Results 181 to 190 of about 13,553 (263)
Compact Snapshot Hyperspectral Imaging With Neural Dispersion‐Engineered Metalens
A dispersion‐engineered metalens, designed via an end‐to‐end deep learning framework, encodes spectral information through wavelength‐dependent PSF shifts. Fabricated by two‐photon grayscale lithography, the ultrathin device demonstrates outstanding spatial‐spectral reconstruction in both indoor and outdoor scenes, positioning it as a promising ...
Peng Liu, Jiaru Chu, Yuhang Chen
wiley +1 more source
Performance of a GPU- and time-efficient pseudo-3D network for magnetic resonance image super-resolution and motion artifact reduction. [PDF]
Li H +10 more
europepmc +1 more source
Scanner‐agnostic artificial intelligence approach for fast bone scintigraphy
Abstract Purpose Current bone scintigraphy protocols often demand full‐count, 10–15 min scans to preserve image quality, and existing deep‐learning (DL) denoisers typically need to be retrained or retuned for each camera manufacturer. We introduce a scanner‐agnostic adaptive‐diffusion U‐Net designed to reconstruct diagnostic‐grade images from half‐time
Vinicius de Oliveira Menezes +9 more
wiley +1 more source
Lightweight Low-Light Enhancement Network with Multi-Bio-Inspired Visual Mechanisms. [PDF]
Zhao Y, Li X, Hao S, Yu M, Gao Y, Fan S.
europepmc +1 more source
Abstract Background Cone‐beam computed tomography (CBCT) is widely used in image‐guided radiotherapy because it reflects the patient's anatomy immediately before treatment. However, CBCT images of the abdominal organs, including the pancreas, are often degraded by respiratory motion.
Airi Nukushina +10 more
wiley +1 more source
CT-to-PET Synthesis in the Head-Neck and Thoracic Region via Conditional 3D Latent Diffusion Modeling. [PDF]
Mahdi MA +5 more
europepmc +1 more source
To overcome two‐dimensional modulation bottlenecks, Hadamard Matrix Slicing Single‐Pixel Imaging (HMS‐SPI) establishes an efficient one‐dimensional imaging paradigm. By slicing the traditional Hadamard matrix into one‐dimensional encoding vectors and spatially expanding them, the required measurement patterns decrease by a factor of N.
Xiaoxue Li +8 more
wiley +1 more source
HACR-Net: An Efficient hybrid attention network for MRI image super-resolution. [PDF]
Muhammad A +3 more
europepmc +1 more source
MarginPath is a novel vision‐language system that automates breast cancer margin assessment using a single label‐free multiphoton microscopy image. By integrating tumor‐associated collagen signatures with virtual H&E imaging, it generates accurate margin heatmaps and comprehensive diagnostic reports.
Shu Wang +15 more
wiley +1 more source

