Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (7): 2301-2310.DOI: 10.11772/j.issn.1001-9081.2021040700
• Frontier and comprehensive applications • Previous Articles
Zefang HAN, Xiong ZHANG(), Hong SHANGGUAN, Xinglong HAN, Jing HAN, Gang FENG, Xueying CUI
Received:
2021-05-06
Revised:
2021-10-08
Accepted:
2021-10-12
Online:
2022-07-15
Published:
2022-07-10
Contact:
Xiong ZHANG
About author:
HAN Zefang, born in 1996, M. S. candidate. Her research interests include medical image processing.Supported by:
韩泽芳, 张雄(), 上官宏, 韩兴隆, 韩静, 奉刚, 崔学英
通讯作者:
张雄
作者简介:
韩泽芳(1996—),女,山西晋城人,硕士研究生,主要研究方向:医学图像处理基金资助:
CLC Number:
Zefang HAN, Xiong ZHANG, Hong SHANGGUAN, Xinglong HAN, Jing HAN, Gang FENG, Xueying CUI. Artifacts sensing generative adversarial network for low-dose CT denoising[J]. Journal of Computer Applications, 2022, 42(7): 2301-2310.
韩泽芳, 张雄, 上官宏, 韩兴隆, 韩静, 奉刚, 崔学英. 用于低剂量CT降噪的伪影感知生成对抗网络[J]. 《计算机应用》唯一官方网站, 2022, 42(7): 2301-2310.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021040700
算法 | PSNR/dB | SSIM | VIF | IFC |
---|---|---|---|---|
LDCT | 26.789 1±1.978 2 | 0.810 0±0.053 5 | 0.364 2±0.057 9 | 2.416 2±0.243 6 |
BM3D | 30.261 8±1.712 8 | 0.856 6±0.040 8 | 0.385 4±0.047 7 | 2.584 8±0.222 1 |
RED-CNN | 30.511 4±1.764 7 | 0.866 0±0.041 8 | 0.390 2±0.059 9 | 2.602 2±0.230 5 |
pix2pix | 28.318 3±1.659 9 | 0.811 1±0.054 5 | 0.334 2±0.054 3 | 2.209 1±0.203 7 |
HFSGAN | 30.081 8±1.588 9 | 0.852 7±0.044 5 | 0.373 3±0.052 7 | 2.504 5±0.202 7 |
SiameseGAN | 29.443 9±1.535 0 | 0.861 7±0.042 2 | 0.391 1±0.056 0 | 2.678 6±0.233 0 |
本文算法 | 31.543 2±1.720 8 | 0.876 4±0.040 9 | 0.426 2±0.058 3 | 2.934 8±0.249 1 |
Tab.1 Statistical table of average quantization index values of denoised results obtained by different algorithms in whole testing dataset (mean±standard deviation)
算法 | PSNR/dB | SSIM | VIF | IFC |
---|---|---|---|---|
LDCT | 26.789 1±1.978 2 | 0.810 0±0.053 5 | 0.364 2±0.057 9 | 2.416 2±0.243 6 |
BM3D | 30.261 8±1.712 8 | 0.856 6±0.040 8 | 0.385 4±0.047 7 | 2.584 8±0.222 1 |
RED-CNN | 30.511 4±1.764 7 | 0.866 0±0.041 8 | 0.390 2±0.059 9 | 2.602 2±0.230 5 |
pix2pix | 28.318 3±1.659 9 | 0.811 1±0.054 5 | 0.334 2±0.054 3 | 2.209 1±0.203 7 |
HFSGAN | 30.081 8±1.588 9 | 0.852 7±0.044 5 | 0.373 3±0.052 7 | 2.504 5±0.202 7 |
SiameseGAN | 29.443 9±1.535 0 | 0.861 7±0.042 2 | 0.391 1±0.056 0 | 2.678 6±0.233 0 |
本文算法 | 31.543 2±1.720 8 | 0.876 4±0.040 9 | 0.426 2±0.058 3 | 2.934 8±0.249 1 |
算法 | SSIM | PSNR/dB | VIF | IFC |
---|---|---|---|---|
LDCT | 0.489 9±0.124 1 | 19.990 5±3.928 5 | 0.163 8±0.040 1 | 1.486 1±0.561 7 |
BM3D | 0.576 2±0.142 6 | 23.114 4±5.698 5 | 0.232 4±0.063 6 | 1.469 8±0.516 8 |
RED-CNN | 0.626 8±0.092 0 | 23.805 8±5.118 5 | 0.252 7±0.051 5 | 1.590 3±0.506 0 |
pix2pix | 0.489 0±0.109 0 | 21.754 8±3.626 2 | 0.152 3±0.046 1 | 1.160 2±0.558 5 |
HFSGAN | 0.603 4±0.092 4 | 23.786 1±4.189 9 | 0.227 9±0.039 1 | 1.451 2±0.541 2 |
SiameseGAN | 0.623 6±0.083 8 | 22.832 6±3.507 1 | 0.244 7±0.035 7 | 1.390 5±0.943 1 |
