{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T11:25:07Z","timestamp":1777548307409,"version":"3.51.4"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Chronic liver disease (CLD) and subsequent liver cirrhosis (LC) are common causes of death and healthcare-related socio-economical costs worldwide. Ultrasound (US) is the first-line imaging modality for assessing the liver and associated hepatocellular carcinomas. Poor quality liver US images caused by aging or inadequate management of US equipment, can pose significant challenges in both diagnosis and treatment. From this perspective, the aim of this study was to enhance and assess the image quality of liver US obtained from an older, lower-performing device using a deep learning approach. A neural network based on a switchable cycle generative adversarial network (CycleGAN) was trained in an unsupervised learning setting, with low-quality images as inputs and high-quality images as targets. The study included consecutively acquired grey-scale liver US examinations from both a 12-year-old and a 4-year-old US device. Images from the older device served as inputs, while images from the newer device were used as targets for the deep learning-based algorithm. Image quality was evaluated by two experienced reviewers. The algorithm significantly improved the brightness, contrast, and overall quality of the reconstructed liver US images (p\u2009&lt;\u20090.001), as assessed by both reviewers. However, no significant differences in image resolution and reverberation artifacts were noted by one of the reviewers. The weighted kappa values for image quality and diagnostic performance ranged from 0.225 to 0.838, indicating fair to almost-perfect inter-reader agreement. The proposed algorithm effectively enhances low-quality liver US images to high diagnostic quality, thereby potentially supporting clinical assessment and intervention in patients with LC.<\/jats:p>","DOI":"10.1371\/journal.pone.0348137","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:43:57Z","timestamp":1777398237000},"page":"e0348137","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image quality improvement of liver ultrasound using unsupervised deep learning"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2126-0763","authenticated-orcid":true,"given":"Jaeyoung","family":"Huh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo Hyeok","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0780-7985","authenticated-orcid":true,"given":"Eun Sun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9566-7489","authenticated-orcid":true,"given":"Jeong Eun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Jeong","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung Ihn","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"pone.0348137.ref001","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.1016\/j.cgh.2019.07.060","article-title":"Contemporary epidemiology of chronic liver disease and cirrhosis","volume":"18","author":"AM Moon","year":"2020","journal-title":"Clin Gastroenterol Hepatol"},{"key":"pone.0348137.ref002","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1186\/s12916-014-0145-y","article-title":"Liver cirrhosis mortality in 187 countries between 1980 and 2010: a systematic analysis","volume":"12","author":"AA Mokdad","year":"2014","journal-title":"BMC Med"},{"issue":"1","key":"pone.0348137.ref003","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1002\/hep.29466","article-title":"Modeling the epidemic of nonalcoholic fatty liver disease demonstrates an exponential increase in burden of disease","volume":"67","author":"C Estes","year":"2018","journal-title":"Hepatology"},{"issue":"1","key":"pone.0348137.ref004","doi-asserted-by":"crossref","first-page":"5195","DOI":"10.1038\/s41598-021-84577-z","article-title":"The incidence trends of liver cirrhosis caused by nonalcoholic steatohepatitis via the GBD study 2017","volume":"11","author":"M Zhai","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0348137.ref005","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1186\/s12889-022-12867-w","article-title":"Global pattern of trends in incidence, mortality, and mortality-to-incidence ratio rates related to liver cancer, 1990\u20132019: a longitudinal analysis based on the global burden of disease study","volume":"22","author":"M Amini","year":"2022","journal-title":"BMC Public Health"},{"issue":"7","key":"pone.0348137.ref006","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.3348\/kjr.2019.0140","article-title":"2018 Korean Liver Cancer Association-National Cancer Center Korea practice guidelines for the management of hepatocellular carcinoma","volume":"20","author":"Korean Liver Cancer Association (KLCA), National Cancer Center (NCC), Goyang, Korea","year":"2019","journal-title":"Korean J Radiol"},{"issue":"2","key":"pone.0348137.ref007","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1002\/hep.29913","article-title":"Diagnosis, staging, and management of hepatocellular carcinoma: 2018 practice guidance by the American Association for the Study of Liver Diseases","volume":"68","author":"JA Marrero","year":"2018","journal-title":"Hepatology"},{"issue":"1","key":"pone.0348137.ref008","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.jhep.2018.03.019","article-title":"EASL Clinical Practice Guidelines: management of hepatocellular carcinoma","volume":"69","author":"European Association for the Study of the Liver","year":"2018","journal-title":"J Hepatol"},{"key":"pone.0348137.ref009","article-title":"Quality