Low-Dose Ct Denoising Via Neural Architecture Search

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from the low-dose CT (LDCT) usually 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 suggests 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 memory-efficient NAS for LDCT denoising, termed M3NAS. The proposed M3NAS fuses features extracted by different scale cells to capture multi-scale image structural details. Also, M3NAS can search a hybrid cell- and network-level structure for better performance. In addition, M3NAS can effectively reduce the amount of model parameters and increase the speed of inference. Extensively experimental results on two different benchmark datasets demonstrate that the proposed M3NAS can achieve better performance and have fewer parameters than several state-of-the-art models.