本文算法 | 0.651 7±0.079 3 | 24.962 8±4.310 1 | 0.306 4±0.044 4 | 1.729 2±0.468 5 |
Tab.2 Average PSNR and SSIM values on 4 ROIs in Fig. 3 to Fig. 6 (mean±standard deviation)
算法 | SSIM | PSNR/dB | VIF | IFC |
---|---|---|---|---|
LDCT | 0.489 9±0.124 1 | 19.990 5±3.928 5 | 0.163 8±0.040 1 | 1.486 1±0.561 7 |
BM3D | 0.576 2±0.142 6 | 23.114 4±5.698 5 | 0.232 4±0.063 6 | 1.469 8±0.516 8 |
RED-CNN | 0.626 8±0.092 0 | 23.805 8±5.118 5 | 0.252 7±0.051 5 | 1.590 3±0.506 0 |
pix2pix | 0.489 0±0.109 0 | 21.754 8±3.626 2 | 0.152 3±0.046 1 | 1.160 2±0.558 5 |
HFSGAN | 0.603 4±0.092 4 | 23.786 1±4.189 9 | 0.227 9±0.039 1 | 1.451 2±0.541 2 |
SiameseGAN | 0.623 6±0.083 8 | 22.832 6±3.507 1 | 0.244 7±0.035 7 | 1.390 5±0.943 1 |
本文算法 | 0.651 7±0.079 3 | 24.962 8±4.310 1 | 0.306 4±0.044 4 | 1.729 2±0.468 5 |
算法 | 子模块 | 平均SSIM | 平均PSNR/dB | ||
---|---|---|---|---|---|
ADSS | URED | AttD | |||
w/o AttD+URED+ADSS | 0.874 7 | 31.378 0 | |||
w/o AttD+URED | √ | 0.874 6 | 31.390 6 | ||
w/o AttD | √ | √ | 0.876 5 | 31.521 6 | |
本文算法 | √ | √ | √ | 0.876 4 | 31.543 2 |
Tab.3 Influence of network structure ablation on algorithm performance
算法 | 子模块 | 平均SSIM | 平均PSNR/dB | ||
---|---|---|---|---|---|
ADSS | URED | AttD | |||
w/o AttD+URED+ADSS | 0.874 7 | 31.378 0 | |||
w/o AttD+URED | √ | 0.874 6 | 31.390 6 | ||
w/o AttD | √ | √ | 0.876 5 | 31.521 6 | |
本文算法 | √ | √ | √ | 0.876 4 | 31.543 2 |
算法 | 训练时间/s | 每幅测试时间/s | 参数量 | 迭代 次数 |
---|---|---|---|---|
BM3D | — | 1.207 8 | — | — |
RED-CNN | 674.68 | 0.104 1 | 1 848 865 | 30 |
pix2pix | 4 740.58 | 0.067 9 | 57 190 084 | 30 |
HFSGAN | 6 522.60 | 0.075 1 | 108 877 962 | 30 |
SiameseGAN | 55 635.40 | 0.047 5 | 86 829 640 | 30 |
本文算法 | 32 177.65 | 0.053 5 | 35 285 594 | 30 |
Tab.4 Comparison of training and testing time of six algorithms
算法 | 训练时间/s | 每幅测试时间/s | 参数量 | 迭代 次数 |
---|---|---|---|---|
BM3D | — | 1.207 8 | — | — |
RED-CNN | 674.68 | 0.104 1 | 1 848 865 | 30 |
pix2pix | 4 740.58 | 0.067 9 | 57 190 084 | 30 |
HFSGAN | 6 522.60 | 0.075 1 | 108 877 962 | 30 |
SiameseGAN | 55 635.40 | 0.047 5 | 86 829 640 | 30 |
本文算法 | 32 177.65 | 0.053 5 | 35 285 594 | 30 |
1 | 张权.低剂量X线CT重建若干问题研究[D]. 南京:东南大学, 2015:1. 10.7666/d.Y2977255 |
ZHANG Q. A study on some problems in image reconstruction for low-dose CT system[D]. Nanjing: Southeast University, 2015:1. 10.7666/d.Y2977255 | |
2 | ALIASGHARZADEH A, MIHANDOOST E, MOHSENI M. A survey of computed tomography dose index and dose length product level in usual computed tomography protocol[J]. Journal of Cancer Research and Therapeutics, 2018, 14(3): 549. 10.4103/0973-1482.172713 |
3 | BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising[C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005: 60-65. |
4 | FERUGLIO P F, VINEGONI C, GROS J, et al. Block matching 3D random noise filtering for absorption optical projection tomography[J]. Physics in Medicine and Biology, 2010, 55(18): No.5401. 10.1088/0031-9155/55/18/009 |
