Consequently, noise in each energy bin increases compared to the full-spectrum data. This work proposes an iterative reconstruction algorithm for noise suppression in the narrower energy bins used in PCCT imaging. The algorithm is based on the framework of prior image constrained compressed sensing (PICCS) and is called spectral PICCS; it uses the full-spectrum image reconstructed using conventional filtered back-projection as the prior image. The spectral PICCS algorithm is implemented using a constrained optimization scheme with adaptive iterative step sizes such that only two tuning parameters are required in most cases. The algorithm was first evaluated using computer simulations, and then validated by both physical phantoms and in vivo swine studies using a research PCCT system. Results from both computer-simulation and experimental studies showed substantial image noise reduction in narrow energy bins (43-73%) without sacrificing CT number accuracy or spatial resolution.

Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares

Background

In order to reduce the radiation dose of CT (computed tomography), compressed sensing theory has been a hot topic since it provides the possibility of a high quality recovery from the sparse sampling data. Recently, the algorithm based on DL (dictionary learning) was developed to deal with the sparse CT reconstruction problem. However, the existing DL algorithm focuses on the minimization problem with the L₂-norm regularization term, which leads to reconstruction quality deteriorating while the sampling rate declines further. Therefore, it is essential to improve the DL method to meet the demand of more dose reduction.

Methods

In this paper, we replaced the L₂-norm regularization term with the L₁-norm one. It is expected that the proposed L₁-DL method could alleviate the over-smoothing effect of the L₂-minimization and reserve more image details. The proposed algorithm solves the L₁-minimization problem by a weighting strategy, solving the new weighted L₂-minimization problem based on IRLS (iteratively reweighted least squares).

Results

Through the numerical simulation, the proposed algorithm is compared with the existing DL method (adaptive dictionary based statistical iterative reconstruction, ADSIR) and other two typical compressed sensing algorithms. It is revealed that the proposed algorithm is more accurate than the other algorithms especially when further reducing the sampling rate or increasing the noise.

Conclusion

The proposed L₁-DL algorithm can utilize more prior information of image sparsity than ADSIR. By transforming the L₂-norm regularization term of ADSIR with the L₁-norm one and solving the L₁-minimization problem by IRLS strategy, L₁-DL could reconstruct the image more exactly.

Compressed Sensing Electron Tomography for Determining Biological Structure

There has been growing interest in applying compressed sensing (CS) theory and practice to reconstruct 3D volumes at the nanoscale from electron tomography datasets of inorganic materials, based on known sparsity in the structure of interest. Here we explore the application of CS for visualizing the 3D structure of biological specimens from tomographic tilt series acquired in the scanning transmission electron microscope (STEM). CS-ET reconstructions match or outperform commonly used alternative methods in full and undersampled tomogram recovery, but with less significant performance gains than observed for the imaging of inorganic materials. We propose that this disparity stems from the increased structural complexity of biological systems, as supported by theoretical CS sampling considerations and numerical results in simulated phantom datasets. A detailed analysis of the efficacy of CS-ET for undersampled recovery is therefore complicated by the structure of the object being imaged. The numerical nonlinear decoding process of CS shares strong connections with popular regularized least-squares methods, and the use of such numerical recovery techniques for mitigating artifacts and denoising in reconstructions of fully sampled datasets remains advantageous. This article provides a link to the software that has been developed for CS-ET reconstruction of electron tomographic data sets.

Patch-based models and algorithms for image processing: a review of the basic principles and methods, and their application in computed tomography

PURPOSE

Image models are central to all image processing tasks. The great advancements in digital image processing would not have been made possible without powerful models which, themselves, have evolved over time. In the past decade, "patch-based" models have emerged as one of the most effective models for natural images. Patch-based methods have outperformed other competing methods in many image processing tasks. These developments have come at a time when greater availability of powerful computational resources and growing concerns over the health risks of the ionizing radiation encourage research on image processing algorithms for computed tomography (CT). The goal of this paper is to explain the principles of patch-based methods and to review some of their recent applications in CT.

METHODS

We first review the central concepts in patch-based image processing and explain some of the state-of-the-art algorithms, with a focus on aspects that are more relevant to CT. Then, we review some of the recent application of patch-based methods in CT.

RESULTS

Patch-based methods have already transformed the field of image processing, leading to state-of-the-art results in many applications. More recently, several studies have proposed patch-based algorithms for various image processing tasks in CT, from denoising and restoration to iterative reconstruction. Although these studies have reported good results, the true potential of patch-based methods for CT has not been yet appreciated.

