Problem
Research questions and friction points this paper is trying to address.
Sparse-view CT reconstruction
Ill-posed inverse problem
Streak artifacts
Deep unrolling
CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction
🤖 AI Summary
This study addresses the ill-posed inverse problem in sparse-view CT reconstruction and the poor convergence of existing deep learning methods by proposing a compact deep unfolding framework inspired by second-order optimization. By constructing a structured Hessian proxy with a conjugate gradient solver and designing a global-local regularization module that integrates convolutional features with Nyström attention, the method effectively models image priors. Experiments on AAPM and DeepLesion datasets demonstrate stable convergence, significant noise power reduction, and enhanced visual fidelity. Achieving superior quantitative metrics compared to state-of-the-art approaches, this work provides an efficient and reliable solution for sparse-view CT reconstruction.
📝 Abstract
Sparse-view computed tomography (CT) reduces radiation dose by acquiring fewer projection views, but the resulting inverse problem is highly ill-posed and often produces severe streak artifacts. Existing deep reconstruction methods have achieved promising performance, yet many rely on first-order updates or large regularization networks, which can be less effective in ill-conditioned settings. We propose \textbf{CG-GLORE}, a compact deep unrolling framework inspired by second-order optimization for sparse-view CT reconstruction. Each unrolled stage uses a CG-solved linear system based on a structured Hessian surrogate: it retains the physics-induced curvature of the data-fidelity term while using an identity approximation for the learned regularization term. Thus, the method is second-order-inspired rather than an exact Newton method for the full learned objective. To model image priors, we design a Global-Local Regularization Network (GLORE), which combines convolutional local feature extraction with a Long-Range Dependency Representation module based on sparse patchification and Nyström attention. This design captures anatomical details and non-local dependencies while maintaining practical complexity. Experiments on AAPM and DeepLesion under multiple sparse-view and noise settings show that CG-GLORE achieves strong quantitative performance, stable convergence, lower noise power, and improved visual fidelity compared with representative reconstruction methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Conjugate Gradient Unrolling
Structured Hessian Surrogate
Global-Local Regularization
Nyström Attention
Sparse-View CT Reconstruction
🔎 Similar Papers
No similar papers found.
