[1]刘琪,胡宇韬,杨淳沨,等.基于噪声自适应感知的低场MRI图像增强方法[J].中国医学物理学杂志,2026,43(3):293-299.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.003]
　LIU Qi,HU Yutao,YANG Chunfeng,et al.Low-field MRI image enhancement method based on adaptive noise perception[J].Chinese Journal of Medical Physics,2026,43(3):293-299.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.003]
点击复制

基于噪声自适应感知的低场MRI图像增强方法()

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

卷:
43卷
期数:
2026年第3期
页码:
293-299
栏目:
医学影像物理
出版日期:
2026-03-27

文章信息/Info

Title:
Low-field MRI image enhancement method based on adaptive noise perception
文章编号:
1005-202X（2026）03-0293-07
作者:
刘琪1; 胡宇韬2; 杨淳沨2; 陈阳1; 2
1.南方医科大学生物医学工程学院， 广东 广州 510515； 2.东南大学计算机科学与工程学院， 江苏 南京 211189
Author(s):
LIU Qi1;  HU Yutao2;  YANG Chunfeng2;  CHEN Yang1;  2
1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China 2. School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
关键词:
低场MRI; 图像增强; 深度学习; 双分支网络
Keywords:
Keywords:?ow-field magnetic resonance imaging image enhancement deep learning dual-path network
分类号:
R318；R445.2
DOI:
DOI:10.3969/j.issn.1005-202X.2026.03.003
文献标志码:
A
摘要:
目的：对低场核磁共振成像（MRI）设备采集的低信噪比、高噪声的MRI图像进行高效且鲁棒的质量提升。方法：针对缺乏一一对应的高场-低场MRI图像的问题，提出在高场MRI图像的K空间数据上进行加噪声和图像域欠采样的低场MRI图像模拟方法，获得用于训练的高场-低场MRI图像数据集。针对难以感知低场MRI图像中噪声强度的问题，提出带有噪声自适应感知分支的双路去噪增强网络，使用公开数据集IXI和fastMRI的数据构建用于训练的数据集，实现对低场图像噪声的有效感知以及对低场图像质量的显著增强。针对难以量化低场图像增强质量的问题，提出采用弗雷歇初始距离（FID）和学习型感知图像块相似度（LPIPS）评估增强后的低场MRI图像的图像质量方法，实现对低场MRI图像增强效果的科学评估。结果：在真实低场数据中，双路去噪增强网络表现出了最好的去噪以及细节保留效果。以IXI数据集进行训练，FID和LPIPS分别为0.472 9和149.649 3；以fastMRI数据集进行训练，FID和LPIPS分别为0.473 4和148.432 3。结论：基于噪声自适应的低场MRI图像增强方法能够较好地对低场图像进行增强，能够有效推进低场MRI设备在临床上的应用。
Abstract:
Abstract: Objective To achieve efficient and robust quality enhancement for low signal-to-noise ratio (SNR) and high-noise-level magnetic resonance imaging (MRI) images acquired by low-field MRI devices. Methods Given the lack of one-to-one paired high- and low-field MRI images, a simulation method was develop to generate low-field MR images by adding noise into the K-space data of high-field MRI images and performing undersampling in the image domain, thereby constructing a paired high- and low-field MRI image dataset for training. A dual-path denoising and enhancement network with an adaptive noise perception branch was introduced to tackle the difficulty in perceiving noise intensity in low-field MR images. Publicly available datasets IXI and fastMRI were used to establish training datasets for enabling effective noise perception and significant quality enhancement of low-field images. In addition, Fréchet inception distance (FID) and learned perceptual image patch similarity (LPIPS) were adopted to evaluate the quality of enhanced low-field MR images, which overcame the challenge of quantifying enhancement performance in low-field MRI images, and enabled a scientific assessment of the efficacy of low-field MRI image enhancement. Results On real low-field data, the dual-path denoising and enhancement network exhibited the best performance in both denoising and detail preservation. When trained on the IXI dataset, the FID and LPIPS values reached 0.472 9 and 149.649 3, respectively when trained on the fastMRI dataset, the corresponding values were 0.473 4 and 148.432 3, respectively. Conclusion The low-field MRI image enhancement method based on adaptive noise perception can effectively enhance low-field images, which promotes the clinical application of low-field MRI devices.

相似文献/References:

[1]林曦,余文明,陈 新,等.同态滤波技术在膜蛋白颗粒图像增强中的应用[J].中国医学物理学杂志,2015,32(02):187.[doi:10.3969/j.issn.1005-202X.2015.02.008]
[2]刘红.基于帧间相似的序列X光图像的预处理技术[J].中国医学物理学杂志,2013,30(05):4409.[doi:10.3969/j.issn.1005-202X.2013.05.016]
[3]步蕊蕊,汪葛,王远军,等.基于三维结构张量的CT肺血管树增强[J].中国医学物理学杂志,2016,33(4):336.[doi:10.3969/j.issn.1005-202X.2016.04.003]
　[J].Chinese Journal of Medical Physics,2016,33(3):336.[doi:10.3969/j.issn.1005-202X.2016.04.003]
[4]邓金城,刘常春,莫珍丽,等. 基于Hessian矩阵及余弦定理的肝门静脉血管检测[J].中国医学物理学杂志,2017,34(5):462.[doi:DOI:10.3969/j.issn.1005-202X.2017.05.006]
[5]王文静,张莉钏,王欣,等.融合改进Retinex图像增强与深度学习的糖尿病视网膜分类检测方法[J].中国医学物理学杂志,2024,41(9):1086.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.005]
　WANG Wenjing,ZHANG Lichuan,WANG Xin,et al.Classification and detection method for diabetic retinopathy based on the combination of improved Retinex image enhancement and deep learning[J].Chinese Journal of Medical Physics,2024,41(3):1086.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.005]
[6]李家乐,陈燕,王冠军,等.基于色相感知与统计特性的眼底图像融合增强方法[J].中国医学物理学杂志,2026,43(2):196.[doi:DOI:10.3969/j.issn.1005-202X.2026.02.008]
　LI Jiale,CHEN Yan,WANG Guanjun,et al.Fundus image fusion enhancement method based on hue perception and statistical properties[J].Chinese Journal of Medical Physics,2026,43(3):196.[doi:DOI:10.3969/j.issn.1005-202X.2026.02.008]

备注/Memo

备注/Memo:
【收稿日期】2025-08-19 【基金项目】国家杰出青年科学基金（T2225025） 【作者简介】刘琪，硕士研究生，研究方向：人工智能医学影像、MRI图像处理，E-mai: 1208857531@qq.com 【通信作者】陈阳，教授，研究方向：人工智能应用、计算机视觉、智能图像处理，E-mail: chenyang.list@seu.edu.cn
更新日期/Last Update: 2026-03-27