{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:13:14Z","timestamp":1768093994751,"version":"3.49.0"},"reference-count":45,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T00:00:00Z","timestamp":1610496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Kewen Xia","award":["U1813222"],"award-info":[{"award-number":["U1813222"]}]},{"name":"Kewen Xia","award":["18JCYBJC16500"],"award-info":[{"award-number":["18JCYBJC16500"]}]},{"name":"Baokai Zu","award":["Q6025001202001"],"award-info":[{"award-number":["Q6025001202001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The use of low-dose computed tomography (LDCT) in medical practice can effectively reduce the radiation risk of patients, but it may increase noise and artefacts, which can compromise diagnostic information. The methods based on deep learning can effectively improve image quality, but most of them use a training set of aligned image pairs, which are difficult to obtain in practice. In order to solve this problem, on the basis of the Wasserstein generative adversarial network (GAN) framework, we propose a generative adversarial network combining multi-perceptual loss and fidelity loss. Multi-perceptual loss uses the high-level semantic features of the image to achieve the purpose of noise suppression by minimizing the difference between the LDCT image and the normal-dose computed tomography (NDCT) image in the feature space. In addition, L2 loss is used to calculate the loss between the generated image and the original image to constrain the difference between the denoised image and the original image, so as to ensure that the image generated by the network using the unpaired images is not distorted. Experiments show that the proposed method performs comparably to the current deep learning methods which utilize paired image for image denoising.<\/jats:p>","DOI":"10.3390\/sym13010126","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T21:50:54Z","timestamp":1610574654000},"page":"126","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Unpaired Image Denoising via Wasserstein GAN in Low-Dose CT Image with Multi-Perceptual Loss and Fidelity Loss"],"prefix":"10.3390","volume":"13","author":[{"given":"Zhixian","family":"Yin","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China"}]},{"given":"Kewen","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China"}]},{"given":"Ziping","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China"}]},{"given":"Jiangnan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China"}]},{"given":"Sijie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China"}]},{"given":"Baokai","family":"Zu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0140-6736(04)15433-0","article-title":"Risk of cancer from diagnostic X-rays: Estimates for the UK and 14 other countries","volume":"363","author":"Darby","year":"2004","journal-title":"Lancet"},{"key":"ref_2","first-page":"1","article-title":"Radiation and the Risk of Cancer","volume":"3","author":"Bindman","year":"2015","journal-title":"Curr. Radiol. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1148\/radiology.175.3.2343122","article-title":"Low-dose CT of the lungs: Preliminary observations","volume":"175","author":"Naidich","year":"1990","journal-title":"Radiology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/s12194-012-0179-9","article-title":"Photon starvation artifacts of X-ray CT: Their true cause and a solution","volume":"6","author":"Mori","year":"2013","journal-title":"Radiol. Phys. Technol."},{"key":"ref_5","first-page":"53","article-title":"Signal statistics in x-ray computed tomography","volume":"4682","author":"Whiting","year":"2002","journal-title":"Proc. SPIE Int. Soc. Opt. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1109\/TMI.2006.882141","article-title":"Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography","volume":"25","author":"Wang","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.1118\/1.598410","article-title":"Adaptive streak artifact reduction in computed tomography resulting from excessive x-ray photon noise","volume":"25","author":"Hsieh","year":"1998","journal-title":"Med. Phys."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Demirkaya, O. (2001). Reduction of noise and image artifacts in computed tomography by nonlinear filtration of projection images. Proc. SPIE, 4322.","DOI":"10.1117\/12.430964"},{"key":"ref_9","first-page":"691329","article-title":"Sinogram smoothing with bilateral filtering for low-dose CT","volume":"6913","author":"Yu","year":"2008","journal-title":"Proc. SPIE Int. Soc. Opt. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1016\/j.ijleo.2013.10.005","article-title":"The adaptive sinogram restoration algorithm based on anisotropic diffusion by energy minimization for low-dose X-ray CT","volume":"125","author":"Cui","year":"2014","journal-title":"Optik-Int. J. Light Electron Opt."},{"key":"ref_11","first-page":"319","article-title":"Image reconstruction from finite numbers of projections","volume":"6","author":"Smith","year":"2001","journal-title":"J. Phys. A Math. Nucl. Gen."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4911","DOI":"10.1118\/1.3232004","article-title":"Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT","volume":"36","author":"Manduca","year":"2009","journal-title":"Med. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ejmp.2012.01.003","article-title":"Iterative reconstruction methods in X-ray CT","volume":"28","author":"Beister","year":"2012","journal-title":"Phys. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4777","DOI":"10.1088\/0031-9155\/53\/17\/021","article-title":"Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization","volume":"53","author":"Sidky","year":"2008","journal-title":"Phys. Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/j.compmedimag.2008.12.007","article-title":"Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior","volume":"33","author":"Chen","year":"2009","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2811","DOI":"10.1016\/j.ijleo.2012.08.045","article-title":"Bayesian sinogram smoothing with an anisotropic diffusion weighted prior for low-dose X-ray computed tomography","volume":"124","author":"Zhang","year":"2013","journal-title":"Opt. Int. J. Light Electron. Opt."