Browse Articles
Discover research articles across all indexed journals
Essential health risk communication for recovery after lifting evacuation orders following the Fukushima Daiichi nuclear power plant accident
Dioxygenation of tryptophan residues by superoxide and myeloperoxidase
Grouped multi-scale vision transformer for medical image segmentation
Abstract Medical image segmentation plays a pivotal role in clinical diagnosis and pathological research by delineating regions of interest within medical images. While early approaches based on Convolutional Neural Networks (CNNs) have achieved significant success, their limited receptive field constrains their ability to capture long-range dependencies. Recent advances in Vision Transformers (ViTs) have demonstrated remarkable improvements by leveraging self-attention mechanisms. However, existing ViT-based segmentation models often struggle to effectively capture multi-scale variations within a single attention layer, limiting their capacity to model complex anatomical structures. To address this limitation, we propose Grouped Multi-Scale Attention (GMSA), which enhances multi-scale feature representation by grouping channels and performing self-attention at different scales within a single layer. Additionally, we introduce Inter-Scale Attention (ISA) to facilitate cross-scale feature fusion, further improving segmentation performance. Extensive experiments on the Synapse, ACDC, and ISIC2018 datasets demonstrate the effectiveness of our model, achieving state-of-the-art results in medical image segmentation. Our code is available at: https://github.com/Chen2zheng/ScaleFormer.
Immune checkpoint protein PD-L1 promotes transcription of angiogenic and oncogenic proteins IL-8, Bcl3, and STAT1 in ovarian cancer cells
Biomimetic propulsion system efficiency for unmanned underwater vehicle
Abstract This paper covers experimental research provided for Biomimetic Unmanned Underwater Vehicle (BUUV). The tests were conducted in a laboratory water tunnel equipped with a direct force-measured sensor and system for Particle Image Velocimetry (PIV) analysis. Different control parameters were tested, and then the generated thrust was compared with electric energy consumption. The main goal of the research is to develop a low hydroacoustic noise and high-energy efficiency propulsion system based on single, flexible fins. The final result is a set of Pareto optimal solutions, which makes it possible to draw more general conclusions on the design of the undulating propulsion system.
New routes for spermine biosynthesis
Analysis on the causes of unsatisfactory prevention effect of postpartum VTE in Chinese women
ER stress and viral defense: Advances and future perspectives on plant unfolded protein response in pathogenesis
Building occupancy estimation using single channel CW radar and deep learning
The multiple myeloma drug market
Enhanced identification of small molecules binding to hnRNPA1 via cryptic pockets mapping coupled with X-ray fragment screening
Protective effects of baicalin against deoxynivalenol-induced oxidative and inflammatory damage in chicken-derived hepatic 3D cell cultures
Abstract Deoxynivalenol (DON) is a trichothecene mycotoxin often contaminating grains used in poultry feed production and causing several adverse effects in farm animals. Therefore, it is important to investigate compounds that can be potential candidates to mitigate these effects, such as baicalin. The effects of DON and baicalin were investigated in chicken-derived 3D hepatic cell cultures, and cell viability, LDH activity, oxidative parameters (NRF-2, 8-OHdG) and inflammatory parameters (IL-6, IL-8, IFN-γ) were monitored for 24 and 48 h. Our results suggest that DON reduced cellular metabolic activity but did not prove to be cytotoxic, and baicalin was able to attenuate this adverse effect. The change in extracellular LDH activity suggests that after 48 h the cells have already started to respond to the adverse effects of the toxin and protective mechanisms were induced. Based on the measured oxidative parameters, baicalin showed antioxidant activity, but after longer exposure, our results indicate a prooxidant effect. Baicalin also had an anti-inflammatory effect based on the amount of IL-6 and IL-8, while DON exerted a dose-and time-dependent pleiotropic activity. These results suggest that DON may have an impact on cellular inflammation and oxidative homeostasis, and that baicalin could be able to alleviate these adverse effects.