Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases

arXiv:2403.16776v1 Announce Type: cross
Abstract: Anatomical atlases are widely used for population analysis. Conditional atlases target a particular sub-population defined via certain conditions (e.g. demographics or pathologies) and allow for the investigation of fine-grained anatomical differences - such as morphological changes correlated with age. Existing approaches use either registration-based methods that are unable to handle large anatomical variations or generative models, which can suffer from training instabilities and hallucinations. To overcome these limitations, we use latent diffusion models to generate …

abstract age analysis arxiv cs.cv cs.lg demographics diff differences diffusion eess.iv fields fine-grained generated investigation population registration type via