%0 Conference Paper
%A Gicquel, Malo
%A Flood, Gabrielle
%A Zhao, Ruoyi
%A Wuestefeld, Anika
%A Spotorno, Nicola
%A Strandberg, Olof
%A Xiao, Yu
%A Åström, Kalle
%A Wisse, Laura E M
%A van Westen, Danielle
%A Berron, David
%A Hansson, Oskar
%A Vogel, Jacob W
%T AI Superresolution: Converting T1‐weighted MRI from 3T to 7T resolution toward enhanced imaging biomarkers for Alzheimer’s disease
%J Alzheimer's and dementia
%V 21
%N Suppl 8
%@ 1552-5260
%M DZNE-2025-01506
%P e109817
%D 2025
%X High-resolution (7T) MRI facilitates in vivo imaging of fine anatomical structures selectively affected in Alzheimer's disease (AD), including medial temporal lobe subregions. However, 7T data is challenging to acquire and largely unavailable in clinical settings. Here, we use deep learning to synthesize 7T resolution T1-weighted MRI images from lower-resolution (3T) images.Paired 7T and 3T T1-weighted images were acquired from 178 participants (134 clinically unimpaired, 48 impaired) from the Swedish BioFINDER-2 study. To synthesize 7T-resolution images from 3T images, we trained two models: a specialized U-Net, and a U-Net mixed with a generative adversarial network (U-Net-GAN) on 80
%B Alzheimer’s Association International Conference
%C 27 Jul 2025 - 31 Jul 2025, Toronto (Canada)
Y2 27 Jul 2025 - 31 Jul 2025
M2 Toronto, Canada
%K Humans
%K Alzheimer Disease: diagnostic imaging
%K Magnetic Resonance Imaging: methods
%K Female
%K Male
%K Aged
%K Deep Learning
%K Neuroimaging: methods
%K Image Processing, Computer-Assisted: methods
%K Brain: diagnostic imaging
%K Sweden
%F PUB:(DE-HGF)1 ; PUB:(DE-HGF)16
%9 AbstractJournal Article
%$ pmid:41434097
%2 pmc:PMC12725268
%R 10.1002/alz70862_109817
%U https://pub.dzne.de/record/283099