Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising

Abstract

Computed tomography (CT) is a popular medical imaging modality in clinical applications. At the same time, the x-ray radiation dose associated with CT scans raises public concerns due to its potential risks to the patients. Over the past years, major efforts have been dedicated to the development of Low-Dose CT (LDCT) methods. However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality. In this paper, we propose a novel 3D noise reduction method, called Structure-sensitive Multi-scale Generative Adversarial Net (SMGAN), to improve the LDCT image quality. Specifically, we incorporate three-dimensional (3D) volumetric information to improve the image quality. Also, different loss functions for training denoising models are investigated. Experiments show that the proposed method can effectively preserve structural and texture information from normal-dose CT (NDCT) images, and significantly suppress noise and artifacts. Qualitative visual assessments by three experienced radiologists demonstrate that the proposed method retrieves more detailed information, and outperforms competing methods.

arXiv commentIEEE Access 2018

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Deformable Convolutional Networks
• GPU-based Low Dose CT Reconstruction via Edge-preserving Total Variation Regularization
• A constrained, total-variation minimization algorithm for low-intensity X-ray CT

Cited by in corpus (31)

• Generative Adversarial Network in Medical Imaging: A Review
• CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey
• CT-image Super Resolution Using 3D Convolutional Neural Network
• Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising
• EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System
• Class-Aware Adversarial Transformers for Medical Image Segmentation
• Probabilistic self-learning framework for Low-dose CT Denoising
• A material decomposition method for dual-energy CT via dual interactive Wasserstein generative adversarial networks
• Bilevel methods for image reconstruction
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• Medical Image Generation using Generative Adversarial Networks
• Super-resolution MRI through Deep Learning
• X-ray Photon-Counting Data Correction through Deep Learning
• A Novel Loss Function Incorporating Imaging Acquisition Physics for PET Attenuation Map Generation using Deep Learning
• Unsupervised Wasserstein Distance Guided Domain Adaptation for 3D Multi-Domain Liver Segmentation
• Low-Dose CT via Deep CNN with Skip Connection and Network in Network
• Noise Reduction to Compute Tissue Mineral Density and Trabecular Bone Volume Fraction from Low Resolution QCT
• V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles: A Deep Reinforcement Learning Approach
• Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
• Deep High-Resolution Network for Low Dose X-ray CT Denoising
• Fuzzy Logic Interpretation of Quadratic Networks
• Multi-Scale Texture Loss for CT denoising with GANs
• Adversarial Multi-scale Feature Learning for Person Re-identification
• Self-supervised Dialogue Learning for Spoken Conversational Question Answering
• Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
• Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering
• Lesion-Inspired Denoising Network: Connecting Medical Image Denoising and Lesion Detection
• Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks
• Multi-Cycle-Consistent Adversarial Networks for CT Image Denoising