Sparse-view Computed Tomography Research Articles

Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction

Recently, a number of approaches to low-dose computed tomography (CT) have been developed and deployed in commercialized CT scanners. Tube current reduction is perhaps the most actively explored technology with advanced image reconstruction algorithms. Sparse data sampling is another viable option to the low-dose CT, and sparse-view CT has been particularly of interest among the researchers in CT community. Since analytic image reconstruction algorithms would lead to severe image artifacts, various iterative algorithms have been developed for reconstructing images from sparsely view-sampled projection data. However, iterative algorithms take much longer computation time than the analytic algorithms, and images are usually prone to different types of image artifacts that heavily depend on the reconstruction parameters. Interpolation methods have also been utilized to fill the missing data in the sinogram of sparse-view CT thus providing synthetically full data for analytic image reconstruction. In this work, we introduce a deep-neural-network-enabled sinogram synthesis method for sparse-view CT, and show its outperformance to the existing interpolation methods and also to the iterative image reconstruction approach.

Low-dose single-energy material decomposition in radiography using a sparse-view computed tomography scan

Dual-energy material decomposition (DEMD) is a well-established theoretical x-ray technique that uses low- and high-kilovoltage radiographs to separate soft tissue and bone in radiography and computed tomography (CT). However, it requires double exposures that result in increased patient radiation doses, causes increases in the execution time, and generates errors due to misregistration attributed to the patient motion between two scans. In this study, we investigated a low-dose, single-energy material decomposition (LSEMD) method in radiography using a sparse-view CT scan where the attenuation length in the object was estimated from the CT image. We performed a systematic simulation and an experiment to demonstrate the feasibility of use of the LSEMD method in radiography. Only 60 projections, far fewer than those required by the Nyquist sampling theory, were acquired at an x-ray tube voltage of 80 kVp, and were used to reconstruct a sparse-view CT image with a state-of-the-art dictionary-learning (DL) algorithm. We investigated the image performance of the LSEMD and compared the elicited results with those obtained with the use of DEMD (80 kVp and 120 kVp were used). Our results indicate that the DL algorithm produced high-quality sparse-view CT images. Accordingly, the LSEMD method yielded material decomposition results that were very similar to the results elicited by the conventional DEMD method in radiography.

A projection-based sparse-view virtual monochromatic computed tomography method based on a compressed-sensing algorithm

Computed tomography (CT) images obtained at different monochromatic X-ray beam energies can be synthesized from conventional dual-energy CT scans. This approach to synthesizing monochromatic CT images is based on basis material decomposition and the knowledge of attenuation of basis materials. The main benefits of virtual monochromatic CT (VMCT) images include reduction of beam-hardening artifacts and provision of accurate atteuation measurements. Despite the VMCT's benefits, main concerns in the use of VMCT in clinics may be high radiation dose the patient is exposed to. In this study, we investigated a projection-based sparse-view VMCT method in an attempt to overcome these difficulties. We performed a computational simulation and evaluated the feasibility of using the VMCT method in sparse-view CT. Two polychromatic data sets of 90 projections, far less than what is required by the Nyquist sampling theory, were simulated at 80 kVp and 140 kVp and used to synthesize VMCT images at a monochromatic energy range of 40–140 keV . VMCT image characteristics were quantitatively evaluated in terms of intensity profile, the contrast-to-noise ratio, and the signal-to-noise ratio. Our results indicate that the CS-based algorithm produced high-quality sparse-view CT images, and thereby the proposed VMCT method yielded CT image results of improved beam-hardening artifacts and quantitative measurements.

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT.

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance.

A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution.

Sparse-view computed tomography (CT) holds great promise for speeding up data acquisition and reducing radiation dose in CT scans. Recent advances in reconstruction algorithms for sparse-view CT, such as iterative reconstruction algorithms, obtained high-quality image while requiring advanced computing power. Lately, deep learning (DL) has been widely used in various applications and has obtained many remarkable outcomes. In this paper, we propose a new method for sparse-view CT reconstruction based on the DL approach. The method can be divided into two steps. First, filter backprojection (FBP) was used to reconstruct the CT image from sparsely sampled sinogram. Then, the FBP results were fed to a DL neural network, which is a DenseNet and deconvolution-based network (DD-Net). The DD-Net combines the advantages of DenseNet and deconvolution and applies shortcut connections to concatenate DenseNet and deconvolution to accelerate the training speed of the network; all of those operations can greatly increase the depth of network while enhancing the expression ability of the network. After the training, the proposed DD-Net achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation. Compared with the other state-of-the-art reconstruction methods, the DD-Net method can increase the structure similarity by up to 18% and reduce the root mean square error by up to 42%. These results indicate that DD-Net has great potential for sparse-view CT image reconstruction.

