Yu Li, Na Shi, Huihua Kong, Xiaoxue Lei. Sparse Angle CT Reconstruction Algorithm Based on Total Variation and Convolutional Sparse Coding in Gradient Domain[J]. Laser & Optoelectronics Progress, 2021, 58(12): 1210031
- Laser & Optoelectronics Progress
- Vol. 58, Issue 12, 1210031 (2021)
Fig. 1. Main steps of TV-CSCGR algorithm
![Images of training set (display window is [-150 250])](/richHtml/lop/2021/58/12/1210031/img_2.jpg)
Fig. 2. Images of training set (display window is [-150 250])
Fig. 3. Training filters by fully sampled CT images
Fig. 4. Reconstruction results of noiseless thoracic image with 64 projection angles (display window is [-1000 250]).(a) SART-TV; (b) SART-CSC; (c) SART-CSCGR; (d) TVPI-G; (e) TV-CSCGR
Fig. 5. Curve change diagrams of two evaluation indexes of noiseless thoracic image when number of projection angles is 64. (a) NRMSE; (b) PSNR
Fig. 6. Reconstruction results of thoracic image with noise when number of projection angles is 64 (display window is [-1000 250]). (a) SART-TV; (b) SART-CSC; (c) SART-CSCGR; (d) TVPI-G; (e) TV-CSCGR
Fig. 7. Curve change diagrams of two evaluation indexes of noisy thoracic image when number of projection angles is 64. (a) NRMSE; (b) PSNR
Fig. 8. Reconstruction results of pelvic image with noise when number of projection angles is 64 (display window is [-1000 250]). (a) SART-TV; (b) SART-CSC; (c) SART-CSCGR; (d) TVPI-G; (e) TV-CSCGR
Fig. 9. Curve change diagrams of two evaluation indexes of pelvic image with noise when number of projection angles is 64. (a) NRMSE; (b) PSNR
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20