CONCLUSIONS

Patch-based methods can play a central role in image reconstruction and processing for CT. They have the potential to lead to substantial improvements in the current state of the art.

Simultaneous CT-MRI Reconstruction for Constrained Imaging Geometries Using Structural Coupling and Compressive Sensing

OBJECTIVE

A unified reconstruction framework is presented for simultaneous CT-MRI reconstruction.

METHODS

In an ideal CT-MRI scanner, CT and MRI acquisitions would occur simultaneously, and would be inherently registered in space and time. Alternatively, separately acquired CT and MRI scans can be fused to simulate an instantaneous acquisition. In this study, structural coupling and compressive sensing techniques are combined to unify CT and MRI reconstructions. A bidirectional image estimation method was proposed to connect images from different modalities. Hence, CT and MRI data serve as prior knowledge to each other for better CT and MRI image reconstruction than what could be achieved with separate reconstruction.

SIGNIFICANCE

Combined CT-MRI imaging has the potential for improved results in existing preclinical and clinical applications, as well as opening novel research directions for future applications.

RESULTS

Our integrated reconstruction methodology is demonstrated with numerical phantom and real-dataset-based experiments, and has yielded promising results.

Image reconstruction from few-view CT data by gradient-domain dictionary learning

BACKGROUND

Decreasing the number of projections is an effective way to reduce the radiation dose exposed to patients in medical computed tomography (CT) imaging. However, incomplete projection data for CT reconstruction will result in artifacts and distortions.

OBJECTIVE

In this paper, a novel dictionary learning algorithm operating in the gradient-domain (Grad-DL) is proposed for few-view CT reconstruction. Specifically, the dictionaries are trained from the horizontal and vertical gradient images, respectively and the desired image is reconstructed subsequently from the sparse representations of both gradients by solving the least-square method.

METHODS

Since the gradient images are sparser than the image itself, the proposed approach could lead to sparser representations than conventional DL methods in the image-domain, and thus a better reconstruction quality is achieved.

RESULTS

To evaluate the proposed Grad-DL algorithm, both qualitative and quantitative studies were employed through computer simulations as well as real data experiments on fan-beam and cone-beam geometry.

CONCLUSIONS

The results show that the proposed algorithm can yield better images than the existing algorithms.

Interior tomographic imaging of mouse heart in a carbon nanotube micro-CT

BACKGROUND

The relatively high radiation dose from micro-CT is a cause for concern in preclinical research involving animal subjects. Interior region-of-interest (ROI) imaging was proposed for dose reduction, but has not been experimentally applied in micro-CT.

OBJECTIVE

Our aim is to implement interior ROI imaging in a carbon nanotube (CNT) x-ray source based micro-CT, and present the ROI image quality and radiation dose reduction for interior cardiac micro-CT imaging of a mouse heart in situ.

METHODS

An aperture collimator was mounted at the source-side to induce a small-sized cone beam (10 mm width) at the isocenter. Interior in situ micro-CT scans were conducted on a mouse carcass and several micro-CT phantoms. A GPU-accelerated hybrid iterative reconstruction algorithm was employed for volumetric image reconstruction. Radiation dose was measured for the same system operated at the interior and global micro-CT modes.

RESULTS

Visual inspection demonstrated comparable image quality between two scan modes. Quantitative evaluation demonstrated high structural similarity index (up to 0.9614) with improved contrast-noise-ratio (CNR) on interior micro-CT mode. Interior micro-CT mode yielded significant reduction (up to 83.9%) for dose length product (DLP).

CONCLUSIONS

This work demonstrates the applicability of using CNT x-ray source based interior micro-CT for preclinical imaging with significantly reduced radiation dose.

Probabilistic atlas prior for CT image reconstruction

BACKGROUND AND OBJECTIVES

In computed tomography (CT), statistical iterative reconstruction (SIR) approaches can produce images of higher quality compared to the conventional analytical methods such as filtered backprojection (FBP) algorithm. Effective noise modeling and possibilities to incorporate priors in the image reconstruction problem are the main advantages that lead to continuous development of SIR methods. Oriented by low-dose CT requirements, several methods are recently developed to obtain a high-quality image reconstruction from down-sampled or noisy projection data. In this paper, a new prior information obtained from probabilistic atlas is proposed for low-dose CT image reconstruction.