Iterative reconstruction for sparse-view x-ray CT using alpha-divergence constrained total generalized variation minimization.

Accurate statistical model of the measured projection data is essential for computed tomography (CT) image reconstruction. The transmission data can be described by a compound Poisson distribution upon an electronic noise background. However, such a statistical distribution is numerically intractable for image reconstruction. Although the sinogram data is easily manipulated, it lacks a statistical description for image reconstruction. To address this problem, we present an alpha-divergence constrained total generalized variation (AD-TGV) method for sparse-view x-ray CT image reconstruction. The AD-TGV method is formulated as an optimization problem, which balances the alpha-divergence (AD) fidelity and total generalized variation (TGV) regularization in one framework. The alpha-divergence is used to measure the discrepancy between the measured and estimated projection data. The TGV regularization can effectively eliminate the staircase and patchy artifacts which is often observed in total variation (TV) regularization. A modified proximal forward-backward splitting algorithm was proposed to minimize the associated objective function. Qualitative and quantitative evaluations were carried out on both phantom and patient data. Compared with the original TV-based method, the evaluations clearly demonstrate that the AD-TGV method achieves higher accuracy and lower noise, while preserving structural details. The experimental results show that the presented AD-TGV method can achieve more gains over the AD-TV method in preserving structural details and suppressing image noise and undesired patchy artifacts. The authors can draw the conclusion that the presented AD-TGV method is potential for radiation dose reduction by lowering the milliampere-seconds (mAs) and/or reducing the number of projection views.

Fast alternating projection methods for constrained tomographic reconstruction.

The alternating projection algorithms are easy to implement and effective for large-scale complex optimization problems, such as constrained reconstruction of X-ray computed tomography (CT). A typical method is to use projection onto convex sets (POCS) for data fidelity, nonnegative constraints combined with total variation (TV) minimization (so called TV-POCS) for sparse-view CT reconstruction. However, this type of method relies on empirically selected parameters for satisfactory reconstruction and is generally slow and lack of convergence analysis. In this work, we use a convex feasibility set approach to address the problems associated with TV-POCS and propose a framework using full sequential alternating projections or POCS (FS-POCS) to find the solution in the intersection of convex constraints of bounded TV function, bounded data fidelity error and non-negativity. The rationale behind FS-POCS is that the mathematically optimal solution of the constrained objective function may not be the physically optimal solution. The breakdown of constrained reconstruction into an intersection of several feasible sets can lead to faster convergence and better quantification of reconstruction parameters in a physical meaningful way than that in an empirical way of trial-and-error. In addition, for large-scale optimization problems, first order methods are usually used. Not only is the condition for convergence of gradient-based methods derived, but also a primal-dual hybrid gradient (PDHG) method is used for fast convergence of bounded TV. The newly proposed FS-POCS is evaluated and compared with TV-POCS and another convex feasibility projection method (CPTV) using both digital phantom and pseudo-real CT data to show its superior performance on reconstruction speed, image quality and quantification.

MO-DE-207A-11: Sparse-View CT Reconstruction Via a Novel Non-Local Means Method

Purpose: Sparse-view computed tomography (CT) reconstruction is an effective strategy to reduce the radiation dose delivered to patients. Due to its insufficiency of measurements, traditional non-local means (NLM) based reconstruction methods often lead to over-smoothness in image edges. To address this problem, an adaptive NLM reconstruction method based on rotational invariance (RIANLM) is proposed. Methods: The method consists of four steps: 1) Initializing parameters; 2) Algebraic reconstruction technique (ART) reconstruction using raw projection data; 3) Positivity constraint of the image reconstructed by ART; 4) Update reconstructed image by using RIANLM filtering. In RIANLM, a novel similarity metric that is rotational invariance is proposed and used to calculate the distance between two patches. In this way, any patch with similar structure but different orientation to the reference patch would win a relatively large weight to avoid over-smoothed image. Moreover, the parameter h in RIANLM which controls the decay of the weights is adaptive to avoid over-smoothness, while it in NLM is not adaptive during the whole reconstruction process. The proposed method is named as ART-RIANLM and validated on Shepp-Logan phantom and clinical projection data. Results: In our experiments, the searching neighborhood size is set to 15 by 15 and the similarity window is set to 3 by 3. For the simulated case with a resolution of 256 by 256 Shepp-Logan phantom, the ART-RIANLM produces higher SNR (35.38dB<24.00dB) and lower MAE (0.0006<0.0023) reconstructed image than ART-NLM. The visual inspection demonstrated that the proposed method could suppress artifacts or noises more effectively and preserve image edges better. Similar results were found for clinical data case. Conclusion: A novel ART-RIANLM method for sparse-view CT reconstruction is presented with superior image. Compared to the conventional ART-NLM method, the SNR and MAE from ART-RIANLM increases 47% and decreases 74%, respectively.

