{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T12:15:25Z","timestamp":1792239325042,"version":"4.4.0"},"reference-count":53,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100002923","name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","doi-asserted-by":"publisher","award":["PIP2021\u20102023\u201011220200102472CO"],"award-info":[{"award-number":["PIP2021\u20102023\u201011220200102472CO"]}],"id":[{"id":"10.13039\/501100002923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021778","name":"Agencia Nacional de Promoci\u00f3n de la Investigaci\u00f3n, el Desarrollo Tecnol\u00f3gico y la Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PICTs2020\u20100045"],"award-info":[{"award-number":["PICTs2020\u20100045"]}],"id":[{"id":"10.13039\/501100021778","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Ultrasound (US) simulation helps train physicians and medical students in image acquisition and interpretation, enabling safe practice of transducer manipulation and organ identification. Current simulators generate realistic images from reference scans. Although physics\u2010based simulators provide real\u2010time images, they lack sufficient realism, while recent deep learning\u2010based models based on unpaired image\u2010to\u2010image translation improve realism but introduce anatomical\u00a0inconsistencies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>We propose a novel framework to reduce hallucinations from generative adversarial networks (GANs) used on physics\u2010based simulations, enhancing anatomical accuracy and realism in abdominal US simulation. Our method aims to produce anatomically consistent images free from artifacts within and outside the field of view (FoV).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We introduce a segmentation\u2010guided loss to enforce anatomical consistency by using a pre\u2010trained Unet model that segments abdominal organs from physics\u2010based simulated scans. Penalizing segmentation discrepancies before and after the translation cycle helps prevent unrealistic artifacts. Additionally, we propose training GANs on images in polar coordinates to limit the field of view to non\u2010blank regions. We evaluated our approach on unpaired datasets comprising 617 real abdominal US images from a SonoSite\u2010M turbo v1.3 scanner and 971 artificial scans from a ray\u2010casting simulator. Data was partitioned at the patient level into training (70%), validation (10%), and testing (20%). Performance was quantitatively assessed with Frechet and Kernel Inception Distances (FID and KID), and organ\u2010specific  histogram distances, reporting 95% confidence intervals. We compared our model against generative methods such as CUT, UVCGANv2, and UNSB, performing statistical analyses using Wilcoxon tests (FID and KID with Bonferroni\u2010corrected ,  with ). A perceptual realism study involving expert radiologists was also\u00a0conducted.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our method significantly reduced FID and KID by 66% and 89%, respectively, compared to CycleGAN, and by 34% and 59% compared to the leading alternative UVCGANv2 (). No significant differences () in echogenicity distributions were found between real and simulated images within liver and gallbladder regions. The user study indicated our simulated scans fooled radiologists in 36.2% of cases, outperforming other\u00a0methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our segmentation\u2010guided, polar\u2010coordinates\u2010trained CycleGAN framework significantly reduces hallucinations, ensuring anatomical consistency, and realism in simulated abdominal US images, surpassing existing\u00a0methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17801","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T20:36:59Z","timestamp":1743453419000},"page":"4540-4556","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving realism in abdominal ultrasound simulation combining a segmentation\u2010guided loss and polar coordinates training"],"prefix":"10.1002","volume":"52","author":[{"given":"Santiago","family":"Vitale","sequence":"first","affiliation":[{"name":"National Scientific and Technical Research Council (CONICET)  Buenos Aires Argentina"},{"name":"Pladema Institute UNICEN  Tandil Buenos Aires Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 Ignacio","family":"Orlando","sequence":"additional","affiliation":[{"name":"National Scientific and Technical Research Council (CONICET)  Buenos Aires Argentina"},{"name":"Pladema Institute UNICEN  Tandil Buenos Aires Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Iarussi","sequence":"additional","affiliation":[{"name":"National Scientific and Technical Research Council (CONICET)  Buenos Aires Argentina"},{"name":"Laboratory of Artificial Intelligence University Torcuato Di Tella  Buenos Aires Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"D\u00edaz","sequence":"additional","affiliation":[{"name":"National Scientific and Technical Research Council (CONICET)  Buenos Aires Argentina"},{"name":"Facultad