METHODS

The proposed approach consists of two main phases. In learning phase, a dataset of images obtained from different patients is used to construct a 3D atlas with Laplacian mixture model. The expectation maximization (EM) algorithm is used to estimate the mixture parameters. In reconstruction phase, prior information obtained from the probabilistic atlas is used to construct the cost function for image reconstruction.

RESULTS

We investigate the low-dose imaging by considering the reduction of X-ray beam intensity and by acquiring the projection data through a small number of views or limited view angles. Experimental studies using simulated data and chest screening CT data demonstrate that the probabilistic atlas prior is a practically promising approach for the low-dose CT imaging.

CONCLUSIONS

The prior information obtained from probabilistic atlas constructed from earlier scans of different patients is useful in low-dose CT imaging.

Sinogram denoising via simultaneous sparse representation in learned dictionaries

Reducing the radiation dose in computed tomography (CT) is highly desirable but it leads to excessive noise in the projection measurements. This can significantly reduce the diagnostic value of the reconstructed images. Removing the noise in the projection measurements is, therefore, essential for reconstructing high-quality images, especially in low-dose CT. In recent years, two new classes of patch-based denoising algorithms proved superior to other methods in various denoising applications. The first class is based on sparse representation of image patches in a learned dictionary. The second class is based on the non-local means method. Here, the image is searched for similar patches and the patches are processed together to find their denoised estimates. In this paper, we propose a novel denoising algorithm for cone-beam CT projections. The proposed method has similarities to both these algorithmic classes but is more effective and much faster. In order to exploit both the correlation between neighboring pixels within a projection and the correlation between pixels in neighboring projections, the proposed algorithm stacks noisy cone-beam projections together to form a 3D image and extracts small overlapping 3D blocks from this 3D image for processing. We propose a fast algorithm for clustering all extracted blocks. The central assumption in the proposed algorithm is that all blocks in a cluster have a joint-sparse representation in a well-designed dictionary. We describe algorithms for learning such a dictionary and for denoising a set of projections using this dictionary. We apply the proposed algorithm on simulated and real data and compare it with three other algorithms. Our results show that the proposed algorithm outperforms some of the best denoising algorithms, while also being much faster.

Improving Low-dose Cardiac CT Images based on 3D Sparse Representation

Cardiac computed tomography (CCT) is a reliable and accurate tool for diagnosis of coronary artery diseases and is also frequently used in surgery guidance. Low-dose scans should be considered in order to alleviate the harm to patients caused by X-ray radiation. However, low dose CT (LDCT) images tend to be degraded by quantum noise and streak artifacts. In order to improve the cardiac LDCT image quality, a 3D sparse representation-based processing (3D SR) is proposed by exploiting the sparsity and regularity of 3D anatomical features in CCT. The proposed method was evaluated by a clinical study of 14 patients. The performance of the proposed method was compared to the 2D spares representation-based processing (2D SR) and the state-of-the-art noise reduction algorithm BM4D. The visual assessment, quantitative assessment and qualitative assessment results show that the proposed approach can lead to effective noise/artifact suppression and detail preservation. Compared to the other two tested methods, 3D SR method can obtain results with image quality most close to the reference standard dose CT (SDCT) images.

Reducing streak artifacts in computed tomography via sparse representation in coupled dictionaries

PURPOSE

Reducing the number of acquired projections is a simple and efficient way to reduce the radiation dose in computed tomography (CT). Unfortunately, this results in streak artifacts in the reconstructed images that can significantly reduce their diagnostic value. This paper presents a novel algorithm for suppressing these artifacts in 3D CT.

METHODS

The proposed algorithm is based on the sparse representation of small blocks of 3D CT images in learned overcomplete dictionaries. It learns two dictionaries, the first dictionary (D(a)) is for artifact-full images that have been reconstructed from a small number (approximately 100) of projections. The other dictionary (D(c)) is for clean artifact-free images. The core idea behind the proposed algorithm is to relate the representation coefficients of an artifact-full block in D(a) to the representation coefficients of the corresponding artifact-free block in D(c). The relation between these coefficients is modeled with a linear mapping. The two dictionaries and the linear relation between the coefficients are learned simultaneously from the training data. To remove the artifacts from a test image, small blocks are extracted from this image and their sparse representation is computed in D(a). The linear map is then used to compute the corresponding coefficients in D(c), which are then used to produce the artifact-suppressed blocks.

RESULTS

The authors apply the proposed algorithm on real cone-beam CT images. Their results show that the proposed algorithm can effectively suppress the artifacts and substantially improve the quality of the reconstructed images. The images produced by the proposed algorithm have a higher quality than the images reconstructed by the FDK algorithm from twice as many projections.