5 | 代晓婷,龚敬,聂生东. 基于结构联合字典的肺部LDCT图像降噪[J]. 电子学报, 2018, 46(6):1445-1453. 10.3969/j.issn.0372-2112.2018.06.025 |
DAI X T, GONG J, NIE S D. Low-dose lung CT image denoising using joint structural dictionary[J]. Acta Electronica Sinica, 2018, 46(6):1445-1453. 10.3969/j.issn.0372-2112.2018.06.025 | |
6 | CHEN W B, SHAO Y L, JIA L N, et al. Low-dose CT image denoising model based on sparse representation by stationarily classified sub-dictionaries[J]. IEEE Access, 2019, 7: 116859-116874. 10.1109/access.2019.2932754 |
7 | LIU W B, WANG Z D, LIU X H, et al. A survey of deep neural network architectures and their applications[J]. Neurocomputing, 2017, 234: 11-26. 10.1016/j.neucom.2016.12.038 |
8 | CHEN H, ZHANG Y, ZHANG W H, et al. Low-dose CT via convolutional neural network[J]. Biomedical Optics Express, 2017, 8(2): 679-694. 10.1364/boe.8.000679 |
9 | SHAN H M, ZHANG Y, YANG Q S, et al. 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network[J]. IEEE Transactions on Medical Imaging, 2018, 37(6): 1522-1534. 10.1109/tmi.2018.2832217 |
10 | CHEN H, ZHANG Y, KALRA M K, et al. Low-dose CT with a residual encoder-decoder convolutional neural network[J]. IEEE Transactions on Medical Imaging, 2017, 36(12): 2524-2535. 10.1109/tmi.2017.2715284 |
11 | WU D F, KIM K, FAKHRI G EL, et al. A cascaded convolutional neural network for X-ray low-dose CT image denoising[EB/OL]. (2017-08-28) [2021-04-20].. |
12 | RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer, 2015: 234-241. |
13 | LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944. 10.1109/cvpr.2017.106 |
14 | YANG Q S, YAN P K, KALRA M K, et al. CT image denoising with perceptive deep neural networks[EB/OL]. (2017-02-22) [2021-04-20].. 10.1007/978-3-030-13969-8_14 |
15 | LIU H Y, JIANG B, SONG Y B, et al. Rethinking image inpainting via a mutual encoder-decoder with feature equalizations[C]// Proceedings of the 2020 European Conference on Computer Vision, LNCS 12347. Cham: Springer, 2020: 725-741. |
16 | GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 2672-2680. |
17 | WOLTERINK J M, LEINER T, VIERGEVER M A, et al. Generative adversarial networks for noise reduction in low-dose CT[J]. IEEE Transactions on Medical Imaging, 2017, 36(12):2536-2545. 10.1109/tmi.2017.2708987 |
18 | YI X, BABYN P. Sharpness-aware low-dose CT denoising using conditional generative adversarial network[J]. Journal of Digital Imaging, 2018, 31(5): 655-669. 10.1007/s10278-018-0056-0 |
19 | DENTON E, CHINTALA S, SZLAM A, et al. Deep generative image models using a Laplacian pyramid of adversarial networks[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2015: 1486-1494. |
20 | ZHANG H, XU T, LI H S, et al. StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 5908-5916. 10.1109/iccv.2017.629 |
21 | LI M, HSU W, XIE X D, et al. SACNN: self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network[J]. IEEE Transactions on Medical Imaging, 2020, 39(7):2289-2301. 10.1109/tmi.2020.2968472 |
