Results 271 to 280 of about 1,957,229 (358)

SpaBatch: Deep Learning‐Based Cross‐Slice Integration and 3D Spatial Domain Identification in Spatial Transcriptomics

open access: yesAdvanced Science, EarlyView.
SpaBatch is an end‐to‐end multi‐slice spatial transcriptomics data integration framework. It simultaneously performs embedding learning, spatial feature denoising and reconstruction, batch effect correction, and spatial domain optimization, effectively correcting batch effects and achieving accurate 3D spatial domain identification.
Jinyun Niu   +5 more
wiley   +1 more source

Degradation of CT Low-Contrast Spatial Resolution Due to the Use of Iterative Reconstruction and Reduced Dose Levels.

open access: yesRadiology, 2015
C. McCollough   +6 more
semanticscholar   +1 more source

High‐Speed Design of Multiplexed Meta‐Optics Enabled by Physics‐Driven Self‐Supervised Network

open access: yesAdvanced Science, EarlyView.
A physics‐driven self‐supervised network (PDSS‐Net) is proposed for high‐speed, iteration‐free design of multiplexed meta‐optics. By learning a direct mapping from holographic targets to all meta‐atom structures, PDSS‐Net achieves a 1000× speedup over traditional optimization methods in designing 2K RGB meta‐holograms.
Yuqing He   +7 more
wiley   +1 more source

Polarization‐Sensitive Holotomography for Multidimensional Label‐Free Imaging and Characterization of Lipid Droplets in Cancer Cells

open access: yesAdvanced Science, EarlyView.
Polarization‐sensitive holotomography (PS‐HT) enables label‐free 3D imaging and quantitative analysis of lipid droplets by exploiting their intrinsic birefringence. Applied to prostate cell models, PS‐HT reveals glucose‐induced lipid accumulation in cancer cells and achieves near‐perfect classification of healthy and cancerous states.
Hossein Khadem   +4 more
wiley   +1 more source

A Generative Framework for Predicting Antiferromagnets

open access: yesAdvanced Science, EarlyView.
This work establishes a design paradigm for antiferromagnets (AFM), accelerating next‐generation spintronic material discovery. By integrating a crystal diffusion variational autoencoder with data augmentation, crystal graph convolutional neural networks, and a genetic algorithm, latent vectors are updated toward AFM property spaces, expanding ...
Jianhu Gong   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy