NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography

TL;DR

This paper introduces NERD, a novel 3D CT reconstruction method using diffusion sampling with L1 regularization, effectively reducing artifacts and improving volumetric image quality.

Contribution

It extends diffusion model-based inverse imaging to 3D CT by incorporating L1 regularization and develops two optimization strategies for efficient reconstruction.

Findings

Achieves state-of-the-art results on 3D CT data.

Reduces inter-slice artifacts in volumetric reconstructions.

Demonstrates high competitiveness compared to existing methods.

Abstract

Numerous diffusion model (DM)-based methods have been proposed for solving inverse imaging problems. Among these, a recent line of work has demonstrated strong performance by formulating sampling as an optimization procedure that enforces measurement consistency, forward diffusion consistency, and both step-wise and backward diffusion consistency. However, these methods have only considered 2D reconstruction tasks and do not directly extend to 3D image reconstruction problems, such as in Computed Tomography (CT). To bridge this gap, we propose NEtwork-Regularized diffusion sampling for 3D CT (NERD) by incorporating an L1 regularization into the optimization objective. This regularizer encourages spatial continuity across adjacent slices, reducing inter-slice artifacts and promoting coherent volumetric reconstructions. Additionally, we introduce two efficient optimization strategies to solve the resulting objective: one based on the Alternating Direction Method of Multipliers (ADMM) and another based on the Primal-Dual Hybrid Gradient (PDHG) method. Experiments on medical 3D CT data demonstrate that our approach achieves either state-of-the-art or highly competitive results.