},{"key":"ref_17","first-page":"190","article-title":"Research of Tongue Image Denoising Based on Partial Differential Equation","volume":"38","author":"Tang","year":"2012","journal-title":"Comput. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1364\/BOE.7.001015","article-title":"Statistical iterative reconstruction using adaptive fractional order regularization","volume":"7","author":"Zhang","year":"2016","journal-title":"Biomed. Opt. Express"},{"key":"ref_19","first-page":"745","article-title":"Sparse-View X-ray Computed Tomography Reconstruction via Mumford-Shah Total Variation Regularization","volume":"9227","author":"Chen","year":"2015","journal-title":"Int. Conf. Intell. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1109\/23.775593","article-title":"Attenuation correction for PET using count-limited transmission images reconstructed with median root prior","volume":"46","author":"Alenius","year":"1999","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_21","first-page":"e264","article-title":"Assessment of prior image induced nonlocal means regularization for low-dose CT reconstruction: Change in anatomy","volume":"44","author":"Zhan","year":"2017","journal-title":"Med. Phys."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1950017","DOI":"10.1142\/S0219467819500177","article-title":"Low-Dose CT Image Restoration Based on Adaptive Prior Feature Matching and Nonlocal Means","volume":"19","author":"Cheng","year":"2019","journal-title":"Int. J. Image Graph."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.neucom.2016.01.090","article-title":"Low-dose cerebral perfusion computed tomography image restoration via low-rank and total variation regularizations","volume":"197","author":"Niu","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"116859","DOI":"10.1109\/ACCESS.2019.2932754","article-title":"Low-Dose CT Image Denoising Model Based on Sparse Representation by Stationarily Classified Sub-Dictionaries","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/TRPMS.2018.2810221","article-title":"Denoising Low-Dose CT Images Using Multiframe Blind Source Separation and Block Matching Filter","volume":"2","author":"Hasan","year":"2018","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, H., Zhang, Y., Zhang, W., Liao, P., and Wang, G. (2017, January 18\u201321). Low-dose CT denoising with convolutional neural network. Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging, Melbourne, Sydney.","DOI":"10.1109\/ISBI.2017.7950488"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1109\/TMI.2017.2715284","article-title":"Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network","volume":"36","author":"Chen","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e360","DOI":"10.1002\/mp.12344","article-title":"A deep convolutional neural network using directional wavelets for low\u2010dose X\u2010ray CT reconstruction","volume":"44","author":"Kang","year":"2017","journal-title":"Med. Phys."},{"key":"ref_30","unstructured":"Kang, E., Min, J., and Ye, J. (2017). Wavelet Domain Residual Network (WavResNet) for Low-Dose X-ray CT Reconstruction. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1137\/17M1141771","article-title":"Deep convolutional framelets: A general deep learning framework for inverse problems","volume":"11","author":"Ye","year":"2018","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110414","DOI":"10.1109\/ACCESS.2019.2934178","article-title":"Unpaired image denoising using a generative adversarial network in X-ray CT","volume":"7","author":"Park","year":"2019","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/TMI.2018.2827462","article-title":"Low-Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss","volume":"37","author":"Yang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_34","first-page":"1","article-title":"Unpaired Low-Dose CT Denoising Network Based on Cycle-Consistent Generative Adversarial Network with Prior Image Information","volume":"2019","author":"Tang","year":"2019","journal-title":"Comput. Math. Methods Med."},{"key":"ref_35","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein GAN. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/07069938X","article-title":"The \u221e-Wasserstein Distance: Local Solutions and Existence of Optimal Transport Maps","volume":"40","author":"Champion","year":"2008","journal-title":"SIAM J. Math. Anal."},{"key":"ref_37","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017). Improved Training of Wasserstein GANs. arXiv."},{"key":"ref_38","first-page":"2672","article-title":"Generative Adversarial Nets","volume":"3","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zuo, W., Gu, S., and Zhang, L. (2017, January 21). Learning Deep CNN Denoiser Prior for Image Restoration. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.300"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Mahendran, A., and Vedaldi, A. (2015, January 7\u201312). Understanding deep image representations by inverting them. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref_42","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Li, F. (2016, January 11\u201314). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref_44","unstructured":"Gholizadeh-Ansari, M., Alirezaie, J., and Babyn, P. (2019). Deep Learning for Low-Dose CT Denoising. arXiv."},{"key":"ref_45","first-page":"1662","article-title":"Noise properties of low-dose CT projections and noise treatment by scale transformations","volume":"3","author":"Lu","year":"2001","journal-title":"Nucl. Sci. Symp. Conf. Rec."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/1\/126\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:10:40Z","timestamp":1760159440000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/1\/126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,13]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["sym13010126"],"URL":"https:\/\/doi.org\/10.3390\/sym13010126","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,13]]}}}