Diffusion Low Rank Hybrid Reconstruction for Sparse View Medical Imaging
This addresses the challenge of high-fidelity medical imaging under extreme sparse sampling, offering potential clinical benefits in low-dose scenarios, though it appears incremental as it builds on existing diffusion and regularization techniques.
The paper tackles the problem of low-dose sparse-view CT reconstruction by proposing TV-LoRA, a method combining diffusion generative priors with multi-regularization constraints, achieving superior performance in SSIM, texture recovery, and artifact suppression across datasets with as few as 2 views.
This work presents TV-LoRA, a novel method for low-dose sparse-view CT reconstruction that combines a diffusion generative prior (NCSN++ with SDE modeling) and multi-regularization constraints, including anisotropic TV and nuclear norm (LoRA), within an ADMM framework. To address ill-posedness and texture loss under extremely sparse views, TV-LoRA integrates generative and physical constraints, and utilizes a 2D slice-based strategy with FFT acceleration and tensor-parallel optimization for efficient inference. Experiments on AAPM-2016, CTHD, and LIDC datasets with $N_{\mathrm{view}}=8,4,2$ show that TV-LoRA consistently surpasses benchmarks in SSIM, texture recovery, edge clarity, and artifact suppression, demonstrating strong robustness and generalizability. Ablation studies confirm the complementary effects of LoRA regularization and diffusion priors, while the FFT-PCG module provides a speedup. Overall, Diffusion + TV-LoRA achieves high-fidelity, efficient 3D CT reconstruction and broad clinical applicability in low-dose, sparse-sampling scenarios.