CONCLUSIONS

The proposed sparsity-based algorithm can be a valuable tool for postprocessing of CT images reconstructed from a small number of projections. Therefore, it has the potential to be an effective tool for low-dose CT.

Predicting standard-dose PET image from low-dose PET and multimodal MR images using mapping-based sparse representation

Positron emission tomography (PET) has been widely used in clinical diagnosis for diseases and disorders. To obtain high-quality PET images requires a standard-dose radionuclide (tracer) injection into the human body, which inevitably increases risk of radiation exposure. One possible solution to this problem is to predict the standard-dose PET image from its low-dose counterpart and its corresponding multimodal magnetic resonance (MR) images. Inspired by the success of patch-based sparse representation (SR) in super-resolution image reconstruction, we propose a mapping-based SR (m-SR) framework for standard-dose PET image prediction. Compared with the conventional patch-based SR, our method uses a mapping strategy to ensure that the sparse coefficients, estimated from the multimodal MR images and low-dose PET image, can be applied directly to the prediction of standard-dose PET image. As the mapping between multimodal MR images (or low-dose PET image) and standard-dose PET images can be particularly complex, one step of mapping is often insufficient. To this end, an incremental refinement framework is therefore proposed. Specifically, the predicted standard-dose PET image is further mapped to the target standard-dose PET image, and then the SR is performed again to predict a new standard-dose PET image. This procedure can be repeated for prediction refinement of the iterations. Also, a patch selection based dictionary construction method is further used to speed up the prediction process. The proposed method is validated on a human brain dataset. The experimental results show that our method can outperform benchmark methods in both qualitative and quantitative measures.

Ordered-subset Split-Bregman algorithm for interior tomography

Inspired by the Compressed Sensing (CS) theory, it has been proved that the interior problem of computed tomography (CT) can be accurately and stably solved if a region-of-interest (ROI) is piecewise constant or polynomial, resulting in the CS-based interior tomography. The key is to minimize the total variation (TV) of the ROI under the constraint of the truncated projections. Coincidentally, the Split-Bregman (SB) method has attracted a major attention to solve the TV minimization problem for CT image reconstruction. In this paper, we apply the SB approach to reconstruct an ROI for the CS-based interior tomography assuming a piecewise constant imaging model. Furthermore, the ordered subsets (OS) technique is used to accelerate the convergence of SB algorithm, leading to a new OS-SB algorithm for interior tomography. The conventional OS simultaneous algebraic reconstruction technique (OS-SART) and soft-threshold filtering (STF) based OS-SART are also implemented as references to evaluate the performance of the proposed OS-SB algorithm for interior tomography. Both numerical simulations and clinical applications are performed and the results confirm the advantages of the proposed OS-SB method.

Edge-oriented dual-dictionary guided enrichment (EDGE) for MRI-CT image reconstruction

In this paper, we formulate the joint/simultaneous X-ray CT and MRI image reconstruction. In particular, a novel algorithm is proposed for MRI image reconstruction from highly under-sampled MRI data and CT images. It consists of two steps. First, a training dataset is generated from a series of well-registered MRI and CT images on the same patients. Then, an initial MRI image of a patient can be reconstructed via edge-oriented dual-dictionary guided enrichment (EDGE) based on the training dataset and a CT image of the patient. Second, an MRI image is reconstructed using the dictionary learning (DL) algorithm from highly under-sampled k-space data and the initial MRI image. Our algorithm can establish a one-to-one correspondence between the two imaging modalities, and obtain a good initial MRI estimation. Both noise-free and noisy simulation studies were performed to evaluate and validate the proposed algorithm. The results with different under-sampling factors show that the proposed algorithm performed significantly better than those reconstructed using the DL algorithm from MRI data alone.

Low-dose CT statistical iterative reconstruction via modified MRF regularization

It is desirable to reduce the excessive radiation exposure to patients in repeated medical CT applications. One of the most effective ways is to reduce the X-ray tube current (mAs) or tube voltage (kVp). However, it is difficult to achieve accurate reconstruction from the noisy measurements. Compared with the conventional filtered back-projection (FBP) algorithm leading to the excessive noise in the reconstructed images, the approaches using statistical iterative reconstruction (SIR) with low mAs show greater image quality. To eliminate the undesired artifacts and improve reconstruction quality, we proposed, in this work, an improved SIR algorithm for low-dose CT reconstruction, constrained by a modified Markov random field (MRF) regularization. Specifically, the edge-preserving total generalized variation (TGV), which is a generalization of total variation (TV) and can measure image characteristics up to a certain degree of differentiation, was introduced to modify the MRF regularization. In addition, a modified alternating iterative algorithm was utilized to optimize the cost function. Experimental results demonstrated that images reconstructed by the proposed method could not only generate high accuracy and resolution properties, but also ensure a higher peak signal-to-noise ratio (PSNR) in comparison with those using existing methods.

