MRCON-Net: Multiscale reweighted convolutional coding neural network for low-dose CT imaging

Jin Liu; Yanqin Kang; Zhenyu Xia; Jun Qiang; JunFeng Zhang; Yikun Zhang; Yang Chen

doi:10.1016/j.cmpb.2022.106851

MRCON-Net: Multiscale reweighted convolutional coding neural network for low-dose CT imaging

Comput Methods Programs Biomed. 2022 Jun:221:106851. doi: 10.1016/j.cmpb.2022.106851. Epub 2022 May 8.

Authors

Jin Liu¹, Yanqin Kang², Zhenyu Xia³, Jun Qiang³, JunFeng Zhang⁴, Yikun Zhang⁵, Yang Chen⁵

Affiliations

¹ College of Computer and Information, Anhui Polytechnic University, Wuhu, China; Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing, China. Electronic address: liujin@ahpu.edu.cn.
² College of Computer and Information, Anhui Polytechnic University, Wuhu, China; Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing, China.
³ College of Computer and Information, Anhui Polytechnic University, Wuhu, China.
⁴ School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou, China.
⁵ Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing, China; School of Cyber Science and Engineering, Southeast University, Nanjing, China; School of Computer Science and Engineering, Southeast University, Nanjing, China.

PMID: 35576686
DOI: 10.1016/j.cmpb.2022.106851

Abstract

Background and objective: Low-dose computed tomography (LDCT) has become increasingly important for alleviating X-ray radiation damage. However, reducing the administered radiation dose may lead to degraded CT images with amplified mottle noise and nonstationary streak artifacts. Previous studies have confirmed that deep learning (DL) is promising for improving LDCT imaging. However, most DL-based frameworks are built intuitively, lack interpretability, and suffer from image detail information loss, which has become a general challenging issue.

Methods: A multiscale reweighted convolutional coding neural network (MRCON-Net) is developed to address the above problems. MRCON-Net is compact and more explainable than other networks. First, inspired by the learning-based reweighted iterative soft thresholding algorithm (ISTA), we extend traditional convolutional sparse coding (CSC) to its reweighted convolutional learning form. Second, we use dilated convolution to extract multiscale image features, allowing our single model to capture the correlations between features of different scales. Finally, to automatically adjust the elements in the feature code to correct the obtained solution, a channel attention (CA) mechanism is utilized to learn appropriate weights.

Results: The visual results obtained based on the American Association of Physicians in Medicine (AAPM) Challenge and United Image Healthcare (UIH) clinical datasets confirm that the proposed model significantly reduces serious artifact noise while retaining the desired structures. Quantitative results show that the average structural similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) achieved on the AAPM Challenge dataset are 0.9491 and 40.66, respectively, and the SSIM and PSNR achieved on the UIH clinical dataset are 0.915 and 42.44, respectively; these are promising quantitative results.

Conclusion: Compared with recent state-of-the-art methods, the proposed model achieves subtle structure-enhanced LDCT imaging. In addition, through ablation studies, the components of the proposed model are validated to achieve performance improvements.

Keywords: Convolutional coding; Low-dose CT; Multiscale; Reweighted learning.

MeSH terms

Algorithms
Artifacts
Image Processing, Computer-Assisted* / methods
Neural Networks, Computer*
Signal-To-Noise Ratio
Tomography, X-Ray Computed / methods