22 | ISOLA P, ZHU J Y, ZHOU T H, et al. Image-to-image translation with conditional adversarial networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5967-5976. 10.1109/cvpr.2017.632 |
23 | YANG L, SHANGGUAN H, ZHANG X, et al. High-frequency sensitive generative adversarial network for low-dose CT image denoising[J]. IEEE Access, 2020, 8: 930-943. 10.1109/access.2019.2961983 |
24 | HUANG X S, LI S Z, WANG Y S. Jensen-Shannon boosting learning for object recognition[C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005: 144-149. |
25 | ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[EB/OL]. (2017-12-06) [2021-04-20].. |
26 | YANG Q S, YAN P K, ZHANG Y B, et al. Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss[J]. IEEE Transactions on Medical Imaging, 2018, 37(6): 1348-1357. 10.1109/tmi.2018.2827462 |
27 | LI X L, YE C, YAN Y J, et al. Low-dose CT image denoising based on improved WGAN-gp[J]. Journal of New Media, 2019, 1(2): 75-85. 10.32604/jnm.2019.06259 |
28 | GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of Wasserstein GANs[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017: 5769-5779. |
29 | MAO X D, LI Q, XIE H R, et al. Least squares generative adversarial networks[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2813-2821. 10.1109/iccv.2017.304 |
30 | PARK H S, BAEK J, YOU S K, et al. Unpaired image denoising using a generative adversarial network in X-ray CT[J]. IEEE Access, 2019, 7:110414-110425. 10.1109/access.2019.2934178 |
31 | American Association of Physicists in Medicine. Low dose CT grand challenge[DS/OL]. [2021-04-20].. 10.1118/1.4957556 |
32 | THOMAS L, SLOVIS M D. The ALARA (as low as reasonably achievable) concept in pediatric CT intelligent dose reduction[J]. Pediatric Radiology, 2002, 32(4): 219-220. |
33 | KANDE N A, DAKHANE R, DUKKIPATI A, et al. SiameseGAN: a generative model for denoising of spectral domain optical coherence tomography images[J]. IEEE Transactions on Medical Imaging, 2021, 40(1): 180-192. 10.1109/tmi.2020.3024097 |
34 | YAO S S, LIN W S, OOG E P, et al. Contrast signal-to-noise ratio for image quality assessment[C]// Proceedings of the 2005 IEEE International Conference on Image Processing. Piscataway: IEEE, 2005: 1529771. 10.1109/icip.2005.1529771 |
35 | WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. 10.1109/tip.2003.819861 |
36 | SHEIKH H R, BOVIK A C. Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15(2): 430-444. 10.1109/tip.2005.859378 |
37 | SHEIKH H R, BOVIK A C, DE VECIANA G. An information fidelity criterion for image quality assessment using natural scene statistics[J]. IEEE Transactions on Image Processing, 2005, 14(12): 2117-2128. 10.1109/tip.2005.859389 |
38 | KINGMA D P, BA J L. Adam: a method for stochastic optimization[EB/OL]. (2017-01-30) [2021-04-20].. |
[1] | Haiqi WANG, Zhihai WANG, Liuke LI, Haoran KONG, Qiong WANG, Jianbo XU. Spatial-temporal prediction model of urban short-term traffic flow based on grid division [J]. Journal of Computer Applications, 2022, 42(7): 2274-2280. |
