Deep Inertia $L_p$ Half-Quadratic Splitting Unrolling Network for Sparse View CT Reconstruction

Abstract

Sparse view computed tomography (CT) reconstruction poses a challenging ill-posed inverse problem, necessitating effective regularization techniques. In this letter, we employ $L_p$-norm ($0<p<1$) regularization to induce sparsity and introduce inertial steps, leading to the development of the inertial $L_p$-norm half-quadratic splitting algorithm. We rigorously prove the convergence of this algorithm. Furthermore, we leverage deep learning to initialize the conjugate gradient method, resulting in a deep unrolling network with theoretical guarantees. Our extensive numerical experiments demonstrate that our proposed algorithm surpasses existing methods, particularly excelling in fewer scanned views and complex noise conditions.

This paper was accepted by IEEE Signal Processing Letters on July 28, 2024

References in corpus (6)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Learned Primal-dual Reconstruction
• Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
• Visual Attention Network for Low Dose CT
• Fast, nonlocal and neural: a lightweight high quality solution to image denoising
• An efficient Quasi-Newton method for nonlinear inverse problems via learned singular values