de Ciencias de la Salud UNICEN  Olavarr\u00eda Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignacio","family":"Larrabide","sequence":"additional","affiliation":[{"name":"National Scientific and Technical Research Council (CONICET)  Buenos Aires Argentina"},{"name":"Pladema Institute UNICEN  Tandil Buenos Aires Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40560-016-0175-y"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.5005\/jp-journals-10009-1816"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.7863\/ultra.15.05073"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0042-100452"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/ase.1452"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1097\/SIH.0000000000000485"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"DonnezM CartonFX Le LannF De SchlichtingE ChabanasM.Realistic synthesis of brain tumor resection ultrasound images with a generative adversarial network. In:Medical Imaging 2021: Image\u2010Guided Procedures Robotic Interventions and Modeling Vol11598.SPIE;2021:637\u2010642.","DOI":"10.1117\/12.2581911"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02203-1"},{"key":"e_1_2_9_10_1","doi-asserted-by":"crossref","unstructured":"ShamsR HartleyR NavabN.Real\u2010time simulation of medical ultrasound from CT images. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2008:734\u2010741.","DOI":"10.1007\/978-3-540-85990-1_88"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2012.2234474"},{"key":"e_1_2_9_12_1","unstructured":"MattauschO GokselO.Monte\u2010carlo ray\u2010tracing for realistic interactive ultrasound simulation. In:Proceedings of the Eurographics Workshop on Visual Computing for Biology and Medicine.ACM;2016:173\u2010181."},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"TomarD ZhangL PortenierT GokselO.Content\u2010preserving unpaired translation from simulated to realistic ultrasound images. In:Medical Image Computing and Computer Assisted Intervention\u2010MICCAI 2021: 24th International Conference Strasbourg France September 27\u2010October 1 2021 Proceedings Part VIII 24.Springer;2021:659\u2013669.","DOI":"10.1007\/978-3-030-87237-3_63"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.202100008"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"TomF SheetD.Simulating patho\u2010realistic ultrasound images using deep generative networks with adversarial learning. In:2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018) IEEE;2018:1174\u20131177.","DOI":"10.1109\/ISBI.2018.8363780"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02349-6"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102461"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"PigeauG ElbatarnyL WuV SchonewilleA FichtingerG UngiT.Ultrasound image simulation with generative adversarial network. In:Medical Imaging 2020: Image\u2010Guided Procedures Robotic Interventions and Modeling vol11315.SPIE;2020:54\u201060.","DOI":"10.1117\/12.2549592"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105583"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"ZhuJY ParkT IsolaP EfrosAA.Unpaired image\u2010to\u2010image translation using cycle\u2010consistent adversarial networks. In:Proceedings of the IEEE international conference on computer vision. arXiv;2017:2223\u20102232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02046-5"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"MaoX LiQ XieH LauRY WangZ Paul SmolleyS.Least squares generative adversarial networks. In:Proceedings of the IEEE international conference on computer vision. IEEE;2017:2813\u20102821.","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"CohenJP LuckM HonariS.Distribution matching losses can hallucinate features in medical image translation. In:Medical Image Computing and Computer Assisted Intervention\u2010MICCAI 2018: 21st International Conference Granada Spain September 16\u201020 2018 Proceedings Part I.Springer;2018:529\u2010536.","DOI":"10.1007\/978-3-030-00928-1_60"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"RubiP VeraEF LarrabideJ CalvoM D'AmatoJ LarrabideI.Comparison of real\u2010time ultrasound simulation models using abdominal CT images. In:12th international symposium on medical information processing and analysis vol10160.SPIE;2017:55\u201063.","DOI":"10.1117\/12.2255741"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.Unet: Convolutional networks for biomedical image segmentation. In:International Conference on Medical image computing and computer assisted intervention.Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2578680"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE;2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_28_1","unstructured":"DangiS LinteC.DenseUNet\u2010K: a simplified densely connected fully convolutional network for image\u2010to\u2010image translation.Github.2019."