Novel Fourier-based iterative reconstruction for sparse fan projection using alternating direction total variation minimization**Projected supported by the National High Technology Research and Development Program of China (Grant No. 2012AA011603) and the National Natural Science Foundation of China (Grant No. 61372172).

Sparse-view x-ray computed tomography (CT) imaging is an interesting topic in CT field and can efficiently decrease radiation dose. Compared with spatial reconstruction, a Fourier-based algorithm has advantages in reconstruction speed and memory usage. A novel Fourier-based iterative reconstruction technique that utilizes non-uniform fast Fourier transform (NUFFT) is presented in this work along with advanced total variation (TV) regularization for a fan sparse-view CT. The proposition of a selective matrix contributes to improve reconstruction quality. The new method employs the NUFFT and its adjoin to iterate back and forth between the Fourier and image space. The performance of the proposed algorithm is demonstrated through a series of digital simulations and experimental phantom studies. Results of the proposed algorithm are compared with those of existing TV-regularized techniques based on compressed sensing method, as well as basic algebraic reconstruction technique. Compared with the existing TV-regularized techniques, the proposed Fourier-based technique significantly improves convergence rate and reduces memory allocation, respectively.

Median prior constrained TV algorithm for sparse view low-dose CT reconstruction

It is known that lowering the X-ray tube current (mAs) or tube voltage (kVp) and simultaneously reducing the total number of X-ray views (sparse view) is an effective means to achieve low-dose in computed tomography (CT) scan. However, the associated image quality by the conventional filtered back-projection (FBP) usually degrades due to the excessive quantum noise. Although sparse-view CT reconstruction algorithm via total variation (TV), in the scanning protocol of reducing X-ray tube current, has been demonstrated to be able to result in significant radiation dose reduction while maintain image quality, noticeable patchy artifacts still exist in reconstructed images. In this study, to address the problem of patchy artifacts, we proposed a median prior constrained TV regularization to retain the image quality by introducing an auxiliary vector m in register with the object. Specifically, the approximate action of m is to draw, in each iteration, an object voxel toward its own local median, aiming to improve low-dose image quality with sparse-view projection measurements. Subsequently, an alternating optimization algorithm is adopted to optimize the associative objective function. We refer to the median prior constrained TV regularization as “TV_MP” for simplicity. Experimental results on digital phantoms and clinical phantom demonstrated that the proposed TV_MP with appropriate control parameters can not only ensure a higher signal to noise ratio (SNR) of the reconstructed image, but also its resolution compared with the original TV method.

NUFFT-Based Iterative Image Reconstruction via Alternating Direction Total Variation Minimization for Sparse-View CT.

Sparse-view imaging is a promising scanning method which can reduce the radiation dose in X-ray computed tomography (CT). Reconstruction algorithm for sparse-view imaging system is of significant importance. The adoption of the spatial iterative algorithm for CT image reconstruction has a low operation efficiency and high computation requirement. A novel Fourier-based iterative reconstruction technique that utilizes nonuniform fast Fourier transform is presented in this study along with the advanced total variation (TV) regularization for sparse-view CT. Combined with the alternating direction method, the proposed approach shows excellent efficiency and rapid convergence property. Numerical simulations and real data experiments are performed on a parallel beam CT. Experimental results validate that the proposed method has higher computational efficiency and better reconstruction quality than the conventional algorithms, such as simultaneous algebraic reconstruction technique using TV method and the alternating direction total variation minimization approach, with the same time duration. The proposed method appears to have extensive applications in X-ray CT imaging.

