.png){kind=icon}
.png){kind=icon}
Return
Asymmetric decoupled dual-domain learning for CT metal artifact reduction: Integrating Fast Fourier Convolution and vision transformers
.png){kind=icon}
PRE
AI
M
J
DOI：10.1016/j.compmedimag.2026.102801.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose an asymmetric decoupled dual-domain framework for MAR. • We integrate Fast Fourier Convolution and Transformers for cross-domain topology. • We design a Residual-Prior Guided Fusion strategy for high-fidelity refinement. • Experiments show SOTA performance (46.49 dB) and clinical generalization.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
No organization information available
Cited Papers