CAFDIM: a group convolution and self-attention fusion-based dual-domain iterative method for sparse-view CT reconstruction
Experiments demonstrate that CAFDIM effectively suppresses sparse-view artifacts, preserves anatomical structures, and achieves superior reconstruction accuracy, visual quality, and generalization ability compared with state-of-the-art methods.
Ji-Zhong Duan, Cheng-Hong Sun, Hai-Bo Tao et al.
· Physics in Medicine and Biol... · 0 citations