Low-dose CT denoising model based on dual encoder-decoder generative adversarial network

doi:10.11772/j.issn.1001-9081.2024010039

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (2): 624-632.DOI: 10.11772/j.issn.1001-9081.2024010039

• Multimedia computing and computer simulation • Previous Articles

Low-dose CT denoising model based on dual encoder-decoder generative adversarial network

Hong SHANGGUAN¹^,²(), Huiying REN¹, Xiong ZHANG¹, Xinglong HAN¹, Zhiguo GUI², Yanling WANG²^,³

^1.School of Electronic Information Engineering，Taiyuan University of Science and Technology，Taiyuan Shanxi 030024，China
^2.State Key Laboratory of Dynamic Measurement Technology （North University of China），Taiyuan Shanxi 030051，China
^3.School of Information，Shanxi University of Finance and Economics，Taiyuan Shanxi 030006，China

Received:2024-01-16 Revised:2024-04-13 Accepted:2024-04-15 Online:2024-05-09 Published:2025-02-10
Contact: Hong SHANGGUAN
About author:REN Huiying， born in 1998， M. S. candidate. Her research interests include medical image processing， deep learning.
ZHANG Xiong， born in 1973， M. S.， professor. His research interests include pattern recognition， medical image processing， video target tracking.
HAN Xinglong， born in 1995， M. S. His research interests include medical image processing， deep learning.
GUI Zhiguo， born in 1972， Ph. D.， professor. His research interests include image processing， image reconstruction.
WANG Yanling， born in 1981， Ph. D.， lecturer. Her research interests include image processing， data analysis.
Supported by:
National Natural Science Foundation of China(62001321);Fundamental Research Program of Shanxi Province(202103021224265);Graduate Education Innovation Project of Taiyuan University of Science and Technology(SY2022015)

基于双编码器双解码器GAN的低剂量CT降噪模型

上官宏¹^,²(), 任慧莹¹, 张雄¹, 韩兴隆¹, 桂志国², 王燕玲²^,³

^1.太原科技大学电子信息工程学院，太原 030024
^2.动态测试技术省部共建国家重点实验室（中北大学），太原 030051
^3.山西财经大学信息学院，太原 030006

通讯作者: 上官宏
作者简介:任慧莹（1998—），女，黑龙江齐齐哈尔人，硕士研究生，主要研究方向：医学图像处理、深度学习
张雄（1973—），男，山西神池人，教授，硕士，主要研究方向：模式识别、医学图像处理、视频目标跟踪
韩兴隆（1995—），男，河南禹州人，硕士，主要研究方向：医学图像处理、深度学习
桂志国（1972—），男，天津蓟州人，教授，博士，主要研究方向：图像处理、图像重建
王燕玲（1981—），女，山西吕梁人，讲师，博士，主要研究方向：图像处理、数据分析。
基金资助:
国家自然科学基金资助项目(62001321);山西省基础研究计划项目(202103021224265);太原科技大学研究生教育创新项目(SY2022015)

Abstract

Abstract:

In recent years， Generative Adversarial Network （GAN） used for Low-Dose Computed Tomography （LDCT） image denoising has shown significant performance advantages， becoming a hot topic in the field. However， the insufficient perception ability of GAN generator for the noise and artifact distribution in LDCT images leads to limit the denoising performance. To address this issue， an LDCT denoising model based on a Dual Encoder-Decoder GAN （DualED-GAN） was proposed. Firstly， a pair of encoder-decoder was proposed to form an artifact pixel-level feature extraction channel for estimating the artifact noise in LDCT images. Secondly， another pair of encoder-decoder was proposed to form an artifact mask information extraction channel for estimating the intensity and location information of artifacts. Finally， the artifact image quality label maps were used to assist in estimating the mask information of artifacts， so that supplementary features were provided for the artifact pixel-level feature extraction channel， thereby enhancing the sensitivity of the GAN denoising network to the distribution intensity of artifact noise. Experimental results show that compared with the sub-optimal model DESD-GAN（Dual-Encoder-Single-Decoder based Generative Adversarial Network）， the proposed model increases the average Peak Signal-to-Noise Ratio （PSNR） by 0.338 7 dB， and the average Structural Similarity Index Measure （SSIM） by 0.002 8 on mayo test set. It can be seen that the proposed model performs better in all terms of artifact suppression， structural preservation， and model robustness.

