Liver disease is a severe health problem that endangers human health worldwide. Mesenchymal stem cell (MSC) therapy is a novel treatment for patients with different liver diseases due to its vast expansion potential and distinctive immunomodulatory properties. Despite several preclinical trials having confirmed the considerable efficacy of MSC therapy in liver diseases, the questionable safety and efficacy still limit its application. As a precursor cell, MSCs can adjust their characteristics in response to the surrounding microenvironment. The microenvironment provides physical and chemical factors essential for stem cell survival, proliferation, and differentiation. However, the mechanisms are still not completely understood. We, therefore, summarized the mechanisms underlying the MSC immune response, especially the interaction between MSCs and the liver microenvironment, discussing how to achieve better therapeutic effects.
In recent decades, researchers have concentrated their efforts on developing techniques to denoise low-dose, sparse-angle CT images. Currently, mainstream low-dose CT methods include traditional iterative reconstruction algorithms and deep learning algorithms. However, these methods still exhibit transition smoothing, noise, and artifact residue. Inspired by the idea of deep learning, we propose an improved fully convolutional neural network using external attention. The network incorporates a novel external attention module, and use perceptual loss as the loss function which is used to construct a fully convolutional model with dense connections. This model fuses extracted feature information to achieve image denoising. Following training, the proposed EA-FCN demonstrated superior performance on actual clinical CT images. Furthermore, our method achieved favorable subjective and objective evaluations in terms of noise and artifact suppression.