NVAM-Net: deep learning networks for reconstructing high-quality fiber orientation distributions.

PURPOSE: Diffusion magnetic resonance imaging (dMRI) is a widely used non-invasive method for investigating brain anatomical structures. Conventional techniques for estimating fiber orientation distribution (FOD) from dMRI data often neglect voxel-level spatial relationships, leading to ambiguous associations between target voxels and their neighbors, which, in turn, adversely impacts FOD accuracy. This study aims to address this issue by introducing a novel neural network, the neighboring voxel attention mechanism network (NVAM-Net), designed to reconstruct high-quality FOD images. METHODS: The NVAM-Net leverages a Transformer architecture and incorporates two innovative attention mechanisms: voxel attention and surface attention. These mechanisms are specifically designed to capture overlooked features among neighboring voxels. The processed features are subsequently passed through two fully connected layers, further enhancing FOD estimation accuracy by separately estimating spherical harmonics (SH) coefficients of varying orders. RESULTS: The experimental findings, based on the Human Connectome Project (HCP) dataset, reveal that the reconstructed super-resolution FOD images achieve results comparable to those obtained through more advanced dMRI acquisition protocols. These results underscore the NVAM-Net's robust performance in reconstructing multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD). CONCLUSION: In summary, this research underscores the NVAM-Net's advantages and practical feasibility in reconstructing high-quality FOD images. It provides a reliable reference point for clinical applications in the field of diffusion magnetic resonance imaging.

Rapid analyzing mixed STR profiles based on the global minimum residual method.

The analysis of mixed short tandem repeat (STR) profiles has been long considered as a difficult challenge in the forensic DNA analysis. In the context of China, the current approach to analyze mixed STR profiles depends mostly on forensic manual method. However, besides the inefficiency, this technique is also susceptible to subjective biases in interpreting analysis results, which can hardly meet up with the growing demand for STR profiles analysis. In response, this study introduces an innovative method known as the global minimum residual method, which not only predicts the proportion of each contributor within a mixture, but also delivers accurate analysis results. The global minimum residual method first gives new definitions to the mixture proportion, then optimizes the allele model. After that, it comprehensively considers all loci present in the STR profile, accumulates and sums the residual values of each locus and selects the mixture proportion with the minimum accumulative sum as the inference result. Furthermore, the grey wolf optimizer is also employed to expedite the search for the optimal value. Notably, for two-person STR profiles, the high accuracy and remarkable efficiency of the global minimum residual method can bring convenience to realize extensive STR profile analysis. The optimization scheme established in this research has exhibited exceptional outcomes in practical applications, boasting significant utility and offering an innovative avenue in the realm of mixed STR profile analysis.

MFCA-MICNN: a convolutional neural network with multiscale fast channel attention and multibranch irregular convolution for noise removal in dMRI.

Diffusion magnetic resonance imaging (dMRI) currently stands as the foremost noninvasive method for quantifying brain tissue microstructure and reconstructing white matter fiber pathways. However, the inherent free diffusion motion of water molecules in dMRI results in signal decay, diminishing the signal-to-noise ratio (SNR) and adversely affecting the accuracy and precision of microstructural data. In response to this challenge, we propose a novel method known as the Multiscale Fast Attention-Multibranch Irregular Convolutional Neural Network for dMRI image denoising. In this work, we introduce Multiscale Fast Channel Attention, a novel approach for efficient multiscale feature extraction with attention weight computation across feature channels. This enhances the model's capability to capture complex features and improves overall performance. Furthermore, we propose a multi-branch irregular convolutional architecture that effectively disrupts spatial noise correlation and captures noise features, thereby further enhancing the denoising performance of the model. Lastly, we design a novel loss function, which ensures excellent performance in both edge and flat regions. Experimental results demonstrate that the proposed method outperforms other state-of-the-art deep learning denoising methods in both quantitative and qualitative aspects for dMRI image denoising with fewer parameters and faster operational speed.

Dynamics of a stochastic HBV infection model with drug therapy and immune response.

Hepatitis B is a disease that damages the liver, and its control has become a public health problem that needs to be solved urgently. In this paper, we investigate analytically and numerically the dynamics of a new stochastic HBV infection model with antiviral therapies and immune response represented by CTL cells. Through using the theory of stochastic differential equations, constructing appropriate Lyapunov functions and applying Itô's formula, we prove that the disease-free equilibrium of the stochastic HBV model is stochastically asymptotically stable in the large, which reveals that the HBV infection will be eradicated with probability one. Moreover, the asymptotic behavior of globally positive solution of the stochastic model near the endemic equilibrium of the corresponding deterministic HBV model is studied. By using the Milstein's method, we provide the numerical simulations to support the analysis results, which shows that sufficiently small noise will not change the dynamic behavior, while large noise can induce the disappearance of the infection. In addition, the effect of inhibiting virus production is more significant than that of blocking new infection to some extent, and the combination of two treatment methods may be the better way to reduce HBV infection and the concentration of free virus.