.png){kind=icon}
.png){kind=icon}
Return
Self-Supervised Isotropic Reconstruction for Abnormality Detection in Anisotropic MRI
.png){kind=icon}
PRE
AI
J
P
T
Y
G
DOI：10.1016/j.compmedimag.2026.102786.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A self-supervised generative adversarial network (GAN)–diffusion pipeline yields isotropic 3D lesion maps from highly anisotropic knee MRI. • Outperformed state-of-the-art self-supervised models in perceptual metrics and blind expert review. • Improved anatomic and lesion delineation, robust across multi-centers and different MR protocols.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
Cited Papers