One Sample Diffusion Model in Projection Domain for Low-Dose CT Imaging

TL;DR

This paper introduces an unsupervised one sample diffusion model in the projection domain for low-dose CT reconstruction, effectively reducing artifacts and maintaining image quality with a single sinogram sample.

Contribution

It proposes a novel unsupervised diffusion model that leverages Hankel matrix formulation and score-based generative modeling for low-dose CT imaging from a single sample.

Findings

Reconstructed images closely resemble normal-dose CT images.

The method effectively reduces artifacts and preserves image quality.

Approaches the quality of standard-dose CT images.

Abstract

Low-dose computed tomography (CT) plays a significant role in reducing the radiation risk in clinical applications. However, lowering the radiation dose will significantly degrade the image quality. With the rapid development and wide application of deep learning, it has brought new directions for the development of low-dose CT imaging algorithms. Therefore, we propose a fully unsupervised one sample diffusion model (OSDM)in projection domain for low-dose CT reconstruction. To extract sufficient prior information from single sample, the Hankel matrix formulation is employed. Besides, the penalized weighted least-squares and total variation are introduced to achieve superior image quality. Specifically, we first train a score-based generative model on one sinogram by extracting a great number of tensors from the structural-Hankel matrix as the network input to capture prior distribution. Then, at the inference stage, the stochastic differential equation solver and data consistency step are performed iteratively to obtain the sinogram data. Finally, the final image is obtained through the filtered back-projection algorithm. The reconstructed results are approaching to the normal-dose counterparts. The results prove that OSDM is practical and effective model for reducing the artifacts and preserving the image quality.