Browse Articles
Discover research articles across all indexed journals
Involvement of LncRNA FAF in chemotherapy-induced cardiotoxicity by mediating pyroptosis through modulation of the NLRP3-Caspase-1 signaling pathway
Effectiveness of rehabilitation dose heterogeneity for improving functional outcomes of patients with acute stroke: a nationwide observational study
A MAGDM approach based on dual hesitant Q-rung orthopair fuzzy Dombi norm with Hamy mean operators and its application
Thixo-viscoelastoplastic rheological characterisation of human mucus using a multimode BMP constitutive equation approach
Binding modes and interaction mechanism of bisphenol A and its analogs in constitutive androstane receptor
Topological interface state-based photonic crystal sensor with porous cap layer for high-performance biosensing
Optogenetic regulation of chloride ions in reactive astrocytes may mitigate Parkinson’s disease pathology
Numerical study on small hole leakage and diffusion of hydrogen in buried pipelines
Impact of SAAC accreditation on laboratories in Saudi Arabia according to ISO/IEC 17025:2017
Land use and land cover changes drive ecosystem services value in the Chinese county of Qianyang
Abstract Understanding how land use changes affect ecosystem services is essential for guiding sustainable development and environmental policy. In rapidly urbanizing regions, quantifying these impacts helps inform land management decisions. This study aims to analyze the impact of land use and land cover (LULC) changes on Ecosystem Services Value (ESV) in Qianyang County, China. We utilized land use data from 2007 to 2022 with a spatial resolution of 30 m. The spatial distribution and clustering of ESV were examined using spatial statistical methods. The Patch-generating Land Use Simulation (PLUS) model, which simulates LULC changes under three scenarios for 2050, was employed to calculate ESV and identify driving forces. Results show that urbanization and topography were the main driving factors for LULC changes in Qianyang County. Our findings provide valuable insights into sustainable land management and ecosystem conservation in the region.
Soil organic carbon fractions and their associated bacterial and fungal abundance in alpine ecosystems
Introducing an efficient method for feature extraction in image retrieval systems
Structural model of hard overburden shell in thick coal seam and its application
Pharmacological activation of SERCA2 reverses ER calcium dysregulation and depression-like behaviors in hyperglycemic mice
A unified multi-task learning framework for automated assessment of left ventricular structure and its systolic function from echocardiography
Network pharmacology and molecular docking reveal antiviral mechanisms of silver nanoparticles synthesized by Oscillatoria sp. against HCV pathogenesis
Automated skin cancer detection using MedFusionNet with attention-based fusion of ConvNeXt and vision transformer
Abstract Skin cancer, especially melanoma, the most severe type, has increased in recent decades. It develops from cells that grow abnormally and can invade the surrounding tissue and spread throughout the body. Early and accurate diagnosis is essential to prevent disease progression and allow for less invasive clinical treatment. The extraction of complex dermoscopic images and the improvement of lesion classification performance have significantly improved skin cancer diagnosis through the use of convolutional neural networks (CNNs). In this study, a novel deep convolutional neural network that combines ConvNeXt and Vision Transformer (ViT) architectures through an adaptive attention-based approach for advanced feature fusion to automatically multi-classify skin cancer samples. This model is evaluated on two dermoscopy benchmark datasets, including ISIC-2019 and HAM10000 and both datasets reflect the real-world problem of class imbalance. The evaluation results of MedFusionNet are calculated using various evaluation metrics, including accuracy, precision, recall and AUC and compared with deep learning algorithms such as ResNet50, MobileNet V2, DenseNet121 and ViT-B16. The experimental results show that MedFusionNet outperforms the current models with a classification accuracy of 98.80% and 97.90% for HAM10000 and ISIC-2019, respectively. Grad-CAM visualizations qualitatively show that the model focuses on clinically relevant lesion regions, providing interpretive insight without claiming complete causal explainability. The results show that the proposed model can efficiently handle multi-class tasks in dermatological imaging and MedFusionNet is a suitable choice for implementation in real-world computer-aided diagnosis systems.