.png){kind=icon}
.png){kind=icon}
Return
FlowLet: Conditional 3D brain MRI synthesis using wavelet flow matching
.png){kind=icon}
OA
AI
DOI：10.1016/j.media.2026.104161.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Wavelet-based flow matching model synthesizes 3D brain MRI. • Age conditioning controls localized morphology changes in synthetic volumes. • Deterministic sampling allows generation in 10 steps without additional latent compression. • Region-and task-based tests show gains in brain age prediction accuracy. • Methodology, code, and evaluation protocols are released free and open-source for reproducibility.
Keywords:
Flow matching
MRI
3D brain synthesis
Generative models
Age-conditioned generation
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.