[2] | Wenjun FAN, Shuguang ZHAO, Lizheng GUO. Ship detection algorithm based on improved RetinaNet [J]. Journal of Computer Applications, 2022, 42(7): 2248-2255. |
[3] | Wentao MAO, Guifang WU, Chao WU, Zhi DOU. Animation video generation model based on Chinese impressionistic style transfer [J]. Journal of Computer Applications, 2022, 42(7): 2162-2169. |
[4] | Tingwei QIN, Pengcheng ZHAO, Pinle QIN, Jianchao ZENG, Rui CHAI, Yongqi HUANG. Point cloud registration algorithm based on residual attention mechanism [J]. Journal of Computer Applications, 2022, 42(7): 2184-2191. |
[5] | Yayao ZUO, Haoyu CHEN, Zhiran CHEN, Jiawei HONG, Kun CHEN. Named entity recognition method combining multiple semantic features [J]. Journal of Computer Applications, 2022, 42(7): 2001-2008. |
[6] | Cheng HUANG, Qianrui ZHAO. Sensitive information detection method based on attention mechanism-based ELMo [J]. Journal of Computer Applications, 2022, 42(7): 2009-2014. |
[7] | Xiaohan LI, Jun WANG, Huading JIA, Liu XIAO. Stock market volatility prediction method based on graph neural network with multi-attention mechanism [J]. Journal of Computer Applications, 2022, 42(7): 2265-2273. |
[8] | Bo LIU, Linbo QING, Zhengyong WANG, Mei LIU, Xue JIANG. Group activity recognition based on partitioned attention mechanism and interactive position relationship [J]. Journal of Computer Applications, 2022, 42(7): 2052-2057. |
[9] | Wanjun LIU, Jiaming WANG, Haicheng QU, Libing DONG, Xinyu CAO. Music genre classification algorithm based on attention spectral-spatial feature [J]. Journal of Computer Applications, 2022, 42(7): 2072-2077. |
[10] | Jia LI, Yuanlin ZHENG, Kaiyang LIAO, Haojie LOU, Shiyu LI, Zehao CHEN. No-reference image quality assessment algorithm based on saliency deep features [J]. Journal of Computer Applications, 2022, 42(6): 1957-1964. |
[11] | Yang ZHANG, Jiangbo HAO. Malicious code detection method based on attention mechanism and residual network [J]. Journal of Computer Applications, 2022, 42(6): 1708-1715. |
[12] | Shan SU, Yang ZHANG, Dongwen ZHANG. Coupling related code smell detection method based on deep learning [J]. Journal of Computer Applications, 2022, 42(6): 1702-1707. |
[13] | Jiafan ZHOU, Yuefeng DU, Baoyan SONG, Xiaoguang LI, Azhu ZHAO, Xujie XIAO. MOOC video recommendation method based on meta-path attention mechanism [J]. Journal of Computer Applications, 2022, 42(6): 1808-1813. |
[14] | Hexuan HU, Huachao SUI, Qiang HU, Ye ZHANG, Zhenyun HU, Nengwu MA. Runoff forecast model based on graph attention network and dual-stage attention mechanism [J]. Journal of Computer Applications, 2022, 42(5): 1607-1615. |
[15] | Xianfeng YANG, Jiahe ZHAO, Ziqiang LI. Text classification model combining word annotations [J]. Journal of Computer Applications, 2022, 42(5): 1317-1323. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||