1
|
Lin J, Li J, Dou J, Zhong L, Di J, Qin Y. Dual-Domain Reconstruction Network Incorporating Multi-Level Wavelet Transform and Recurrent Convolution for Sparse View Computed Tomography Imaging. Tomography 2024; 10:133-158. [PMID: 38250957 PMCID: PMC11154272 DOI: 10.3390/tomography10010011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 01/08/2024] [Accepted: 01/10/2024] [Indexed: 01/23/2024] Open
Abstract
Sparse view computed tomography (SVCT) aims to reduce the number of X-ray projection views required for reconstructing the cross-sectional image of an object. While SVCT significantly reduces X-ray radiation dose and speeds up scanning, insufficient projection data give rise to issues such as severe streak artifacts and blurring in reconstructed images, thereby impacting the diagnostic accuracy of CT detection. To address this challenge, a dual-domain reconstruction network incorporating multi-level wavelet transform and recurrent convolution is proposed in this paper. The dual-domain network is composed of a sinogram domain network (SDN) and an image domain network (IDN). Multi-level wavelet transform is employed in both IDN and SDN to decompose sinograms and CT images into distinct frequency components, which are then processed through separate network branches to recover detailed information within their respective frequency bands. To capture global textures, artifacts, and shallow features in sinograms and CT images, a recurrent convolution unit (RCU) based on convolutional long and short-term memory (Conv-LSTM) is designed, which can model their long-range dependencies through recurrent calculation. Additionally, a self-attention-based multi-level frequency feature normalization fusion (MFNF) block is proposed to assist in recovering high-frequency components by aggregating low-frequency components. Finally, an edge loss function based on the Laplacian of Gaussian (LoG) is designed as the regularization term for enhancing the recovery of high-frequency edge structures. The experimental results demonstrate the effectiveness of our approach in reducing artifacts and enhancing the reconstruction of intricate structural details across various sparse views and noise levels. Our method excels in both performance and robustness, as evidenced by its superior outcomes in numerous qualitative and quantitative assessments, surpassing contemporary state-of-the-art CNNs or Transformer-based reconstruction methods.
Collapse
Affiliation(s)
- Juncheng Lin
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| | - Jialin Li
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| | - Jiazhen Dou
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| | - Liyun Zhong
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| | - Jianglei Di
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| | - Yuwen Qin
- Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China; (J.L.); (J.L.); (J.D.); (L.Z.); (Y.Q.)
- Guangdong Provincial Key Laboratory of Information Photonics Technology, Guangdong University of Technology, Guangzhou 510006, China
- Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education, Guangdong University of Technology, Guangzhou 510006, China
| |
Collapse
|
2
|
Deep Learning-Based Computed Tomography Features in Evaluating Early Screening and Risk Factors for Chronic Obstructive Pulmonary Disease. CONTRAST MEDIA & MOLECULAR IMAGING 2022; 2022:5951418. [PMID: 36051929 PMCID: PMC9410847 DOI: 10.1155/2022/5951418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Revised: 07/06/2022] [Accepted: 07/09/2022] [Indexed: 11/18/2022]
Abstract
This research aimed to investigate the diagnostic effect of computed tomography (CT) images based on a deep learning double residual convolution neural network (DRCNN) model on chronic obstructive pulmonary disease (COPD) and the related risk factors for COPD. The questionnaire survey was conducted among 980 permanent residents aged ≥ 40 years old. Among them, 84 patients who were diagnosed with COPD and volunteered to participate in the experiment and 25 healthy people were selected as the research subjects, and all of them underwent CT imaging scans. At the same time, an image noise reduction model based on the DRCNN was proposed to process CT images. The results showed that 84 of 980 subjects were diagnosed with COPD, and the overall prevalence of COPD in this epidemiological survey was 8.57%. Multivariate logistic regression model analysis showed that the regression coefficients of COPD with age, family history of COPD, and smoking were 0.557, 0.513, and 0.717, respectively (P < 0.05). The diagnostic sensitivity, specificity, and accuracy of DRCNN-based CT for COPD were greatly superior to those of single CT and the difference was considerable (P < 0.05). In summary, advanced age, family history of COPD, and smoking were independent risk factors for COPD. CT based on the DRCNN model can improve the diagnostic accuracy of simple CT images for COPD and has good performance in the early screening of COPD.
Collapse
|