Low-dose CT reconstruction using dataset-free learning.

Low-Dose computer tomography (LDCT) is an ideal alternative to reduce radiation risk in clinical applications. Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging. In this paper, we propose an unsupervised and training data-free learning reconstruction method for LDCT imaging that avoids the requirement for training data. The proposed method is a post-processing technique that aims to enhance the initial low-quality reconstruction results, and it reconstructs the high-quality images by neural work training that minimizes the ℓ1-norm distance between the CT measurements and their corresponding simulated sinogram data, as well as the total variation (TV) value of the reconstructed image. Moreover, the proposed method does not require to set the weights for both the data fidelity term and the plenty term. Experimental results on the AAPM challenge data and LoDoPab-CT data demonstrate that the proposed method is able to effectively suppress the noise and preserve the tiny structures. Also, these results demonstrate the rapid convergence and low computational cost of the proposed method. The source code is available at https://github.com/linfengyu77/IRLDCT.

A Generalized Nesterov-Accelerated Second-Order Latent Factor Model for High-Dimensional and Incomplete Data.

High-dimensional and incomplete (HDI) data are frequently encountered in big date-related applications for describing restricted observed interactions among large node sets. How to perform accurate and efficient representation learning on such HDI data is a hot yet thorny issue. A latent factor (LF) model has proven to be efficient in addressing it. However, the objective function of an LF model is nonconvex. Commonly adopted first-order methods cannot approach its second-order stationary point, thereby resulting in accuracy loss. On the other hand, traditional second-order methods are impractical for LF models since they suffer from high computational costs due to the required operations on the objective's huge Hessian matrix. In order to address this issue, this study proposes a generalized Nesterov-accelerated second-order LF (GNSLF) model that integrates twofold conceptions: 1) acquiring proper second-order step efficiently by adopting a Hessian-vector algorithm and 2) embedding the second-order step into a generalized Nesterov's acceleration (GNA) method for speeding up its linear search process. The analysis focuses on the local convergence for GNSLF's nonconvex cost function instead of the global convergence has been taken; its local convergence properties have been provided with theoretical proofs. Experimental results on six HDI data cases demonstrate that GNSLF performs better than state-of-the-art LF models in accuracy for missing data estimation with high efficiency, i.e., a second-order model can be accelerated by incorporating GNA without accuracy loss.

[CT and MRI fusion based on generative adversarial network and convolutional neural networks under image enhancement].

Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q AB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.

A Smoothed Matrix Multivariate Elliptical Distribution-Based Projection Method for Feature Extraction.

Big data has the traits such as "the curse of dimensionality," high storage cost, and heavy computation burden. Self-representation-based feature extraction methods cannot effectively deal with the image-level structural noise in the data, so how to character a better relationship of reconstruction representation is very important. Recently, sparse representation with smoothed matrix multivariate elliptical distribution (SMED) using structural information to handle low-rank error images caused by illumination or occlusion has been proposed. Based on SMED, we present a new method named SMEDP for feature extraction. SMEDP firstly utilizes SMED to automatically construct an adjacency graph and then obtains an optimal projection matrix by maximizing the ratio of the local scatter matrix and the total scatter matrix in the PCA subspace. Experiments on the COIL-20 object database, ORL face database, and CMU PIE face database prove that SMEDP works well and can achieve considerable visual and recognition performance than the relevant methods.

Direct numerical simulation of low Reynolds number turbulent air-water transport in fuel cell flow channel.

With performance improvement of low-temperature fuel cell (FC), high reactant supply and water generation rates may induce air-water turbulence in the FC flow channel. In this research, an air-water turbulent direct numerical simulation (DNS) model is developed to simulate different droplet sizes, locations and interactions in the air-water transport processes comprehensively. It is found that a larger droplet breaks up more easily in turbulence, and a smaller droplet tends to keep lumped. The droplet at corner does not break up because it is away from channel center. The droplet interaction simulations show that the small droplets merge to form slugs, but still keep lumped in turbulence. It is suggested that two conditions need to be satisfied for droplet break up in FC flow channel, one is turbulent flow, and another is that the droplet needs to be large enough and occupy the center region of flow channel to suffer sufficient turbulence fluctuations. The DNS results illustrate some unique phenomena in turbulent flow, and show that the turbulence has significant effect on the air-water flow behavior in FC flow channel.

Changes in main nutrients and medicinal composition of Chinese yam (Dioscorea opposita) tubers during storage.

The changes in the main nutrient and medicinal components during the storage of the Chinese yam (Dioscorea opposita) tubers were studied. The harvested tubers were stored under ambient conditions (10 °C to 18 °C, 60 % to 80 % Relative Humidity) and cold temperature and packaged conditions (4 °C, 60 % to 65 % Relative Humidity) for 45 day. The allantoin, starch, total alcohol-soluble sugar, reducing sugar, protein, and moisture contents of the samples were evaluated. Their amylase activities were also investigated. Results of ambient conditions indicated that, during storage, moisture decreased by 67.96 % to 56.51 %, and total sugars, reducing sugars, and protein increased by 6.49 % to 9.81 %, 1.7 % to 2.27 %, and 13.02 % to 14.55 %, respectively. Starch and enzyme activities increased during the early days of storage and progressively decreased, and the content of allantoin changed in volatility. The changes were more significant at cold temperatures and packaged conditions than at ambient conditions. This result suggests that after-ripening occurred in the early stages of Chinese yam tubers, which positively affected the nutritional potential of the tubers by a marked increase in nutrients. Low-temperature sweetening greatly affects the nutritional potential of tubers by a series of complicated interactions between starch and sugars at 4 °C.