22 March 2019 in IEEE Transactions on Medical Imaging
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. Qualitative and quantitative results demonstrate that the proposed methods achieve better performance than several existing stateof- the-art methods.
10 January 2018 in Inverse Problems
Spectral computed tomography (CT) has been a promising technique in research and clinics because of its ability to produce improved energy resolution images with narrow energy bins. However, the narrow energy bin image is often affected by serious quantum noise because of the limited number of photons used in the corresponding energy bin. To address this problem, we present an iterative reconstruction method for spectral CT using nonlocal low-rank and sparse matrix decomposition (NLSMD), which exploits the self-similarity of patches that are collected in multi-energy images. Specifically, each set of patches can be decomposed into a low-rank component and a sparse component, and the low-rank component represents the stationary background over different energy bins, while the sparse component represents the rest of the different spectral features in individual energy bins. Subsequently, an effective alternating optimization algorithm was developed to minimize the associated objective function. To validate and evaluate the NLSMD method, qualitative and quantitative studies were conducted by using simulated and real spectral CT data. Experimental results show that the NLSMD method improves spectral CT images in terms of noise reduction, artifact suppression and resolution preservation.
28 August 2023 in IEEE Transactions on Radiation and Plasma Medical Sciences
The radiation dose in computed tomography (CT) examinations is harmful for patients but can be significantly reduced by intuitively decreasing the number of projection views. Reducing projection views usually leads to severe aliasing artifacts in reconstructed images. Previous deep learning (DL) techniques with sparse-view data require sparse-view/full-view CT image pairs to train the network with supervised manners. When the number of projection view changes, the DL network should be retrained with updated sparse-view/full-view CT image pairs. To relieve this limitation, we present a fully unsupervised score-based generative model in sinogram domain for sparse-view CT reconstruction. Specifically, we first train a score-based generative model on full-view sinogram data and use multichannel strategy to form high-dimensional tensor as the network input to capture their prior distribution. Then, at the inference stage, the stochastic differential equation (SDE) solver and data-consistency step were performed iteratively to achieve full-view projection. Filtered back-projection (FBP) algorithm was used to achieve the final image reconstruction. Qualitative and quantitative studies were implemented to evaluate the presented method with several CT data. Experimental results demonstrated that our method achieved comparable or better performance than the supervised learning counterparts.
10 March 2019 in IEEE Transactions on Computational Imaging
Spectral computed tomography (CT) reconstructs multienergy images from data in different energy bins. However, these reconstructed images can be contaminated by noise due to the limited numbers of photons in the corresponding energy bins. In this paper, we propose a spectral CT reconstruction method aided by self-similarity in image-spectral tensors, which utilizes the selfsimilarity of patches in both spatial and spectral domains. Patches with similar structures identified by a joint spatial and spectral searching strategy form a basic tensor unit, and can be utilized to improve image quality. Specifically, each tensor is decomposed into a low-rank component and a sparse component, which respectively represent the stable structures and feature differences across different energy bins. The augmented Lagrange method is applied to optimize the proposed objective function. To validate the performance of the proposed method, several simulated clinical and real data experiments are performed. The qualitative and quantitative results demonstrate that the proposed method outperforms several representative state-of-the-art algorithms in terms of preserving image details and reducing artifacts.
1 August 2023 in IEEE Transactions on Computational Social Systems
The identification of important nodes (vertexes) in multilayer networks has aroused many scholars’ attention and various centrality methods have deen developed. However, the current centralities ignore the impact of community structure on node importance. In this article, we define a community-based centrality for finding key vertexes in multilayer networks, referred to as the CBCM. We first construct a multilayer network model with interlayer edges, which is represented by a fourth-order tensor. Based on the fourth-order tensor, we develop a centrality, called PR_BIS, to measure the importance of vertexes and network layers in multilayer networks, simultaneously. CBCM determines the importance of a vertex in each network layer by combining the following three factors: the PageRank centrality score of the vertex, the importance of the community where the vertex is located, and the ability of the vertex within a community to affect vertexes in other communities within two steps. Based on the importance of all the network layers measured by PR_BIS centrality, we perform weighted fusion for the importance of a vertex in all network layers to obtain the importance of the vertex in multilayer networks. Finally, numerical experiments are performed on several multilayer networks to verify the effectiveness and superiority of CBCM and PR_BIS.
4 February 2022 in IEEE Transactions on Radiation and Plasma Medical Sciences
Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications. Iterative reconstruction is one of the most promising ways to compensate for the increased noise due to the reduction of photon flux. Rather than most existing prior-driven algorithms that benefit from manually designed prior functions or supervised learning schemes, in this work, we integrate the data consistency as a conditional term into the iterative generative model for low-dose CT. At the stage of prior learning, the gradient of data density is directly learned from normal-dose CT images as a prior. Then, at the iterative reconstruction stage, the stochastic gradient descent is employed to update the trained prior with annealed and conditional schemes. The distance between the reconstructed image and the manifold is minimized along with data fidelity during reconstruction. Experimental comparisons demonstrated the noise reduction and detail preservation abilities of the proposed method.