No-reference denoising of low-dose CT projections

TL;DR

This paper introduces a self-supervised deep learning method for denoising low-dose CT projections that only requires noisy data and leverages adjacent image relationships, achieving near-supervised accuracy.

Contribution

The proposed method is the first to perform CT denoising using only noisy projections without needing paired high-dose images, improving practicality and performance.

Findings

Achieves near-supervised denoising accuracy.

Outperforms existing self-supervised methods.

Requires only noisy projections, not paired data.

Abstract

Low-dose computed tomography (LDCT) became a clear trend in radiology with an aspiration to refrain from delivering excessive X-ray radiation to the patients. The reduction of the radiation dose decreases the risks to the patients but raises the noise level, affecting the quality of the images and their ultimate diagnostic value. One mitigation option is to consider pairs of low-dose and high-dose CT projections to train a denoising model using deep learning algorithms; however, such pairs are rarely available in practice. In this paper, we present a new self-supervised method for CT denoising. Unlike existing self-supervised approaches, the proposed method requires only noisy CT projections and exploits the connections between adjacent images. The experiments carried out on an LDCT dataset demonstrate that our method is almost as accurate as the supervised approach, while also outperforming the considered self-supervised denoising methods.