.png){kind=icon}
.png){kind=icon}
Return
Dual-domain latent alignment for MRI-to-CT synthesis via target-aware manifold learning
.png){kind=icon}
PRE
AI
W
Y
S
Y
Y
S
DOI：10.1016/j.compmedimag.2026.102804.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A dual-domain latent alignment framework jointly leverages paired and unpaired CT data. • Geometric Reference Selection identifies anatomically compatible CT anchors for stable latent alignment. • A Latent Space Modulator improves CT-specific feature adaptation while preserving anatomy. • Extensive experiments provide promising evidence of competitive performance across multiple evaluation metrics.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
Cited Papers