.png){kind=icon}
.png){kind=icon}
Return
LDM-Morph: Latent diffusion model guided deformable image registration
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2025.112925.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• LDM-Morph improves medical image registration using a latent diffusion model. • A dual-stream encoder is proposed to enhance feature learning for image alignment. • LGCA module is designed to boost feature interaction and improve precision. • Novel hierarchical similarity metric improves accuracy and topology preservation.
Keywords:
Deformable registration
Latent diffusion model
Dual-stream cross learning
Latent feature
Unsupervised learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W