A 3D U-Net trained on NACC with pseudo-morphological augmentations and supervised contrastive learning achieves higher macro-F1 on unseen ADNI and AIBL scans than several SDG baselines.
Learning with domain-knowledge for generalizable prediction of Alzheimer’s disease from multi-site structural MRI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning
A 3D U-Net trained on NACC with pseudo-morphological augmentations and supervised contrastive learning achieves higher macro-F1 on unseen ADNI and AIBL scans than several SDG baselines.