assurance for grey-scale imaging","author":"EL Madsen","year":"2000","journal-title":"Ultrasound Med Biol"},{"key":"pone.0348137.ref010","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.ejrad.2019.02.038","article-title":"The present and future of deep learning in radiology","volume":"114","author":"L Saba","year":"2019","journal-title":"Eur J Radiol"},{"issue":"6","key":"pone.0348137.ref011","doi-asserted-by":"crossref","first-page":"2086","DOI":"10.1109\/TUFFC.2021.3056197","article-title":"Variational formulation of unsupervised deep learning for ultrasound image artifact removal","volume":"68","author":"S Khan","year":"2021","journal-title":"IEEE Trans Ultrason Ferroelectr Freq Control"},{"issue":"2","key":"pone.0348137.ref012","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1002\/mp.13284","article-title":"Cycle-consistent adversarial denoising network for multiphase coronary CT angiography","volume":"46","author":"E Kang","year":"2019","journal-title":"Med Phys"},{"issue":"2","key":"pone.0348137.ref013","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2020190027","article-title":"Attention-aware discrimination for MR-to-CT image translation using cycle-consistent generative adversarial networks","volume":"2","author":"V Kearney","year":"2020","journal-title":"Radiol Artif Intell"},{"issue":"1","key":"pone.0348137.ref014","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1038\/s41598-020-80803-2","article-title":"Cone-beam CT image quality improvement using Cycle-Deblur consistent adversarial networks (Cycle-Deblur GAN) for chest CT imaging in breast cancer patients","volume":"11","author":"H-J Tien","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0348137.ref015","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1109\/ICCV.2017.244","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"J-Y Zhu","year":"2017","journal-title":"2017 IEEE International Conference on Computer Vision (ICCV). IEEE"},{"issue":"2","key":"pone.0348137.ref016","article-title":"Speckle noise reduction in ultrasound fetal images using edge preserving adaptive shock filters","volume":"12","author":"RE Pregitha","year":"2012","journal-title":"IJSRP"},{"key":"pone.0348137.ref017","first-page":"2454","article-title":"Liver ultrasound image enhancement using bilateral filter","volume":"8","author":"R Gautam","year":"2018","journal-title":"IJETR"},{"key":"pone.0348137.ref018","article-title":"A new approach in spatial filtering to reduce speckle noise","volume":"1","author":"MR Hoque","year":"2011","journal-title":"Int J Soft Comput Eng"},{"issue":"1","key":"pone.0348137.ref019","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0262291","article-title":"Quantitative ultrasound, elastography, and machine learning for assessment of steatosis, inflammation, and fibrosis in chronic liver disease","volume":"17","author":"F Destrempes","year":"2022","journal-title":"PLoS One"},{"key":"pone.0348137.ref020","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1159\/000122595","article-title":"Diagnostic accuracy of imaging for liver cirrhosis compared to histologically proven liver cirrhosis","volume":"51","author":"M Kudo","year":"2008","journal-title":"Intervirology"},{"issue":"4","key":"pone.0348137.ref021","doi-asserted-by":"crossref","first-page":"445","DOI":"10.11152\/mu-4080","article-title":"An overview of ultrasound-derived radiomics and deep learning in liver","volume":"25","author":"D Zhang","year":"2023","journal-title":"Med Ultrason"},{"key":"pone.0348137.ref022","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1007\/s00330-019-06407-1","article-title":"Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network","volume":"30","author":"JH Lee","year":"2020","journal-title":"Eur Radiol"},{"issue":"4","key":"pone.0348137.ref023","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.diii.2019.02.009","article-title":"Diagnosis of focal liver lesions from ultrasound using deep learning","volume":"100","author":"B Schmauch","year":"2019","journal-title":"Diagn Interv Imaging"},{"issue":"5","key":"pone.0348137.ref024","doi-asserted-by":"crossref","first-page":"2973","DOI":"10.1007\/s00330-019-06595-w","article-title":"Transfer learning radiomics based on multimodal ultrasound imaging for staging liver fibrosis","volume":"30","author":"L-Y Xue","year":"2020","journal-title":"Eur Radiol"},{"key":"pone.0348137.ref025","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.210110","article-title":"Deep learning for the detection, localization, and characterization of focal liver lesions on abdominal US images","volume":"4","author":"H Dadoun","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"pone.0348137.ref026","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.ejro.2015.05.002","article-title":"State-of-the-art imaging of liver fibrosis and cirrhosis: a comprehensive review of current applications and future perspectives","volume":"2","author":"A Huber","year":"2015","journal-title":"Eur J Radiol Open"},{"issue":"12","key":"pone.0348137.ref027","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1007\/s11548-018-1843-2","article-title":"Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images","volume":"13","author":"M Byra","year":"2018","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"5","key":"pone.0348137.ref028","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/TUFFC.2019.2903795","article-title":"Beamforming and speckle reduction using neural networks","volume":"66","author":"D Hyun","year":"2019","journal-title":"IEEE Trans Ultrason Ferroelectr