},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/acd236"},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"IsolaP ZhuJY ZhouT EfrosAA.Image\u2010to\u2010image translation with conditional adversarial networks. In:Proceedings of the IEEE conference on computer vision and pattern recognition.IEEE;2017:1125\u20101134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_9_31_1","unstructured":"UlyanovD VedaldiA LempitskyV.Instance normalization: The missing ingredient for fast stylization.arXiv.2016:1607.08022"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"UlyanovD VedaldiA LempitskyV.Improved texture networks: Maximizing quality and diversity in feed\u2010forward stylization and texture synthesis. In:Proceedings of the IEEE conference on computer vision and pattern recognition.IEEE;2017:4105\u20104113.","DOI":"10.1109\/CVPR.2017.437"},{"key":"e_1_2_9_33_1","unstructured":"KingmaDP BaJ.Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980.2014."},{"key":"e_1_2_9_34_1","doi-asserted-by":"crossref","unstructured":"ParkT EfrosAA ZhangR ZhuJY.Contrastive learning for unpaired image\u2010to\u2010image translation. In:Computer Vision\u2010ECCV 2020: 16th European Conference Glasgow UK August 23\u201028 2020 Proceedings Part IX 16.Springer;2020:319\u2010345.","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"TomarD ZhangL PortenierT GokselO.Content\u2010preserving unpaired translation from simulated to realistic ultrasound images. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:659\u2010669.","DOI":"10.1007\/978-3-030-87237-3_63"},{"key":"e_1_2_9_36_1","unstructured":"TorbunovD HuangY TsengHH et\u00a0al.Rethinking CycleGAN: Improving Quality of GANs for Unpaired Image\u2010to\u2010Image Translation.arXiv.2023:2303.16280"},{"key":"e_1_2_9_37_1","unstructured":"KimB KwonG KimK YeJC.Unpaired Image\u2010to\u2010Image Translation via Neural Schr\u00f6dinger Bridge. in: Internacional Conference on Learning Representations.arXiv.2023:2305.15086"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"MaX AnantrasirichaiN BolomytisS AchimA.PMT: Partial\u2010Modality Translation Based on Diffusion Models for Prostate Magnetic Resonance and Ultrasound Image Registration. In:Annual Conference on Medical Image Understanding and Analysis.Springer;2024:285\u2010297.","DOI":"10.1007\/978-3-031-66958-3_21"},{"key":"e_1_2_9_39_1","unstructured":"AlqahtaniH Kavakli\u2010ThorneM KumarG SBSSTCF.An analysis of evaluation metrics of gans. In:International Conference on Information Technology and Applications (ICITA). vol7 2019."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103329"},{"key":"e_1_2_9_41_1","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel M","year":"2017"},{"key":"e_1_2_9_42_1","unstructured":"Bi\u0144kowskiM SutherlandDJ ArbelM GrettonA.Demystifying mmd gans. in: Internacional Conference on Learning Representations.arXiv.2018:1801.01401"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"LiangJ YangX HuangY et\u00a0al.Weakly\u2010supervised high\u2010fidelity ultrasound video synthesis with feature decoupling. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2022:310\u2010319.","DOI":"10.1007\/978-3-031-16440-8_30"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"SzegedyC VanhouckeV IoffeS ShlensJ WojnaZ.Rethinking the inception architecture for computer vision. In:Proceedings of the IEEE conference on computer vision and pattern recognition.IEEE;2016:2818\u20102826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_9_45_1","unstructured":"ObukhovA SeitzerM WuP ZhydenkoS KylJ LinE.High\u2010fidelity performance metrics for generative models in PyTorch.Zenodo;2020."},{"key":"e_1_2_9_46_1","unstructured":"BonferroniC.Statistic theory of classes and calculation of probabilities.Volume in Honor of Riccardo della Volta. Florence: University of Florence.Seeber.1937:1\u201062."},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/0301-5629(85)90108-5"},{"key":"e_1_2_9_49_1","doi-asserted-by":"crossref","unstructured":"ChinaD TomF NandamuriS et\u00a0al.Ultracompression: framework for high density compression of ultrasound volumes using physics modeling deep neural networks. In:2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).IEEE;2019:798\u2010801.","DOI":"10.1109\/ISBI.2019.8759159"},{"key":"e_1_2_9_50_1","doi-asserted-by":"crossref","unstructured":"TripathiAK MukhopadhyayS DharaAK.Performance metrics for image contrast. In:2011 International Conference on Image Information Processing.IEEE;2011:1\u20104.","DOI":"10.1109\/ICIIP.2011.6108900"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-014-0458-y"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024"},{"key":"e_1_2_9_53_1","first-page":"1","volume-title":"International Challenge on Kidney and Kidney Tumor Segmentation","author":"Myronenko A","year":"2023"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107642"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T08:04:51Z","timestamp":1762934691000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":53,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1002\/mp.17801"],"URL":"https:\/\/doi.org\/10.1002\/mp.17801","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2024-04-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}