Key words: Low-Dose Computed Tomography (LDCT), Generative Adversarial Network (GAN), encoder, decoder, denoising

摘要：

近年来，生成对抗网络（GAN）用于低剂量计算机断层成像（LDCT）图像降噪已经表现出显著的性能优势，成为该领域的研究热点。然而，GAN的生成器对LDCT图像中噪声和伪影分布的感知能力不足，导致网络的降噪性能受限。因此，提出一种基于双编码器双解码器生成对抗网络（DualED-GAN）的低剂量CT降噪模型。首先，提出由一对编解码器构成伪影像素级特征提取通道，用于估计LDCT中的伪影噪声；其次，提出由另外一对编解码器构成伪影掩码信息提取通道，用于估计伪影的强度和位置信息；最后，采用伪影图像质量标签图辅助估计伪影的掩码信息，可以为伪影像素级特征提取通道提供补充特征，进而提高GAN降噪网络对伪影噪声分布强度的敏感性。实验结果表明，在mayo测试集上与次优模型DESD-GAN（Dual-Encoder-Single-Decoder based Generative Adversarial Network）相比，所提模型的平均峰值信噪比（PSNR）提高了0.338 7 dB，平均结构相似性度（SSIM）提高了0.002 8。可见，所提模型在伪影抑制、结构保留与模型鲁棒性方面均有更好的表现。

关键词: 低剂量计算机断层成像, 生成对抗网络, 编码器, 解码器, 降噪

CLC Number:

TP391.41

Hong SHANGGUAN, Huiying REN, Xiong ZHANG, Xinglong HAN, Zhiguo GUI, Yanling WANG. Low-dose CT denoising model based on dual encoder-decoder generative adversarial network[J]. Journal of Computer Applications, 2025, 45(2): 624-632.

上官宏, 任慧莹, 张雄, 韩兴隆, 桂志国, 王燕玲. 基于双编码器双解码器GAN的低剂量CT降噪模型[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 624-632.

