000283099 001__ 283099
000283099 005__ 20251230135929.0
000283099 0247_ $$2doi$$a10.1002/alz70862_109817
000283099 0247_ $$2pmid$$apmid:41434097
000283099 0247_ $$2pmc$$apmc:PMC12725268
000283099 0247_ $$2ISSN$$a1552-5260
000283099 0247_ $$2ISSN$$a1552-5279
000283099 037__ $$aDZNE-2025-01506
000283099 041__ $$aEnglish
000283099 082__ $$a610
000283099 1001_ $$aGicquel, Malo$$b0
000283099 1112_ $$aAlzheimer’s Association International Conference$$cToronto$$d2025-07-27 - 2025-07-31$$gAAIC 25$$wCanada
000283099 245__ $$aAI Superresolution: Converting T1‐weighted MRI from 3T to 7T resolution toward enhanced imaging biomarkers for Alzheimer’s disease
000283099 260__ $$c2025
000283099 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1767099306_6287
000283099 3367_ $$033$$2EndNote$$aConference Paper
000283099 3367_ $$2BibTeX$$aINPROCEEDINGS
000283099 3367_ $$2DRIVER$$aconferenceObject
000283099 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$mjournal
000283099 3367_ $$2DataCite$$aOutput Types/Conference Abstract
000283099 3367_ $$2ORCID$$aOTHER
000283099 520__ $$aHigh-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% of the data. We evaluated model performance on the remaining 20%, compared to models from the literature (V-Net, WATNet), using image-based performance metrics and by surveying five blinded MRI professionals based on subjective quality. For n = 11 participants, amygdalae were automatically segmented with FastSurfer on 3T and synthetic-7T images, and compared to a manually segmented 'ground truth'. To assess downstream performance, FastSurfer was run on n = 3,168 triplets of matched 3T and AI-generated synthetic-7T images, and a multi-class random forest model classifying clinical diagnosis was trained on both datasets.Synthetic-7T images were generated for images in the test set (Figure 1A). Image metrics suggested the U-Net as the top performing model (Figure 1B), though blinded experts qualitatively rated the GAN-U-Net as the best looking images, exceeding even real 7T images (Figure 1C). Automated segmentations of amygdalae from the synthetic GAN-U-Net model were more similar to manually segmented amygdalae, compared to the original 3T they were synthesized from, in 9/11 images (Figure 2). Classification obtained modest performance (accuracy∼60%) but did not differ across real or synthetic images (Figure 3A). Synthetic image models used slightly different features for classification (Figure 3B).Synthetic T1-weighted images approaching 7T resolution can be generated from 3T images, which may improve image quality and segmentation, without compromising performance in downstream tasks. This approach holds promise for better measurement of deep cortical or subcortical structures relevant to AD. Work is ongoing toward improving performance, generalizability and clinical utility.
000283099 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000283099 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000283099 650_2 $$2MeSH$$aHumans
000283099 650_2 $$2MeSH$$aAlzheimer Disease: diagnostic imaging
000283099 650_2 $$2MeSH$$aMagnetic Resonance Imaging: methods
000283099 650_2 $$2MeSH$$aFemale
000283099 650_2 $$2MeSH$$aMale
000283099 650_2 $$2MeSH$$aAged
000283099 650_2 $$2MeSH$$aDeep Learning
000283099 650_2 $$2MeSH$$aNeuroimaging: methods
000283099 650_2 $$2MeSH$$aImage Processing, Computer-Assisted: methods
000283099 650_2 $$2MeSH$$aBrain: diagnostic imaging
000283099 650_2 $$2MeSH$$aSweden
000283099 7001_ $$aFlood, Gabrielle$$b1
000283099 7001_ $$aZhao, Ruoyi$$b2
000283099 7001_ $$aWuestefeld, Anika$$b3
000283099 7001_ $$0P:(DE-2719)2811765$$aSpotorno, Nicola$$b4
000283099 7001_ $$aStrandberg, Olof$$b5
000283099 7001_ $$aXiao, Yu$$b6
000283099 7001_ $$aÅström, Kalle$$b7
000283099 7001_ $$aWisse, Laura E M$$b8
000283099 7001_ $$avan Westen, Danielle$$b9
000283099 7001_ $$0P:(DE-2719)2812972$$aBerron, David$$b10
000283099 7001_ $$aHansson, Oskar$$b11
000283099 7001_ $$aVogel, Jacob W$$b12
000283099 773__ $$0PERI:(DE-600)2201940-6$$a10.1002/alz70862_109817$$gVol. 21 Suppl 8, no. Suppl 8, p. e109817$$nSuppl 8$$pe109817$$tAlzheimer's and dementia$$v21$$x1552-5260$$y2025
000283099 8564_ $$uhttps://pub.dzne.de/record/283099/files/DZNE-2025-1506.pdf$$yOpenAccess
000283099 8564_ $$uhttps://pub.dzne.de/record/283099/files/DZNE-2025-1506.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000283099 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812972$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b10$$kDZNE
000283099 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000283099 9141_ $$y2025
000283099 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bALZHEIMERS DEMENT : 2022$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)3001$$2StatID$$aDEAL Wiley$$d2025-01-06$$wger
000283099 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bALZHEIMERS DEMENT : 2022$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000283099 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2025-01-06
000283099 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-06
000283099 9201_ $$0I:(DE-2719)5000070$$kAG Berron$$lClinical Cognitive Neuroscience$$x0
000283099 980__ $$aabstract
000283099 980__ $$aVDB
000283099 980__ $$aUNRESTRICTED
000283099 980__ $$ajournal
000283099 980__ $$aI:(DE-2719)5000070
000283099 9801_ $$aFullTexts