QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction

Sparse-view CT FBP (c) Unrolled quasi-Newton (b) Unrolled first-order (a) Post-processing Gound Truth DuDoTrans FBPConvNet RegFormer LEARN Data-Hungry Speed Data-Hungry Speed QN-Mixer (ours) Sparse-view scan Artifacts Artifacts Artifacts Speed 32 views v ie w 1 v ie w 2 d e te c to rs X-ray source Object Artifacts Data-Hungry Bad in Good in Figure 1. CT Reconstruction with 32 views of State-of-the-Art Methods. Comparative analysis with post-processing and first-order unrolling networks highlights QN-Mixer's superiority in artifact removal, training time, and data efficiency.