Results 101 to 110 of about 60,075 (226)

Diffusion model‐regularized implicit neural representation for computed tomography metal artifact reduction

Quantitative Biology, Volume 14, Issue 2, June 2026.
Abstract Computed tomography (CT) images are often severely corrupted by artifacts in the presence of metals. Existing supervised metal artifact reduction (MAR) approaches suffer from performance instability on known data due to their reliance on limited paired metal‐clean data, which limits their clinical applicability. Moreover, existing unsupervised
Jie Wen, Chenhe Du, Xiao Wang, Yuyao Zhang   +3 more
wiley   +1 more source

Diffusional magnetic resonance imaging anonymizing with variational autoencoder

Quantitative Biology, Volume 14, Issue 2, June 2026.
Abstract Anonymization is a crucial de‐identification technique that protects data privacy while ensuring its utility for model building. Current generative models such as generative adversarial networks and variational auto‐encoders (VAEs) have been applied to medical image anonymization but mainly focus on general image features, lacking specificity ...
Yunheng Shen, Ling Zheng, Ruohan Liu, Haoran Feng, Hairong Lv   +4 more
wiley   +1 more source

High‐Resolution Diffusion‐Weighted Imaging With Self‐Gated Self‐Supervised Unrolled Reconstruction

Magnetic Resonance in Medicine, Volume 95, Issue 5, Page 2852-2862, May 2026.
ABSTRACT Purpose High‐resolution diffusion‐weighted imaging (DWI) is clinically demanding. The purpose of this work is to develop an efficient self‐supervised algorithm unrolling technique for submillimeter‐resolution DWI. Methods We developed submillimeter DWI acquisition utilizing multi‐band multi‐shot EPI with diffusion shift encoding.
Zhengguo Tan, Patrick A. Liebig, Annika Hofmann, Frederik B. Laun, Florian Knoll   +4 more
wiley   +1 more source

T2$$ {\boldsymbol{T}}_{\mathbf{2}} $$‐Weighted Imaging of Water, Fat and Silicone

Magnetic Resonance in Medicine, Volume 95, Issue 5, Page 2765-2775, May 2026.
ABSTRACT Purpose Magnetic resonance imaging (MRI) is a sensitive method for assessing silicone implant integrity, with T2$$ {T}_2 $$‐weighted imaging being essential for detecting abnormalities in surrounding tissue. Silicone breast imaging protocols often require multiple tailored sequences for species suppression and diagnostic contrast. We propose a
Aizada Nurdinova, Xuetong Zhou, Julio A. Oscanoa, Preya Shah, Kawin Setsompop, Bruce L. Daniel, Brian A. Hargreaves   +6 more
wiley   +1 more source

Deep Learning Reconstruction Enables Diagnostic‐Quality 0.4T Knee and Spine MRI in One‐Third of the Time

NMR in Biomedicine, Volume 39, Issue 5, May 2026.
The deep learning model CIRIM successfully accelerated knee and spine data up to an acceleration factor of 3, after optimizing the undersampling mask and loss function. The model demonstrated robustness and generalizability to different contrasts, matrix sizes, orientations, and anatomies. ABSTRACT There has been a growing interest in low‐field MRI due
Daisy M. van den Berg, Rosario Varriale, Fabrizio Ferrando, Paolo Traverso, Luca Balbi, Giacomo Belgiorno, Kerensa Beekman, Laura Kox, Gustav J. Strijkers, Matthan W. A. Caan   +9 more
wiley   +1 more source

Deep Learning Empowered Microstructure Codebook: New Paradigm for Multi‐Parameter Tissue Characterization Estimation

Human Brain Mapping, Volume 47, Issue 5, 1 April 2026.
We propose DEMIC, a deep‐learning microstructure codebook framework for dMRI microstructure imaging: (1) accurate multi‐parameter estimation from undersampled data; (2) robust cross‐protocol and cross‐model generalization; and (3) flexible transfer to new microstructural indices via fine‐tuning.
Tenglong Wang, Zhonghua Wan, Shuxin Cao, Jiahao Yu, Yifei He, Yu Xie, Fan Zhang, Ye Wu   +7 more
wiley   +1 more source

Image Denoising Using Multi-ModelFusion Technique

International Journal of Computing and Related Technologies
Image denoising is a fundamental challenge in the field of image processing, with the primary goal of recovering high-quality images from noisy counterparts.
Kamal Khan, Muhammad Anwar, Saifullah
doaj  

Efficient Kilometer‐Scale Precipitation Downscaling With Conditional Wavelet Diffusion

Journal of Geophysical Research: Machine Learning and Computation, Volume 3, Issue 2, April 2026.
Abstract Precipitation products such as Integrated Multi‐satellitE Retrievals have coarse resolution (∼10 ${\sim} 10$ km), which limits their application in hydrological modeling and extreme weather analysis. We propose the Wavelet Diffusion Model (WDM), a fast generative framework for high‐quality precipitation downscaling trained on multi‐radar multi‐
Chugang Yi, Minghan Yu, Weikang Qian, Yixin Wen, Haizhao Yang   +4 more
wiley   +1 more source

Recomposable Layered Metasurfaces for Wavelength‐Multiplexed Optical Encryption via Modular Diffractive Deep Neural Networks

Advanced Functional Materials, Volume 36, Issue 24, 23 March 2026.
Modular diffractive deep neural network metasurfaces encode and reconstruct holograms across layer combinations and wavelengths, enabling secure, multifunctional operation. Each layer acts independently yet composes jointly, yielding up to m(2N −1) channels for m wavelengths and N layers.
Cherry Park, Youngsun Jeon, Seokho Lee, Yeseul Kim, Junsuk Rho   +4 more
wiley   +1 more source

GLCM and PSNR Analysis of Woven Fabric Images Made from Natural Dyes Due to Sunlight Exposure

JOIV: International Journal on Informatics Visualization
Traditional woven fabrics generally use natural dyes that come from the local area. Natural dyes are often considered low quality if exposed to sunlight.
Patrisius Batarius, Albertus Joko Santoso, Alfry Aristo Jansen Sinlae   +2 more
doaj   +1 more source