Iterative Image Reconstruction for Sparse-View CT Using Normal-Dose Image Induced Total Variation Prior

X-ray computed tomography (CT) iterative image reconstruction from sparse-view projection data has been an important research topic for radiation reduction in clinic. In this paper, to relieve the requirement of misalignment reduction operation of the prior image constrained compressed sensing (PICCS) approach introduced by Chen et al, we present an iterative image reconstruction approach for sparse-view CT using a normal-dose image induced total variation (ndiTV) prior. The associative objective function of the present approach is constructed under the penalized weighed least-square (PWLS) criteria, which contains two terms, i.e., the weighted least-square (WLS) fidelity and the ndiTV prior, and is referred to as “PWLS-ndiTV”. Specifically, the WLS fidelity term is built based on an accurate relationship between the variance and mean of projection data in the presence of electronic background noise. The ndiTV prior term is designed to reduce the influence of the misalignment between the desired- and prior- image by using a normal-dose image induced non-local means (ndiNLM) filter. Subsequently, a modified steepest descent algorithm is adopted to minimize the associative objective function. Experimental results on two different digital phantoms and an anthropomorphic torso phantom show that the present PWLS-ndiTV approach for sparse-view CT image reconstruction can achieve noticeable gains over the existing similar approaches in terms of noise reduction, resolution-noise tradeoff, and low-contrast object detection.

Image reconstruction for sparse-view CT and interior CT-introduction to compressed sensing and differentiated backprojection.

New designs of future computed tomography (CT) scanners called sparse-view CT and interior CT have been considered in the CT community. Since these CTs measure only incomplete projection data, a key to put these CT scanners to practical use is a development of advanced image reconstruction methods. After 2000, there was a large progress in this research area briefly summarized as follows. In the sparse-view CT, various image reconstruction methods using the compressed sensing (CS) framework have been developed towards reconstructing clinically feasible images from a reduced number of projection data. In the interior CT, several novel theoretical results on solution uniqueness and solution stability have been obtained thanks to the discovery of a new class of reconstruction methods called differentiated backprojection (DBP). In this paper, we mainly review this progress including mathematical principles of the CS image reconstruction and the DBP image reconstruction for readers unfamiliar with this area. We also show some experimental results from our past research to demonstrate that this progress is not only theoretically elegant but also works in practical imaging situations.

Improved Compressed Sensing-Based Algorithm for Sparse-View CT Image Reconstruction

In computed tomography (CT), there are many situations where reconstruction has to be performed with sparse-view data. In sparse-view CT imaging, strong streak artifacts may appear in conventionally reconstructed images due to limited sampling rate that compromises image quality. Compressed sensing (CS) algorithm has shown potential to accurately recover images from highly undersampled data. In the past few years, total-variation-(TV-) based compressed sensing algorithms have been proposed to suppress the streak artifact in CT image reconstruction. In this paper, we propose an efficient compressed sensing-based algorithm for CT image reconstruction from few-view data where we simultaneously minimize three parameters: the ℓ 1 norm, total variation, and a least squares measure. The main feature of our algorithm is the use of two sparsity transforms—discrete wavelet transform and discrete gradient transform. Experiments have been conducted using simulated phantoms and clinical data to evaluate the performance of the proposed algorithm. The results using the proposed scheme show much smaller streaking artifacts and reconstruction errors than other conventional methods.

Adaptive-weighted total variation minimization for sparse data toward low-dose x-ray computed tomography image reconstruction

Previous studies have shown that by minimizing the total variation (TV) of the to-be-estimated image with some data and other constraints, piecewise-smooth x-ray computed tomography (CT) can be reconstructed from sparse-view projection data without introducing notable artifacts. However, due to the piecewise constant assumption for the image, a conventional TV minimization algorithm often suffers from over-smoothness on the edges of the resulting image. To mitigate this drawback, we present an adaptive-weighted TV (AwTV) minimization algorithm in this paper. The presented AwTV model is derived by considering the anisotropic edge property among neighboring image voxels, where the associated weights are expressed as an exponential function and can be adaptively adjusted by the local image-intensity gradient for the purpose of preserving the edge details. Inspired by the previously reported TV-POCS (projection onto convex sets) implementation, a similar AwTV-POCS implementation was developed to minimize the AwTV subject to data and other constraints for the purpose of sparse-view low-dose CT image reconstruction. To evaluate the presented AwTV-POCS algorithm, both qualitative and quantitative studies were performed by computer simulations and phantom experiments. The results show that the presented AwTV-POCS algorithm can yield images with several notable gains, in terms of noise-resolution tradeoff plots and full-width at half-maximum values, as compared to the corresponding conventional TV-POCS algorithm.