Figures/Tables 11

References 33

1	韩泽芳，上官宏，张雄，等. 基于深度学习的低剂量CT成像算法研究进展［J］. CT理论与应用研究， 2022， 31（1）： 117-134.
	HAN Z F， SHANGGUAN H， ZHANG X， et al. Advances in research on low-dose CT imaging algorithm based on deep learning［J］. Computerized Tomography Theory and Applications， 2022， 31（1）： 117-134.
2	NAIDICH D P， MARSHALL C H， GRIBBIN C， et al. Low-dose CT of the lungs： preliminary observations［J］. Radiology， 1990， 175（3）： 729-731.
3	张权. 低剂量X线CT重建若干问题研究［D］. 南京：东南大学， 2015：11-12.
	ZHANG Q. A study on some problems in image reconstruction for low-dose CT system［D］. Nanjing： Southeast University， 2015： 11-12.
4	CHEN Y， SHI L， FENG Q， et al. Artifact suppressed dictionary learning for low-dose CT image processing［J］. IEEE Transactions on Medical Imaging， 2014， 33（12）： 2271-2292.
5	CHEN H， ZHANG Y， KALRA M K， et al. Low-dose CT with a Residual Encoder-Decoder Convolutional Neural Network （RED-CNN）［J］. IEEE Transactions on Medical Imaging， 2017， 36（12）： 2524-2535.
6	CHEN M， PU Y F， BAI Y C. Low-dose CT image denoising using residual convolutional network with fractional TV loss［J］. Neurocomputing， 2021， 452： 510-520.
7	郝文强，崔学英，郭映亭. 基于Transformer和CNN的低剂量CT图像去噪网络［J］. 海南师范大学学报（自然科学版）， 2023， 36（2）： 176-182.
	HAO W Q， CUI X Y， GUO Y T. Low-dose CT image denoising network based on Transformer and CNN［J］. Journal of Hainan Normal University （Natural Science）， 2023， 36（2）： 176-182.
8	WEI Y， ZHANG Z， ZHANG H， et al. A coarse-to-fine multi-stream hybrid deraining network for single image deraining［C］// Proceedings of the 2019 IEEE International Conference on Data Mining. Piscataway： IEEE， 2019： 628-637.
9	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	HAN Z， SHANGGUAN H， ZHANG X， et al. A dual-encoder-single-decoder based low-dose CT denoising network［J］. IEEE Journal of Biomedical and Health Informatics， 2022， 26（7）： 3251-3260.
11	YASARLA R， PATEL V M. Confidence measure guided single image de-raining［J］. IEEE Transactions on Image Processing， 2020， 29： 4544-4555.
12	JIAO F， GUI Z， LIU Y， et al. Low-dose CT image denoising via frequency division and encoder-dual decoder GAN［J］. Signal， Image and Video Processing， 2021， 15（8）： 1907-1915.
13	韩静. 医学诊疗任务导向的低剂量CT图像伪影抑制研究［D］. 太原：太原科技大学， 2023：4-5.
	HAN J. Research on medical diagnosis and treatment task oriented low dose CT image artifact suppression［D］. Taiyuan： Taiyuan University of Science and Technology， 2023： 4-5.
14	ZHANG H， PATEL V M. Density-aware single image de-raining using a multi-stream dense network［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 695-704.
15	HU X， FU C W， ZHU L， et al. Depth-attentional features for single-image rain removal［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 8014-8023.
16	GUO S， YAN Z， ZHANG K， et al. Toward convolutional blind denoising of real photographs［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 1712-1722.
17	WANG Y， GONG D， YANG J， et al. An effective two-branch model-based deep network for single image deraining［EB/OL］. ［2023-05-14］..
18	WANG Y， ZHANG H， LIU Y， et al. Gradient information guided deraining with a novel network and adversarial training［EB/OL］. ［2023-10-09］..
19	HEINRICH M P， STILLE M， BUZUG T M. Residual U-net convolutional neural network architecture for low-dose CT denoising［J］. Current Directions in Biomedical Engineering， 2018， 4（1）： 297-300.
20	韩兴隆. 低剂量CT图像伪影抑制的编解码特征提取网络研究［D］. 太原：太原科技大学， 2022：31-32.
	HAN X L. Research on encoder-decoder feature extraction network for low-dose CT［D］. Taiyuan： Taiyuan University of Science and Technology， 2022： 31-32.
21	ISOLA P， ZHU J Y， ZHOU T， 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： 1125-1134.
22	WU L， ZHANG X， CHEN H， et al. VP-NIQE： an opinion-unaware visual perception natural image quality evaluator［J］. Neurocomputing， 2021， 463： 17-28.
23	American Association of Physicists in Medicine. Low dose CT grand challenge［DS/OL］. ［2023-04-20］..
24	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.
25	WANG D， WU Z， YU H. TED-Net： convolution-free T2T vision transformer-based encoder-decoder dilation network for low-dose CT denoising［C］// Proceedings of the 2021 International Workshop on Machine Learning in Medical Imaging， LNCS 12966. Cham： Springer， 2021： 416-425.
26	CHEN Z， HE Z， LU Z M. DEA-Net： single image dehazing based on detail-enhanced convolution and content-guided attention［J］. IEEE Transactions on Image Processing， 2024， 33： 1002-1015.
27	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.
28	HAN Z， SHANGGUAN H， ZHANG X， et al. A coarse-to-fine multi-scale feature hybrid low-dose CT denoising network［J］. Signal Processing： Image Communication， 2023， 118： No.117009.
29	CHEN C， CARLSON D， GAN Z， et al. Bridging the gap between stochastic gradient MCMC and stochastic optimization［C］// Proceedings of the 19th International Conference on Artificial Intelligence and Statistics. New York： JMLR.org， 2016： 1051-1060.
30	YAO S， LIN W， ONG E， et al. Contrast signal-to-noise ratio for image quality assessment［C］// Proceedings of the 2005 IEEE International Conference on Image Processing — Volume 1. Piscataway： IEEE， 2005： 397-401.
31	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.
32	HAN Y， CAI Y， CAO Y， et al. A new image fusion performance metric based on visual information fidelity［J］. Information Fusion， 2013， 14（2）： 127-135.
33	BAUER E， KOHAVI R. An empirical comparison of voting classification algorithms： Bagging， boosting， and variants［J］. Machine Learning， 1999， 36（1/2）： 105-139.

实验序号	方法	生成器								PSNR/dB↑
		Enc1-Dec1		Enc2-Dec2		双通道交互关系
		编码器	解码器	编码器	解码器	双通道交互关系
		EFAL	DFEL	RCD	RDC	E_U→ E_D	E_U→ D_D	E_D→ D_U	D_D→ D_U
1	O_SESD	√	√							31.373 1±1.752 9
	O_SEDD	√	√		√		√			31.454 0±1.745 2
	O_DESD	√	√	√				√		31.399 9±1.748 2
	DualED-GAN	√	√	√	√		√	√		31.473 6±1.749 1
2	O_nocon	√	√	√	√					30.747 2±1.757 1
	O_UEDE	√	√	√	√	√				31.066 2±1.751 2
	O_UEDD	√	√	√	√		√			31.001 2±1.749 1
	O_DEUD	√	√	√	√			√		31.125 9±1.749 5
	O_DDUD	√	√	√	√				√	31.002 9±1.751 1
3	O₀	0	0	0	0		√	√		30.855 7±1.798 2
	O₁	1	1	1	1		√	√		31.124 1±1.774 0
	O₂	2	2	2	2		√	√		31.136 8±1.775 9
	DualED-GAN	3	3	3	3		√	√		31.142 4±1.758 7

