武汉大学 电子信息学院， 武汉 430072
出版日期:2019-08-28发布日期:2019-09-10通讯作者:杨剑锋，男，副教授，电话(Tel.): 027-68752280；E-mail: yjf@whu.edu.cn.作者简介:章云港（1994-），男，浙江省温州市人，硕士生，主要研究方向为深度学习与图像处理.Improved Residual Encoder-Decoder Network for Low-Dose CT Image Denoising
ZHANG Yungang,YANG Jianfeng,YI BenshunElectronic Information School, Wuhan University, Wuhan 430072, China
Online:2019-08-28Published:2019-09-10摘要/Abstract
摘要： 针对低剂量CT图像中存在复杂噪声与伪影的问题，提出了一种用于低剂量CT图像去噪的改进型残差编解码网络.原始的残差编解码网络由一系列卷积层与反卷积层组成，且通过短连接结构学习残差.改进措施主要包括3个方面：首先，引入了批量归一化提高网络的去噪效果；其次，使用空洞卷积替换普通卷积，从而有效减少了网络中参数的数量；最后，对网络隐层中的特征图数量进行了调整，进一步优化了网络性能与复杂度.实验结果表明：改进后的网络复杂度降低，去噪效果得到提升.
关键词: 图像去噪； 低剂量CT； 深度学习； 卷积神经网络
Abstract: Aiming at the complex noise and artifacts in low-dose CT images, an improved residual encoder-decoder network for low-dose CT image denoising is proposed. The original residual encoder-decoder network consists of a series of convolution and deconvolution layers, and learns the residuals through shortcut connections. The improvement method mainly includes three aspects: firstly, batch normalization is introduced to improve the denoising performance of the network; secondly, dilated convolution is used to replace normal convolution so as to reduce the parameters in the network without degrading the denoising performance; besides, the number of feature maps in the hidden layer of the network has been adjusted to further optimize the network performance and complexity. Experimental results show that the improved network significantly reduces the complexity and also improves the denoising performance.
Key words: image denoising; low-dose CT; deep learning; convolutional neural network
PDF全文下载地址:
点我下载PDF
