QS-ADN: Quasi-Supervised Artifact Disentanglement Network for Low-Dose CT Image Denoising by Local Similarity Among Unpaired Data

TL;DR

This paper proposes QS-ADN, a quasi-supervised artifact disentanglement network that leverages hidden similarities among unpaired low-dose and normal-dose CT images to improve denoising performance without requiring paired training data.

Contribution

It introduces a novel quasi-supervised learning mode for artifact disentanglement networks, utilizing matched unpaired images to enhance low-dose CT denoising.

Findings

Competitive noise suppression compared to state-of-the-art methods

Effective utilization of unpaired data through matching and prior information

Easy to implement by modifying existing networks

Abstract

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is expensive to obtain and cannot be perfectly simulated. Unsupervised learning utilizes unpaired data and is highly desirable for LDCT denoising. As an example, an artifact disentanglement network (ADN) relies on unparied images and obviates the need for supervision but the results of artifact reduction are not as good as those through supervised learning.An important observation is that there is often hidden similarity among unpaired data that can be utilized. This paper introduces a new learning mode, called quasi-supervised learning, to empower the ADN for LDCT image denoising.For every LDCT image, the best matched image is first found from an unpaired normal-dose CT (NDCT) dataset. Then, the matched pairs and the corresponding matching degree as prior information are used to construct and train our ADN-type network for LDCT denoising.The proposed method is different from (but compatible with) supervised and semi-supervised learning modes and can be easily implemented by modifying existing networks. The experimental results show that the method is competitive with state-of-the-art methods in terms of noise suppression and contextual fidelity. The code and working dataset are publicly available at https://github.com/ruanyuhui/ADN-QSDL.git.