实验序号	方法	生成器								PSNR/dB↑
		Enc1-Dec1		Enc2-Dec2		双通道交互关系
		编码器	解码器	编码器	解码器	双通道交互关系
		EFAL	DFEL	RCD	RDC	E_U→ E_D	E_U→ D_D	E_D→ D_U	D_D→ D_U
1	O_SESD	√	√							31.373 1±1.752 9
	O_SEDD	√	√		√		√			31.454 0±1.745 2
	O_DESD	√	√	√				√		31.399 9±1.748 2
	DualED-GAN	√	√	√	√		√	√		31.473 6±1.749 1
2	O_nocon	√	√	√	√					30.747 2±1.757 1
	O_UEDE	√	√	√	√	√				31.066 2±1.751 2
	O_UEDD	√	√	√	√		√			31.001 2±1.749 1
	O_DEUD	√	√	√	√			√		31.125 9±1.749 5
	O_DDUD	√	√	√	√				√	31.002 9±1.751 1
3	O₀	0	0	0	0		√	√		30.855 7±1.798 2
	O₁	1	1	1	1		√	√		31.124 1±1.774 0
	O₂	2	2	2	2		√	√		31.136 8±1.775 9
	DualED-GAN	3	3	3	3		√	√		31.142 4±1.758 7

降噪模型	PSNR/dB↑	SSIM↑	VIF↑	MSE↓	NIQE↓
BM3D^［24］	27.336 4±2.273 4	0.727 4±0.047 4	0.272 2±0.035 9	138.420 0±81.800 0	6.501 8±1.046 0
pix2pix^［21］	28.318 3±1.659 9	0.811 1±0.054 5	0.334 2±0.054 3	102.726 5±37.389 9	4.763 8±0.960 0
RED-CNN^［5］	30.511 4±1.764 7	0.866 0±0.041 8	0.390 2±0.055 9	62.861 3±26.771 1	5.038 4±0.871 3
TED-Net^［25］	31.080 1±1.758 5	0.844 2±0.042 2	0.403 9±0.058 5	54.992 6±22.387 7	4.382 3±1.092 1
HFSGAN^［27］	30.081 8±0.044 5	0.852 7±1.588 9	0.373 3±0.052 7	68.187 0±24.996 2	5.257 1±0.855 3
SEDD-GAN^［12］	30.838 6±1.509 8	0.870 6±0.038 3	0.400 8±0.049 4	57.023 6±20.787 4	5.091 4±1.132 4
DESD-GAN^［10］	31.134 9±1.899 1	0.873 8±0.042 0	0.418 6±0.057 6	55.260 2±26.157 1	5.026 8±0.961 6
CMFHGAN^［27］	30.891 7±2.281 4	0.872 7±0.042 8	0.485 7±0.052 1	63.802 9±51.636 6	4.924 9±0.976 2
DEA-Net^［28］	30.983 6±1.698 6	0.859 1±0.045 7	0.458 9±0.054 9	55.904 1±21.784 1	4.424 5±1.006 1
DualED-GAN	31.473 6±1.749 1	0.876 6±0.041 2	0.426 0±0.059 0	50.154 2±20.056 8	4.842 1±0.988 9

