Author Affiliations
1School of Engineering Science, University of Science and Technology of China, Hefei, Anhui 230026, China2Key Laboratory of Precision Scientific Instrumentation of Anhui Higher Education Institutes, Hefei, Anhui 230026, China3Zhejiang Lab, Hangzhou, Zhejiang 311121, Chinashow less
Fig. 1. Network structure of DI-Net. (a) Overall schematic of DI-Net; (b) network structure of D-Net (M=512,N=768,k=16) and I-Net (M=256,N=256,k=32)
Fig. 2. Schematic of the experimental setup
Fig. 3. Reconstruction results of vascular phantom based on 128 projection views (All color bars stand for amplitudes of pixels on images). (a) Reference image; (b)(d) images reconstructed by FBP algorithm, Post-Unet algorithm, and DI-Net algorithm, respectively; (e)(g) difference images between the reference image and the images reconstructed by FBP, Post-Unet, and DI-Net, respectively; (d) quantitative evaluation results of the reconstruction images
Fig. 4. Reconstruction results of vascular phantom based on 256 projection views (All color bars stand for amplitudes of pixels on images). (a) Reference image; (b)(d) images reconstructed by FBP algorithm, Post-Unet algorithm, and DI-Net algorithm, respectively; (e)(g) difference images between the reference image and the images reconstructed by FBP, Post-Unet, and DI-Net, respectively; (d) quantitative evaluation results of the reconstruction images
Fig. 5. Quantitative evaluation results of different algorithms on the vascular test dataset (To facilitate observation, the ordinate of the boxplot in the small dashed box is stretched and separately shown in the large dashed box). (a)(d) MSE; (b)(e) PSNR; (c)(f) SSIM
Fig. 6. Reconstruction results of mouse slice based on 128 projection views (All color bars stand for amplitudes of pixels on images). (a) Reference image; (b)(d) images reconstructed by FBP algorithm, Post-Unet algorithm, and DI-Net algorithm, respectively; (e)(g) difference images between the reference image and the images reconstructed by FBP, Post-Unet, and DI-Net, respectively; (d) quantitative evaluation results of the reconstruction images
Fig. 7. Reconstruction results of mouse slice based on 256 projection views (All color bars stand for amplitudes of pixels on images). (a) Reference image; (b)(d) images reconstructed by FBP algorithm, Post-Unet algorithm, and DI-Net algorithm, respectively; (e)(g) difference images between the reference image and the images reconstructed by FBP, Post-Unet, and DI-Net, respectively; (d) quantitative evaluation results of the reconstruction images
Fig. 8. Quantitative evaluation results of different algorithms on the mouse slice test dataset. (a)(d) MSE; (b)(e) PSNR; (c)(f) SSIM
Number of views | Method | MSE | PSNR /dB | SSIM |
---|
128 | FBP | 1.880×10-2 | 23.18 | 0.4495 | Post-Unet | 5.005×10-4 | 39.05 | 0.9919 | DI-Net | 1.308×10-4 | 44.95 | 0.9974 | 256 | FBP | 5.700×10-3 | 25.90 | 0.7463 | Post-Unet | 6.235×10-5 | 45.50 | 0.9978 | DI-Net | 3.640×10-5 | 47.82 | 0.9984 |
|
Table 1. Mean value of quantitative evaluation results for different algorithms on the vascular test dataset
Number of views | Method | MSE | PSNR /dB | SSIM |
---|
128 | FBP | 0.0848 | 28.57 | 0.5385 | Post-Unet | 0.0119 | 37.00 | 0.8972 | DI-Net | 0.0072 | 39.26 | 0.9371 | 256 | 0.0218 | FBP | 33.77 | 0.7719 | Post-Unet | 0.0047 | 40.38 | 0.9462 | DI-Net | 0.0022 | 43.52 | 0.9741 |
|
Table 2. Mean value of quantitative evaluation results for different algorithms on the mouse slice test dataset
Number of views | FBP | Post-Unet | DI-Net |
---|
128 | 0.10 | 0.13 | 0.20 | 256 | 0.20 | 0.23 | 0.20 |
|
Table 3. Comparisons of consuming time for different algorithms unit:s