Few-view Computed Tomography Image Reconstruction Research Articles

Few-View CT Image Reconstruction via Least-Squares Methods: Assessment and Optimization

The use of iterative algebraic methods applied to the reconstruction of computed tomography (CT) medical images is proliferating to reconstruct high-quality CT images using far fewer views than through analytical methods. This would imply reducing the dose of X-rays applied to patients who require this medical test. Least-squares methods are a promising approach to reconstruct the images with few projections obtaining high quality. In addition, since these techniques involve a high computational load, it is necessary to develop efficient methods that make use of high-performance-computing tools to accelerate reconstructions. In this paper, three least-squares methods are analyzed—Least-Squares Model Based (LSMB), Least-Squares QR (LSQR), and Least-Squares Minimal Residual (LSMR)—to determine whether the LSMB method provides faster convergence and thus lower computational times. Moreover, a block version of both the LSQR method and the LSMR method was implemented. With them, multiple right-hand sides (multiple slices) can be solved at the same time, taking advantage of the parallelism obtained with the implementation of the methods using the Intel Math Kernel Library. The two implementations are compared in terms of convergence, time, and quality of the images obtained, reducing the number of projections and combining them with a regularization and acceleration technique. The experiments show how the implementations are scalable and obtain images of good quality from a reduced number of views, with the LSQR method being better suited for this application.

Deep Encoder-Decoder Adversarial Reconstruction(DEAR) Network for 3D CT from Few-View Data.

X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizing X-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dose has been an important topic in recent years. Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper, we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT image reconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in 3D instead of 2D geometry, a 3D deep network has a great potential for improving the image quality in a data driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publicly available abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other 2D deep learning methods, the proposed DEAR-3D network can utilize 3D information to produce promising reconstruction results.

Few-view CT image reconstruction using improved total variation regularization.

X-ray radiation is harmful to human health. Thus, obtaining a better reconstructed image with few projection view constraints is a major challenge in the computed tomography (CT) field to reduce radiation dose. In this study, we proposed and tested a new algorithm that combines penalized weighted least-squares using total generalized variation (PWLS-TGV) and dictionary learning (DL), named PWLS-TGV-DL to address this challenge. We first presented and tested this new algorithm and evaluated it through both data simulation and physical experiments. We then analyzed experimental data in terms of image qualitative and quantitative measures, such as the structural similarity index (SSIM) and the root mean square error (RMSE). The experiments and data analysis indicated that applying the new algorithm to CT data recovered images more efficiently and yielded better results than the traditional CT image reconstruction approaches.

Few-view computed tomography image reconstruction using mean curvature model with curvature smoothing and surface fitting

The edge and curve of an image surface are crucial visual cues in vision psychology. Studies show that human beings can effectively process curvature information, such as distinguishing the concavity and convexity of an image. This finding indicates that curvature is essential for a desired image to be felt authentic and real. In this paper, a novel few-view computed tomography (CT) image reconstruction model is proposed based on mean curvature (MC). Similar to the total variation model, the MC employs the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm to utilize the sparse prior information. Constructing efficient numerical algorithms for minimizing the MC model is significant due to the associated high-order Euler-Lagrange equations. A two-step numerical method, including curvature smoothing and surface fitting, is presented to solve the proposed model, which can be stably and efficiently solved by the alternating direction minimization. By applying the variable splitting method, the explicit solutions of the corresponding subproblems can be efficiently and quickly approximated by fast Fourier transform and the proximal point method. The accuracy and efficiency of the simulated and real data are qualitatively and quantitatively evaluated to verify the efficiency and feasibility of the proposed method. Comparisons with conventional algorithms demonstrate that the proposed approach has considerable advantages in few-view CT reconstruction problems.

Constrained Total Generalized p-Variation Minimization for Few-View X-Ray Computed Tomography Image Reconstruction.

Total generalized variation (TGV)-based computed tomography (CT) image reconstruction, which utilizes high-order image derivatives, is superior to total variation-based methods in terms of the preservation of edge information and the suppression of unfavorable staircase effects. However, conventional TGV regularization employs l1-based form, which is not the most direct method for maximizing sparsity prior. In this study, we propose a total generalized p-variation (TGpV) regularization model to improve the sparsity exploitation of TGV and offer efficient solutions to few-view CT image reconstruction problems. To solve the nonconvex optimization problem of the TGpV minimization model, we then present an efficient iterative algorithm based on the alternating minimization of augmented Lagrangian function. All of the resulting subproblems decoupled by variable splitting admit explicit solutions by applying alternating minimization method and generalized p-shrinkage mapping. In addition, approximate solutions that can be easily performed and quickly calculated through fast Fourier transform are derived using the proximal point method to reduce the cost of inner subproblems. The accuracy and efficiency of the simulated and real data are qualitatively and quantitatively evaluated to validate the efficiency and feasibility of the proposed method. Overall, the proposed method exhibits reasonable performance and outperforms the original TGV-based method when applied to few-view problems.

Improved total variation minimization method for few-view computed tomography image reconstruction.

BackgroundDue to the harmful radiation dose effects for patients, minimizing the x-ray exposure risk has been an area of active research in medical computed tomography (CT) imaging. In CT, reducing the number of projection views is an effective means for reducing dose. The use of fewer projection views can also lead to a reduced imaging time and minimizing potential motion artifacts. However, conventional CT image reconstruction methods will appears prominent streak artifacts for few-view data. Inspired by the compressive sampling (CS) theory, iterative CT reconstruction algorithms have been developed and generated impressive results.MethodIn this paper, we propose a few-view adaptive prior image total variation (API-TV) algorithm for CT image reconstruction. The prior image reconstructed by a conventional analytic algorithm such as filtered backprojection (FBP) algorithm from densely angular-sampled projections.ResultsTo validate and evaluate the performance of the proposed algorithm, we carried out quantitative evaluation studies in computer simulation and physical experiment.ConclusionThe results show that the API-TV algorithm can yield images with quality comparable to that obtained with existing algorithms.