摘要
高分辨率磁共振图像对于医学诊断具有重要意义,本文提出一种多分辨率学习卷积神经网络,并应用于磁共振图像超分辨率。网络是一种新型深度残差网络,包含用于特征提取的残差单元、多分辨率上采样的反卷积层以及多分辨率学习层。设计的网络在低分辨率图像空间中实现图像超分辨率,采用多分辨率上采样实现多个残差单元信息融合并加速网络,多分辨率学习能够自适应地确定各分辨率上采样的高维特征图对磁共振图像超分辨重建的贡献度。实验表明,论文提出的方法能够很好地超分辨率重建磁共振图像,优于最新的深度学习方法。
High-resolution magnetic resonance images are of great significance for medical diagnosis.A convolutional neural network with multi-resolution learning is proposed for magnetic resonance image(MR)superresolution.The network is an improved deep residual network,which involves residual units for feature extraction,a deconvolution layer for multi-resolution up-sampling,and a multi-resolution learning layer.The proposed network performs the super-resolution task in the low-resolution space,which can accelerate the network.Multiresolution upsampling is put forward to integrate multiple residual unit information and to accelerate the network.Multi-resolution learning can adaptively determine the contributions of these upsampled high-dimensional feature maps to high-resolution MR image reconstruction.Experiment results indicate that the proposed method can achieve a good super-resolution reconstruction performance for magnetic resonance images,which is superior to the state-of-the-art deep learning methods.
作者
夏皓
蔡念
王平
王晗
Xia Hao;Cai Nian;Wang Ping;Wang Han(School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China;Department of Hepatobiliaiy Surgery,the First Affiliated Hospital of Guangzhou Medical University,Guangzhou 510120,China;School of Electromechanical Engineering,Guangdong University of Technology,Guangzhou 510006,China)
出处
《广东工业大学学报》
CAS
2020年第6期26-31,共6页
Journal of Guangdong University of Technology
基金
广东省科技重大专项项目(2017B090911012)
广州市民生科技攻关计划重大专项项目(201803010065)
季华实验室项目(X190071UZ190)。
关键词
卷积神经网络
多分辨率学习
磁共振图像
超分辨率重建
convolutional neural network
multi-resolution learning
magnetic resonance image
super-resolution reconstruction
