Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0210008(2022)
LDCT Denoising Method Based on Dual Attention Mechanism and Compound Loss
Figures & Tables(15)
Fig. 1. Dual attention module. (1) Channel attention module; (2) spatial attention module
Fig. 7. LDCT and denoising effect of different algorithms of test Fig. 1. (a) LDCT; (b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm; (h) NDCT
Fig. 8. Partial enlarged view of ROI in Figs.7. (a) LDCT; (b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm; (h) NDCT
Fig. 9. Noise after denoising by LDCT and different algorithms in Figs. 7. (a) LDCT; (b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm
Fig. 10. LDCT and denoising effect of different algorithms of test Fig. 2.(a) LDCT; (b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm; (h) NDCT
Fig. 11. Partial enlarged view of ROI in Figs.10. (a) LDCT; (b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm ; (h) NDCT
Fig. 12. Noise after denoising by LDCT and different algorithms in Figs.10. (a) LDCT;(b) BM3D; (c) K-SVD; (d) RED-CNN; (e) WGAN-VGG; (f) CycleGAN; (g) proposed algorithm
Fig. 13. Performance indicators of ROI area in Fig. 7 and Fig. 10. (a) PSNR indicator; (b) SSIM indicator
Table 1. Objective evaluation indicators in Fig. 7 and Fig. 10
View tableTable 1. Objective evaluation indicators in Fig. 7 and Fig. 10
Algorithm Fig. 7 Fig. 10 PSNR SSIM PSNR SSIM LDCT 16.9986 0.6888 15.6697 0.5829 BM3D 18.3782 0.7056 16.9822 0.6006 K-SVD 18.4449 0.6968 17.0610 0.5917 RED-CNN 22.3074 0.7267 20.7173 0.6167 WGAN-VGG 20.7928 0.7115 19.2119 0.6014 CycleGAN 21.6082 0.7186 20.0165 0.6097 Proposed algorithm 22.9577 0.7587 20.8507 0.6529
Table 2. Average objective indicators of different algorithms in test set
View tableTable 2. Average objective indicators of different algorithms in test set
Algorithm PSNR SSIM LDCT 21.5756 0.7928 BM3D 23.9134 0.8122 K-SVD 24.0704 0.8040 RED-CNN 26.4464 0.8195 WGAN-VGG 24.9213 0.8121 CycleGAN 25.7264 0.8163 Proposed algorithm 27.2176 0.8538
Tools
Get Citation
Copy Citation Text
Zhitao Guo, Yi Su, Jinli Yuan, Linlin Zhao. LDCT Denoising Method Based on Dual Attention Mechanism and Compound Loss[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210008
Paper Information
Category: Image Processing
Received: Dec. 23, 2020
Accepted: Mar. 11, 2021
Published Online: Dec. 23, 2021
The Author Email: Jinli Yuan (jinli_yuan@hebut.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20