摘要
对于不完整的医学CT扫描数据,传统算法无法保证重建图像满足诊断要求。针对这种情况,提出了一种基于加权引导滤波与梯度域卷积稀疏编码结合的CT重建算法。该算法首先采用惩罚最小二乘法迭代重建初始CT图像;其次,利用加权引导滤波获取图像的低频分量,采用带有梯度约束的卷积稀疏编码处理图像的高频分量;最后,将两段分量相结合得到的新图像作为输入继续进行最小二乘逼近,反复迭代重建,直到获得更清晰的图像。实验结果表明,与其他卷积稀疏算法及组稀疏算法相比,该算法可有效抑制噪声和伪影,恢复更多图像的结构和边缘细节信息,获得更优的重建图像。
For incomplete medical CT scan data,traditional algorithms cannot ensure that the recon‐structed images meet the diagnostic requirements.In order to solve this situation,a CT reconstruction algorithm based on the combination of weighted guided filtering and gradient domain convolutional sparse coding was proposed.Firstly,the penalty least squares method is used to iteratively reconstruct the initial CT image.Secondly,the weighted guided filtering is used to obtain the low-frequency components of the image,and the convolutional sparse coding with gradient constraints is used to process the high-frequency components of the image.Finally,the two components are combined to obtain a new image as input,and the least-squares approximation is continued,and the iterative reconstruction is repeated until a clearer image is obtained.Experimental results show that compared with other convolutional sparse algorithms and group sparse algorithms,the proposed algorithm can effectively suppress noise and artifacts,recover more image structure and edge detail information,and obtain better reconstructed images.
作者
马燕
白艳萍
续婷
程蓉
MA Yan;BAI Yanping;XU Ting;CHENG Rong(School of Mathematics,North University of China,Taiyuan 030051,China)
出处
《测试技术学报》
2025年第5期558-564,572,共8页
Journal of Test and Measurement Technology
基金
山西省基础研究计划资助项目(202103021224195,202103021224212,202103021223189,20210302123019)
山西省回国留学人员科研项目(2021-108)。
关键词
计算机断层成像
卷积稀疏编码
加权引导滤波
稀疏角度
图像重建
computed tomography
convolutional sparse coding
weighted guided filtering
sparse angle
image reconstruction
