SPULTRA: Low-Dose CT Image Reconstruction with Joint Statistical and Learned Image Models

TL;DR

This paper introduces SPULTRA, a novel low-dose CT reconstruction method combining a shifted-Poisson statistical model with learned image transforms, resulting in improved image quality over traditional methods.

Contribution

It proposes a new framework using a shifted-Poisson likelihood and a data-driven regularizer with learned transforms, enhancing low-dose CT image reconstruction.

Findings

Better reconstruction quality than PWLS-ULTRA in low-dose scans

Uses nonconvex data-fidelity and regularizer with efficient quadratic surrogate optimization

Maintains similar computational cost per iteration as existing methods

Abstract

Low-dose CT image reconstruction has been a popular research topic in recent years. A typical reconstruction method based on post-log measurements is called penalized weighted-least squares (PWLS). Due to the underlying limitations of the post-log statistical model, the PWLS reconstruction quality is often degraded in low-dose scans. This paper investigates a shifted-Poisson (SP) model based likelihood function that uses the pre-log raw measurements that better represents the measurement statistics, together with a data-driven regularizer exploiting a Union of Learned TRAnsforms (SPULTRA). Both the SP induced data-fidelity term and the regularizer in the proposed framework are nonconvex. The proposed SPULTRA algorithm uses quadratic surrogate functions for the SP induced data-fidelity term. Each iteration involves a quadratic subproblem for updating the image, and a sparse coding and clustering subproblem that has a closed-form solution. The SPULTRA algorithm has a similar computational cost per iteration as its recent counterpart PWLS-ULTRA that uses post-log measurements, and it provides better image reconstruction quality than PWLS-ULTRA, especially in low-dose scans.