降噪模型	PSNR/dB↑	SSIM↑	VIF↑	MSE↓	NIQE↓
BM3D^［24］	27.336 4±2.273 4	0.727 4±0.047 4	0.272 2±0.035 9	138.420 0±81.800 0	6.501 8±1.046 0
pix2pix^［21］	28.318 3±1.659 9	0.811 1±0.054 5	0.334 2±0.054 3	102.726 5±37.389 9	4.763 8±0.960 0
RED-CNN^［5］	30.511 4±1.764 7	0.866 0±0.041 8	0.390 2±0.055 9	62.861 3±26.771 1	5.038 4±0.871 3
TED-Net^［25］	31.080 1±1.758 5	0.844 2±0.042 2	0.403 9±0.058 5	54.992 6±22.387 7	4.382 3±1.092 1
HFSGAN^［27］	30.081 8±0.044 5	0.852 7±1.588 9	0.373 3±0.052 7	68.187 0±24.996 2	5.257 1±0.855 3
SEDD-GAN^［12］	30.838 6±1.509 8	0.870 6±0.038 3	0.400 8±0.049 4	57.023 6±20.787 4	5.091 4±1.132 4
DESD-GAN^［10］	31.134 9±1.899 1	0.873 8±0.042 0	0.418 6±0.057 6	55.260 2±26.157 1	5.026 8±0.961 6
CMFHGAN^［27］	30.891 7±2.281 4	0.872 7±0.042 8	0.485 7±0.052 1	63.802 9±51.636 6	4.924 9±0.976 2
DEA-Net^［28］	30.983 6±1.698 6	0.859 1±0.045 7	0.458 9±0.054 9	55.904 1±21.784 1	4.424 5±1.006 1
DualED-GAN	31.473 6±1.749 1	0.876 6±0.041 2	0.426 0±0.059 0	50.154 2±20.056 8	4.842 1±0.988 9

[1]	Xin LIU, Dawei YANG, Changheng SHAO, Haiwen WANG, Mingjiang PANG, Yanru LI. Hierarchical multi-label classification model for public complaints with long-tailed distribution [J]. Journal of Computer Applications, 2025, 45(1): 82-89.
[2]	Zhigang XU, Chuang ZHANG. Multi-level color restoration of mural image based on gated positional encoding [J]. Journal of Computer Applications, 2024, 44(9): 2931-2937.
[3]	Yuwei DING, Hongbo SHI, Jie LI, Min LIANG. Image denoising network based on local and global feature decoupling [J]. Journal of Computer Applications, 2024, 44(8): 2571-2579.
[4]	Kaili DENG, Weibo WEI, Zhenkuan PAN. Industrial defect detection method with improved masked autoencoder [J]. Journal of Computer Applications, 2024, 44(8): 2595-2603.
[5]	Chenqian LI, Jun LIU. Ultrasound carotid plaque segmentation method based on semi-supervision and multi-scale cascaded attention [J]. Journal of Computer Applications, 2024, 44(8): 2604-2610.
[6]	Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617.
[7]	Li LIU, Haijin HOU, Anhong WANG, Tao ZHANG. Generative data hiding algorithm based on multi-scale attention [J]. Journal of Computer Applications, 2024, 44(7): 2102-2109.
[8]	Junfeng SHEN, Xingchen ZHOU, Can TANG. Dual-channel sentiment analysis model based on improved prompt learning method [J]. Journal of Computer Applications, 2024, 44(6): 1796-1806.
[9]	Xun YAO, Zhongzheng QIN, Jie YANG. Generative label adversarial text classification model [J]. Journal of Computer Applications, 2024, 44(6): 1781-1785.
[10]	Haoran WANG, Dan YU, Yuli YANG, Yao MA, Yongle CHEN. Domain transfer intrusion detection method for unknown attacks on industrial control systems [J]. Journal of Computer Applications, 2024, 44(4): 1158-1165.
[11]	Zongyu LI, Siwei QIANG, Xiaobo GUO, Zhenfeng ZHU. Re-weighted adversarial variational autoencoder and its application in industrial causal effect estimation [J]. Journal of Computer Applications, 2024, 44(4): 1099-1106.
[12]	Weina DONG, Jia LIU, Xiaozhong PAN, Lifeng CHEN, Wenquan SUN. High-capacity robust image steganography scheme based on encoding-decoding network [J]. Journal of Computer Applications, 2024, 44(3): 772-779.
[13]	Yi ZHENG, Cunyi LIAO, Tianqian ZHANG, Ji WANG, Shouyin LIU. Image denoising-based cell-level RSRP estimation method for urban areas [J]. Journal of Computer Applications, 2024, 44(3): 855-862.
[14]	Ruifeng HOU, Pengcheng ZHANG, Liyuan ZHANG, Zhiguo GUI, Yi LIU, Haowen ZHANG, Shubin WANG. Iterative denoising network based on total variation regular term expansion [J]. Journal of Computer Applications, 2024, 44(3): 916-921.
[15]	Zhuo ZHANG, Huazhu CHEN. Deep subspace clustering based on multiscale self-representation learning with consistency and diversity [J]. Journal of Computer Applications, 2024, 44(2): 353-359.

Low-dose CT denoising model based on dual encoder-decoder generative adversarial network

基于双编码器双解码器GAN的低剂量CT降噪模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 33

Related Articles 15

Recommended Articles

Metrics