Freq Control"},{"issue":"2","key":"pone.0348137.ref029","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1109\/TMI.2018.2864821","article-title":"Efficient B-mode ultrasound image reconstruction from sub-sampled RF data using deep learning","volume":"38","author":"YH Yoon","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0348137.ref030","first-page":"619","article-title":"Deep learning-based universal beamformer for ultrasound imaging.","author":"S Khan","year":"2019","journal-title":"Advances in ultrasound technology"},{"issue":"8","key":"pone.0348137.ref031","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/TUFFC.2020.2977202","article-title":"Adaptive and compressive beamforming using deep learning for medical ultrasound","volume":"67","author":"S Khan","year":"2020","journal-title":"IEEE Trans Ultrason Ferroelectr Freq Control"},{"key":"pone.0348137.ref032","doi-asserted-by":"crossref","first-page":"5967","DOI":"10.1109\/CVPR.2017.632","article-title":"Image-to-image translation with conditional adversarial networks","author":"P Isola","year":"2017","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); IEEE"},{"key":"pone.0348137.ref033","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1109\/ICCV.2017.167","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"X Huang","year":"2017","journal-title":"2017 IEEE International Conference on Computer Vision (ICCV). IEEE"},{"key":"pone.0348137.ref034","doi-asserted-by":"crossref","first-page":"14000","DOI":"10.1109\/ICCV48922.2021.01376","article-title":"Instance-wise hard negative example generation for contrastive learning in unpaired image-to-image translation","author":"W Wang","year":"2021","journal-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE"},{"key":"pone.0348137.ref035","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1145\/3503161.3547802","article-title":"Exploring negatives in contrastive learning for unpaired image-to-image translation","author":"Y Lin","year":"2022","journal-title":"Proceedings of the 30th ACM International Conference on Multimedia. New York, NY, USA: ACM"},{"key":"pone.0348137.ref036","doi-asserted-by":"crossref","unstructured":"Park T, Efros AA, Zhang R, Zhu J-Y. Contrastive learning for unpaired image-to-image translation; 2020. p. 319\u201345. https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"pone.0348137.ref037","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1109\/WACV56688.2023.00077","article-title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","author":"D Torbunov","year":"2023","journal-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE"},{"key":"pone.0348137.ref038","doi-asserted-by":"crossref","first-page":"7922","DOI":"10.1109\/CVPR52733.2024.00757","article-title":"StegoGAN: leveraging steganography for non-bijective image-to-image translation","author":"S Wu","year":"2024","journal-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE"},{"issue":"5","key":"pone.0348137.ref039","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1016\/S0168-8278(98)80228-6","article-title":"Dual-energy CT in the diagnosis and quantification of fatty liver: limited clinical value in comparison to ultrasound scan and single-energy CT, with special reference to iron overload","volume":"28","author":"MH Mendler","year":"1998","journal-title":"J Hepatol"},{"issue":"1","key":"pone.0348137.ref040","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1148\/rg.2019180043","article-title":"In-phase and opposed-phase imaging: applications of chemical shift and magnetic susceptibility in the chest and abdomen","volume":"39","author":"AS Shetty","year":"2019","journal-title":"Radiographics"},{"issue":"1","key":"pone.0348137.ref041","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"JR Landis","year":"1977","journal-title":"Biometrics"},{"key":"pone.0348137.ref042","doi-asserted-by":"crossref","first-page":"338","DOI":"10.21037\/atm.2016.09.11","article-title":"Diagnosis of hepatitis B","volume":"4","author":"JE Song","year":"2016","journal-title":"Ann Transl Med"},{"issue":"1","key":"pone.0348137.ref043","doi-asserted-by":"crossref","first-page":"19","DOI":"10.4103\/0973-6247.126683","article-title":"Hepatitis C virus: screening, diagnosis, and interpretation of laboratory assays","volume":"8","author":"E Gupta","year":"2014","journal-title":"Asian J Transfus Sci"},{"key":"pone.0348137.ref044","first-page":"122","article-title":"Deep learning convolutional neural networks for the estimation of liver fibrosis severity from ultrasound texture.","author":"D Beauchamp","year":"2019","journal-title":"Medical imaging 2019: computer-aided diagnosis. SPIE"},{"issue":"1","key":"pone.0348137.ref045","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/jum.15070","article-title":"Application of deep learning in quantitative analysis of 2-dimensional ultrasound imaging of nonalcoholic fatty liver disease","volume":"39","author":"W Cao","year":"2020","journal-title":"J Ultrasound Med"},{"issue":"4","key":"pone.0348137.ref046","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1136\/gutjnl-2018-316204","article-title":"Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study","volume":"68","author":"K Wang","year":"2019","journal-title":"Gut"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:44:09Z","timestamp":1777398249000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348137"}},"subtitle":[],"editor":[{"given":"Do Young","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348137","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]}}}