A Cascaded Convolutional Neural Network for X-ray Low-dose CT Image Denoising

TL;DR

This paper introduces a cascaded CNN approach for low-dose CT image denoising, iteratively reducing noise and artifacts to improve image quality for better diagnosis, validated on a large dataset.

Contribution

The paper proposes a novel cascaded CNN training framework that iteratively refines denoising performance and reduces artifacts in low-dose CT images.

Findings

Improved denoising performance on the 2016 Low-dose CT Grand Challenge dataset.

Effective reduction of residual artifacts in denoised images.

Demonstrated the potential of cascaded CNNs for clinical CT image enhancement.

Abstract

Image denoising techniques are essential to reducing noise levels and enhancing diagnosis reliability in low-dose computed tomography (CT). Machine learning based denoising methods have shown great potential in removing the complex and spatial-variant noises in CT images. However, some residue artifacts would appear in the denoised image due to complexity of noises. A cascaded training network was proposed in this work, where the trained CNN was applied on the training dataset to initiate new trainings and remove artifacts induced by denoising. A cascades of convolutional neural networks (CNN) were built iteratively to achieve better performance with simple CNN structures. Experiments were carried out on 2016 Low-dose CT Grand Challenge datasets to evaluate the method's performance.