Low-Dose X-ray CT Reconstruction via Dictionary Learning

By Qiong Xu, Hengyong Yu, Xuanqin Mou, Lei Zhang, Jiang Hsieh, Ge Wang. IEEE Transactions on Medical Imaging, 2012

691 citations recorded by the source corpus.

Although diagnostic medical imaging provides enormous benefits in the early detection and accuracy diagnosis of various diseases, there are growing concerns on the potential side effect of radiation induced genetic, cancerous and other diseases. How to reduce radiation dose while maintaining the diagnostic performance is a major challenge in the computed tomography (CT) field. Inspired by the compressive sensing theory, the sparse constraint in terms of total variation (TV) minimization has already led to promising results for low-dose CT reconstruction. Compared to the discrete gradient transform used in the TV method, dictionary learning is proven to be an effective way for sparse representation. On the other hand, it is important to consider the statistical property of projection data in the low-dose CT case. Recently, we have developed a dictionary learning based approach for low-dose X-ray CT. In this paper, we present this method in detail and evaluate it in experiments. In our method, the sparse constraint in terms of a redundant dictionary is incorporated into an objective function in a statistical iterative reconstruction framework. The dictionary can be either predetermined before an image reconstruction task or adaptively defined during the reconstruction process. An alternating minimization scheme is developed to minimize the objective function. Our approach is evaluated with low-dose X-ray projections collected in animal and human CT studies, and the improvement associated with dictionary learning is quantified relative to filtered backprojection and TV-based reconstructions. The results show that the proposed approach might produce better images with lower noise and more detailed structural features in our selected cases. However, there is no proof that this is true for all kinds of structures.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/d2493cc3887afb1e49d5bd9c494345db0ee6b8f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Jong Chul Ye
2. Ozan Öktem
3. Jonas Adler
4. Paul S. Babyn
5. Xin Yi
6. Yanbo Zhang
7. Hengyong Yu
8. Ge Wang

In Radiology, Nuclear Medicine and Imaging

1. Jong Chul Ye
2. Ozan Öktem
3. Paul S. Babyn
4. Xin Yi
5. Jonas Adler
6. Michael T. McCann
7. Hengyong Yu
8. Yanbo Zhang

Citations in the corpus

• Artifact Suppressed Dictionary Learning for Low-Dose CT Image Processing (2014, methodology): “They concerned undersampled MRI image reconstruction [32], resolution enhancement [33], interior tomography [34], DL constrained iterative LDCT reconstruction [35], 3-D medical image denoising [36], few-views tomography [9-11, 15-17, 37], spectral CT [38] and abdomen LDCT image processing [39].”
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network (2018, positive): “prior information includes non-negativity, maximum CT number, total variation [16], non-local means [17], dictionary learning [18], low rank [19], and their variants.”
• A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution (2018, background): “Since x-ray imaging is mainly a photon-noise dominated process [8], reducing the x-ray exposure will lead to image degradation under other identical conditions.”
• CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction (2017, methodology): “, using a penalized weighted least-squares data term and sparsity-promoting regularizer [34], dictionary learning-based regularizer [35], or generalized total variation regularizer [36].”
• Solving inverse problems using data-driven models (2019, background): “2016), which adds the dictionary D = {φi} ⊂ X as an unknown to the sparse-land model as in global dictionary-based statistical iterative reconstruction (GDSIR) (Xu et al. 2012; see also Chun, Zheng, Long and Fessler 2017).”
• A Perspective on Deep Imaging (2016, background): “More recently, dictionary learning, which is a contemporary machine learning approach, was adapted for MRI and CT image reconstruction [27], [30], [31].”
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss (2017, methodology): “Popular image priors include total variation (TV) and its variants [16]–[18], as well as dictionary learning [19], [20].”
• Deep Convolutional Neural Network for Inverse Problems in Imaging (2016, methodology): “Learning has also been explored for X-ray CT reconstruction; In [43], the authors use a regularization term that promotes patches of the reconstruction to be sparse in a learned dictionary.”
• Learned Primal-Dual Reconstruction (2017, methodology): “Examples of this include dictionary learning [9], but several alternative methods have been investigated, such as learning a variational auto-encoder [10] or using a cascade of”
• Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network (2017, methodology): “like accelerated updating method and has inspired many applications in the medical domain [16, 17, 38, 39, 66].”
• A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction (2016, background): “For example, a dictionary that represents image features such as edges is constructed or updated during the reconstruction process.(12) In addition, existing ridgelets, shearlets, and curvelets can compose the dictionary.”
• Convolutional Neural Network based Metal Artifact Reduction in X-ray Computed Tomography (2017, background): “where rj is the mean number of background events and readout noise variance, which is assumed as a known nonnegative constant [42], [43].”