New AI framework scDECA fuses gene priors with cell-level structure in single-cell data
Researchers have introduced scDECA, a dual-encoder cross-attention framework that combines raw gene expression, pretrained gene priors and local structure to ...
Researchers have introduced scDECA, a dual-encoder cross-attention framework that combines raw gene expression, pretrained gene priors and local structure to ...
A deep learning framework trained on orthophotos from the 2011 Great East Japan Earthquake detected damaged roads and bridges with ...
A retrospective feasibility study reports that a deep learning network substantially improved simulated ultra-low-dose multi-tracer PET/MR images in Alzheimer's disease, ...
Researchers have unveiled an artificial intelligence system that classifies international trade transactions as low, medium, or high risk with reported ...
A dual-decoder deep-learning network localized 14 shoulder bony landmarks on contralateral CT scans with a mean radial error of 2.1 ...
A narrative review of 45 studies finds lightweight AI models such as MobileNet and EfficientNet achieve strong mammography accuracy on ...
A new dual-branch AI framework called TBFuseFormer detects tuberculosis on chest X-rays with 99.39 percent held-out test accuracy after removing ...
A bibliometric review of 382 publications maps the rapid growth, geographic concentration and thematic evolution of artificial intelligence research on ...
A geological-feature enhanced Cascade Mask R-CNN suppresses spectral confusion and class imbalance to recognize landslides in high-resolution satellite imagery, cutting ...
A new review details the major updates to the ACR's Lung-RADS system, from Category 0 and expanded juxtapleural criteria to ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine