MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising

TL;DR

This paper introduces MANAS, a neural architecture search method tailored for low-dose CT denoising, which effectively captures multi-scale details and optimizes network structure for improved image quality.

Contribution

First application of NAS to LDCT denoising, proposing a multi-scale and multi-level search framework that outperforms existing methods.

Findings

MANAS achieves superior denoising performance across multiple dose levels.

The multi-scale feature fusion improves structural detail preservation.

Hybrid cell- and network-level search enhances model effectiveness.

Abstract

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from the dose-reduced CT or low-dose CT (LDCT) suffer from severe noise, compromising the subsequent diagnosis and analysis. Recently, convolutional neural networks have achieved promising results in removing noise from LDCT images; the network architectures used are either handcrafted or built on top of conventional networks such as ResNet and U-Net. Recent advance on neural network architecture search (NAS) has proved that the network architecture has a dramatic effect on the model performance, which indicates that current network architectures for LDCT may be sub-optimal. Therefore, in this paper, we make the first attempt to apply NAS to LDCT and propose a multi-scale and multi-level NAS for LDCT denoising, termed MANAS. On the one hand, the proposed MANAS fuses features extracted by different scale cells to capture multi-scale image structural details. On the other hand, the proposed MANAS can search a hybrid cell- and network-level structure for better performance. Extensively experimental results on three different dose levels demonstrate that the proposed MANAS can achieve better performance in terms of preserving image structural details than several state-of-the-art methods. In addition, we also validate the effectiveness of the multi-scale and multi-level architecture for LDCT denoising.