[1]刘家奇,刘环宇,李君宝.基于深度学习网络的医学核磁共振成像超分辨率重构实验[J].中国医学物理学杂志,2021,38(1):30-39.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.006]
　LIU Jiaqi,LIU Huanyu,LI Junbao.Experimental research on super-resolution reconstruction of medical MR image by deep learning network[J].Chinese Journal of Medical Physics,2021,38(1):30-39.[doi:DOI:10.3969/j.issn.1005-202X.2021.01.006]
点击复制

基于深度学习网络的医学核磁共振成像超分辨率重构实验()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
38卷
期数:
2021年第1期
页码:
30-39
栏目:
医学影像物理
出版日期:
2021-01-29

文章信息/Info

Title:
Experimental research on super-resolution reconstruction of medical MR image by deep learning network
文章编号:
1005-202X（2021）01-0030-10
作者:
刘家奇; 刘环宇; 李君宝
哈尔滨工业大学自动化测试与控制研究所， 黑龙江 哈尔滨 150000
Author(s):
LIU Jiaqi;  LIU Huanyu;  LI Junbao
Institute of Automation Test and Control, Harbin Institute of Technology, Harbin 150000, China
关键词:
核磁共振成像; 深度学习; 超分辨率
Keywords:
Keywords: MRI deep learning super-resolution
分类号:
R318；R445.2
DOI:
DOI:10.3969/j.issn.1005-202X.2021.01.006
文献标志码:
A
摘要:
基于深度学习网络的医学核磁共振（MR）图像超分辨重建实验研究，提出并构建一个大规模的高质量用于MR图像超分辨的数据集，涵盖了头颅、膝盖、乳房以及头颈4个部位。通过数据质量筛选和不同低分辨率图像生成方式，在原始图像的高分辨率基础下，以×2、×3、×4的下采样尺度，原始MRI图像形成3种不同尺度下的MR图像数据集，同时给出不同部位超分辨难易程度分析。采用7个在自然图像的超分辨率领域中取得最好效果的深度学习网络，将它们迁移到MR图像中，学习低分辨率MR图像到高低分辨MR图像的映射关系，并对比分析这些深度学习网络在自然图像的超分辨效果。通过实验可以看出，深度学习网络在MR图像超分辨取得了比传统算法更好的效果，部分结果不亚于自然图像；不同部位的超分辨效果差异较大，难以以一个深度学习网络使不同部位均具有更好的超分辨效果。深度学习网络在MR图像超分辨将具有重要的应用价值和理论意义。
Abstract:
Abstract: Based on an experimental research on super-resolution reconstruction of medical MR (Magnetic Resonance, MR) images by deep learning network, a large-scale high-quality data set for MR images super-resolution was proposed and constructed, which covers 4 parts: skull, knees, breasts, and head & neck. With the original images as the high-resolution, the original MRI images was down-sampled with the scale of ×2, ×3, ×4, and constituted MR image data at 3 different scales through data quality screening and different low-resolution image generation methods. The difficulty levels of super-resolution was anylyzed for different parts. 7 deep learning networks that achieved the best results in the super-resolution field of natural images were adopted and transfered to MR images to learn the mapping relationship from low-resolution MR images to high- and low-resolution MR images, and the super-resolution effects of these deep learning networks in natural images were comparatively analyzed. Through the experiment, it can be seen that the deep learning networks have achieved better results than traditional algorithms in MR image super-resolution, and some results are no less than those in natural images. The super-resolution effects of different parts are quite different, and it is difficult to give each parts an equally good effect by only using a deep learning network. Deep lExperimental research on super-resolution reconstruction of medical MR image by deep learning network earning networks will have important application value and theoretical significance in MR image super-resolution.

相似文献/References:

[1]叶雪梅.纽曼系统护理模式对肝脏MRI动态增强扫描负性情绪及并发症的影响[J].中国医学物理学杂志,2015,32(01):64.[doi:10.3969/j.issn.1005-202X.2015.01.016]
[2]刘平安,樊明.成人外侧盘状半月板损伤与否核磁共振成像冠状面上影像学指标观察[J].中国医学物理学杂志,2016,33(3):308.[doi:DOI:10.3969/j.issn.1005-202X.2016.03.019]
　[J].Chinese Journal of Medical Physics,2016,33(1):308.[doi:DOI:10.3969/j.issn.1005-202X.2016.03.019]
[3]刘国才,胡泽田,朱苏雨,等.头颈部肿瘤PET与MRI融合放疗靶区自适应区域生长勾画[J].中国医学物理学杂志,2016,33(3):222.[doi:10.3969/j.issn.1005-202X.2016.03.002]
　[J].Chinese Journal of Medical Physics,2016,33(1):222.[doi:10.3969/j.issn.1005-202X.2016.03.002]
[4]贾高杰,邱崧,蔡茗名,等.三维点云重构和体显示在医学辅助诊断中的应用[J].中国医学物理学杂志,2016,33(6):593.[doi:10.3969/j.issn.1005-202X.2016.06.012]
　[J].Chinese Journal of Medical Physics,2016,33(1):593.[doi:10.3969/j.issn.1005-202X.2016.06.012]
[5]汪红志,施群雁,苗志英,等.核磁共振成像技术虚拟软件开发[J].中国医学物理学杂志,2016,33(10):1030.[doi:10.3969/j.issn.1005-202X.2016.10.012]
　[J].Chinese Journal of Medical Physics,2016,33(1):1030.[doi:10.3969/j.issn.1005-202X.2016.10.012]
[6]涂昊.超声与核磁共振成像对早产儿脑室周围白质软化诊断价值的对比性分析[J].中国医学物理学杂志,2016,33(12):1276.[doi:10.3969/j.issn.1005-202X.2016.12.021]
　[J].Chinese Journal of Medical Physics,2016,33(1):1276.[doi:10.3969/j.issn.1005-202X.2016.12.021]
[7]余炜,汪剑寒,杨昆,等.脑出血时脑脊液变化对磁感应相移信号的影响[J].中国医学物理学杂志,2017,34(1):39.[doi:10.3969/j.issn.1005-202X.2017.01.008]
　[J].Chinese Journal of Medical Physics,2017,34(1):39.[doi:10.3969/j.issn.1005-202X.2017.01.008]
[8]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
　[J].Chinese Journal of Medical Physics,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[9]祁红琳,胡先玲,李传明,等. 基于MRI纹理特征的早期肝癌术后复发预测[J].中国医学物理学杂志,2017,34(9):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
　[J].Chinese Journal of Medical Physics,2017,34(1):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
[10]蔡爱楠,随力,王君. CT/MRI双模态造影剂的制备及研究进展[J].中国医学物理学杂志,2018,35(2):219.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.020]
　CAI Ainan,SUI Li,WANG Jun. Preparation and research progress of CT/MRI bimodal contrast agent[J].Chinese Journal of Medical Physics,2018,35(1):219.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.020]

备注/Memo

备注/Memo:
【收稿日期】2020-08-23 【基金项目】国家自然科学基金（61671170） 【作者简介】刘家奇，硕士研究生，研究方向：超分辨率重建，E-mail: ljq- _swjtu@163.com。 【通信作者】李君宝，博士，教授，研究方向：机器学习在医学影像的应用，E-mail: lijunbao@hit.edu.cn
更新日期/Last Update: 2021-01-29