Strategies for CT Reconstruction using Diffusion Posterior Sampling with a Nonlinear Model

TL;DR

This paper introduces enhanced strategies for diffusion posterior sampling in CT reconstruction, significantly improving stability, speed, and accuracy, especially in low-dose and sparse-view scenarios, making the method more practical.

Contribution

The work proposes specific modifications to DPS, including jumpstart sampling and likelihood update improvements, to boost efficiency and robustness in nonlinear CT reconstruction.

Findings

Achieved up to 46.72% PSNR and 51.50% SSIM improvements in simulations.

Reduced reconstruction time from over 23.5 seconds to under 1.5 seconds per slice.

Demonstrated robustness on physical phantom data across various dose levels.

Abstract

Diffusion Posterior Sampling(DPS) methodology is a novel framework that permits nonlinear CT reconstruction by integrating a diffusion prior and an analytic physical system model, allowing for one-time training for different applications. However, baseline DPS can struggle with large variability, hallucinations, and slow reconstruction. This work introduces a number of strategies designed to enhance the stability and efficiency of DPS CT reconstruction. Specifically, jumpstart sampling allows one to skip many reverse time steps, significantly reducing the reconstruction time as well as the sampling variability. Additionally, the likelihood update is modified to simplify the Jacobian computation and improve data consistency more efficiently. Finally, a hyperparameter sweep is conducted to investigate the effects of parameter tuning and to optimize the overall reconstruction performance. Simulation studies demonstrated that the proposed DPS technique achieves up to 46.72% PSNR and 51.50% SSIM enhancement in a low-mAs setting, and an over 31.43% variability reduction in a sparse-view setting. Moreover, reconstruction time is sped up from >23.5 s/slice to <1.5 s/slice. In a physical data study, the proposed DPS exhibits robustness on an anthropomorphic phantom reconstruction which does not strictly follow the prior distribution. Quantitative analysis demonstrates that the proposed DPS can accommodate various dose levels and number of views. With 10% dose, only a 5.60% and 4.84% reduction of PSNR and SSIM was observed for the proposed approach. Both simulation and phantom studies demonstrate that the proposed method can significantly improve reconstruction accuracy and reduce computational costs, greatly enhancing the practicality of DPS CT reconstruction.