摘要
为解决核磁共振图像重构中由于欠采样导致的重构图像质量较低的问题,提出了一种基于凸-非凸稀疏正则和即插即用近似点梯度下降的核磁共振图像重构算法。首先给出了凸-非凸稀疏正则的近似点算子。然后基于该近似点算子提出近似点梯度下降算法。最后将上述算法中的近似点算子用某种合适的去噪器(如神经网络去噪器)替换,得到即插即用近似点梯度下降算法,并将其应用到核磁共振图像重构上。数值实验中,分别用不同的待重构图像、采样模板和去噪器进行对比实验,实验结果表明,所提算法在使用神经网络去噪器时,峰值信噪比较已有算法提升了6.26 dB。同时视觉效果也得到了显著的提升,在处理边缘和纹路方面效果都更加明显,从而验证了算法的有效性。
A magnetic resonance image reconstruction algorithm based on convex-nonconvex sparse regularization and plug-and-play proximal gradient descent algorithm is proposed to deal with low reconstruction quality due to undersampling.Firstly,the proximal operator of convex-nonconvex sparse regularization is given.Then,a proximal gradient descent algo-rithm is proposed.Finally,properly trained denoisers,such as neural network denoisers,are used to replace the proximal operator and plug in the above algorithm.The so-called plug-and-play proximal gradient descent algorithm is then applied to magnetic resonance image reconstruction.In numerical experiments,different images,sampling templates and denoisers are used for comparison experiments.The experimental results show that compared with other algorithms,the peak signal to-noise ratio of the proposed algorithm with a properly trained neural network denoiser improves 6.26 dB.Visual effects have also been significantly improved,the effect of processing edges and textures is more obvious,thus verifying the effec-tiveness of the algorithm.
作者
李金城
谢朝阳
李金兰
张涛
邹健
LI Jincheng;XIE Zhaoyang;LI Jinlan;ZHANG Tao;ZOU Jian(School of Information and Mathematics,Yangtze University,Jingzhou,Hubei 434023,China)
出处
《计算机工程与应用》
CSCD
北大核心
2022年第22期239-245,共7页
Computer Engineering and Applications
基金
国家自然科学基金(61673006)。
关键词
核磁共振成像
凸-非凸稀疏正则
近似点梯度下降算法
即插即用算法
神经网络去噪器
magnetic resonance imaging
convex-nonconvex sparse regularization
proximal gradient descent algorithm
plug-and-play algorithm
neural network denoiser
作者简介
李金城(1997-),女,硕士研究生,主要研究方向为信号处理、图像处理、最优化理论与算法;谢朝阳(1999-),男,硕士研究生,主要研究方向为压缩感知、图像处理;李金兰(2000-),女,硕士研究生,主要研究方向为图像处理、数值优化;张涛(1978-),男,博士,教授,主要研究方向为二层规划,深度学习;通信作者:邹健(1983-),男,博士,副教授,主要研究方向为信号处理、图像处理、数值优化,E-mail:zoujian@yangtzeu.edu.cn。
