SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network

• Published in: IEEE transactions on medical imaging 2020-07, Vol.39 (7), p.2289-2301
• Main Authors: Li, Meng, Hsu, William, Xie, Xiaodong, Cong, Jason, Gao, Wen
• Format: Article
• Language: English
• Subjects: Artificial neural networks; autoencoder; Computed tomography; Convolutional neural networks; denoising; Diagnostic software; Diagnostic systems; Feature extraction; Image quality; Image reconstruction; Image resolution; Information retrieval; Low-dose CT; Machine learning; Medical imaging; Modules; Multilayers; Neural networks; Noise reduction; perceptual loss; Radiation; Radiation effects; Receptive field; self-attention; Spatial data; Three-dimensional displays
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2020.2968472

Computed tomography (CT) is a widely used screening and diagnostic tool that allows clinicians to obtain a high-resolution, volumetric image of internal structures in a non-invasive manner. Increasingly, efforts have been made to improve the image quality of low-dose CT (LDCT) to reduce the cumulative radiation exposure of patients undergoing routine screening exams. The resurgence of deep learning has yielded a new approach for noise reduction by training a deep multi-layer convolutional neural networks (CNN) to map the low-dose to normal-dose CT images. However, CNN-based methods heavily rely on convolutional kernels, which use fixed-size filters to process one local neighborhood within the receptive field at a time. As a result, they are not efficient at retrieving structural information across large regions. In this paper, we propose a novel 3D self-attention convolutional neural network for the LDCT denoising problem. Our 3D self-attention module leverages the 3D volume of CT images to capture a wide range of spatial information both within CT slices and between CT slices. With the help of the 3D self-attention module, CNNs are able to leverage pixels with stronger relationships regardless of their distance and achieve better denoising results. In addition, we propose a self-supervised learning scheme to train a domain-specific autoencoder as the perceptual loss function. We combine these two methods and demonstrate their effectiveness on both CNN-based neural networks and WGAN-based neural networks with comprehensive experiments. Tested on the AAPM-Mayo Clinic Low Dose CT Grand Challenge data set, our experiments demonstrate that self-attention (SA) module and autoencoder (AE) perceptual loss function can efficiently enhance traditional CNNs and can achieve comparable or better results than the state-of-the-art methods.