A General-Thresholding Solution for ℓp (0 < p <1) Regularized CT Reconstruction

It is well known that ℓ1 minimization can be used to recover sufficiently sparse unknown signals in the compressive sensing field. The ℓp regularization method, a generalized version between the well-known ℓ1 regularization and the ℓ0 regularization, has been proposed for a sparser solution. In this paper, we derive several quasi-analytic thresholding representations for the ℓp(0 < p < 1) regularization. The derived representations are exact matches for the well-known soft-threshold filtering for the ℓ1 regularization and the hard-threshold filtering for the ℓ0 regularization. The error bounds of the approximate general formulas are analyzed. The general-threshold representation formulas are incorporated into an iterative thresholding framework for a fast solution of an ℓp regularized computed tomography (CT) reconstruction. A series of simulated and realistic data experiments are conducted to evaluate the performance of the proposed general-threshold filtering algorithm for CT reconstruction, and it is also compared with the well-known re-weighted approach. Compared with the re-weighted algorithm, the proposed general-threshold filtering algorithm can substantially reduce the necessary view number for an accurate reconstruction of the Shepp-Logan phantom. In addition, the proposed general-threshold filtering algorithm performs well in terms of image quality, reconstruction accuracy, convergence speed, and sensitivity to parameters.

A Model of Regularization Parameter Determination in Low-Dose X-Ray CT Reconstruction Based on Dictionary Learning

In recent years, X-ray computed tomography (CT) is becoming widely used to reveal patient's anatomical information. However, the side effect of radiation, relating to genetic or cancerous diseases, has caused great public concern. The problem is how to minimize radiation dose significantly while maintaining image quality. As a practical application of compressed sensing theory, one category of methods takes total variation (TV) minimization as the sparse constraint, which makes it possible and effective to get a reconstruction image of high quality in the undersampling situation. On the other hand, a preliminary attempt of low-dose CT reconstruction based on dictionary learning seems to be another effective choice. But some critical parameters, such as the regularization parameter, cannot be determined by detecting datasets. In this paper, we propose a reweighted objective function that contributes to a numerical calculation model of the regularization parameter. A number of experiments demonstrate that this strategy performs well with better reconstruction images and saving of a large amount of time.

A Novel Iterative CT Reconstruction Approach Based on FBP Algorithm

The Filtered Back-Projection (FBP) algorithm and its modified versions are the most important techniques for CT (Computerized tomography) reconstruction, however, it may produce aliasing degradation in the reconstructed images due to projection discretization. The general iterative reconstruction (IR) algorithms suffer from their heavy calculation burden and other drawbacks. In this paper, an iterative FBP approach is proposed to reduce the aliasing degradation. In the approach, the image reconstructed by FBP algorithm is treated as the intermediate image and projected along the original projection directions to produce the reprojection data. The difference between the original and reprojection data is filtered by a special digital filter, and then is reconstructed by FBP to produce a correction term. The correction term is added to the intermediate image to update it. This procedure can be performed iteratively to improve the reconstruction performance gradually until certain stopping criterion is satisfied. Some simulations and tests on real data show the proposed approach is better than FBP algorithm or some IR algorithms in term of some general image criteria. The calculation burden is several times that of FBP, which is much less than that of general IR algorithms and acceptable in the most situations. Therefore, the proposed algorithm has the potential applications in practical CT systems.

Ring artifacts correction in compressed sensing tomographic reconstruction

Ring artifacts are a very common problem in tomographic reconstruction, and numerous methods exist to either pre-process the sinogram or correct the reconstructed slice. A novel approach to perform the correction as part of the reconstruction process is presented. It is shown that for iterative techniques, which amount to optimizing an objective function, the ring artifacts correction can be easily integrated in the formalism, enabling simultaneous slice reconstruction and ring artifacts correction. This method is tested and compared with mainstream correction techniques for both simulated and experimental data. Results show that the correction is efficient, especially for undersampled datasets. This technique is included in the PyHST2 code which is used at the European Synchrotron Radiation Facility for tomographic reconstruction.