A weakly supervised conditional diffusion model, guided by fluid-randomized synthetic lesions, improves anomaly detection and pseudo-healthy reconstruction in 3D brain MRI over VAE, LDM, UNA, and supervised inpainting baselines.
arXiv (2018) 2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization
A weakly supervised conditional diffusion model, guided by fluid-randomized synthetic lesions, improves anomaly detection and pseudo-healthy reconstruction in 3D brain MRI over VAE, LDM, UNA, and supervised inpainting baselines.