{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:33:16Z","timestamp":1792168396496,"version":"4.4.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We used deep learning to generate synthetic, resembling in appearance, iodine-enhanced, mammograms from low-energy contrast-enhanced mammography (CEM) images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We retrospectively selected 140 CEM examinations. We trained a two-dimensional cycle-generative adversarial network on 390 images in 100 patients (195 breasts; 102 positive and 93 negative for lesion detection) using paired low-energy and iodine-enhanced images as input and output, respectively. We validated our model in 40 test patients (63 breasts; 37 positive and 26 negative for lesion detection) by calculating the contrast-to-noise ratio (CNR) for low-energy, synthetic, and clinical iodine-enhanced images and the mean absolute error (MAE) and similarity index metric (SSIM) between clinical and synthetic iodine-enhanced images regarding their changes from low-energy. Three radiologists scored (a-to-d) the test set images for background parenchymal enhancement (BPE) and lesion detection (yes\/no) on clinical and synthetic images. The presence of artifacts was reported on all images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We observed a high correlation between clinical and synthetic iodine-enhanced images regarding their changes from low-energy: MAE,\n                      <jats:italic>r<\/jats:italic>\n                      \u2009=\u20090.99; SSIM,\n                      <jats:italic>r<\/jats:italic>\n                      \u2009=\u20090.80. CNR was -0.015\/-0.16\u2009\u00b1\u20090.23\/0.05 (mean\u2009\u00b1\u2009standard deviation) for clinical\/synthetic, respectively. A \u201chalo\u201d artifact present in above 50% of the clinical iodine-enhanced images was corrected in the synthetic ones. On synthetic images, BPE (scores a\u2013b\n                      <jats:italic>versus<\/jats:italic>\n                      c\u2013d) was 85.8% accurate. Lesion detection accuracy was 89.4% and 79.4%, sensitivity 87.4 and 72.1%, and specificity 92.3% and 90.0% for clinical and synthetic images, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning holds the potential to generate synthetic iodine-enhanced mammograms from low-energy images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Radiologists could perform some clinical tasks, such as lesion detection and BPE estimation on synthetic iodine-enhanced images, without contrast injection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Our deep learning model generated synthetic iodine-enhanced images that visually resembled the clinical iodine-enhanced images.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Radiologists could use the synthetic images to perform clinical tasks, such as lesion detection and BPE evaluation.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Our model can improve image quality by removing common artifacts, including the breast-in-breast (halo).<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Our method is a way to combine the benefits of CEM while sparing the need for contrast media.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00681-7","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:51:04Z","timestamp":1773658264000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generating synthetic CEM from low-energy images using deep learning: A future without contrast media? A proof-of-concept study"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3371-2915","authenticated-orcid":false,"given":"Konstantinos","family":"Zormpas-Petridis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Kalantar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ludovica","family":"Iaccarino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Mancino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianluca","family":"Franceschini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Clauser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"Longo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evis","family":"Sala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Belli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"D\u2019Angelo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"681_CR1","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1148\/radiol.2021201948","volume":"299","author":"MS Jochelson","year":"2021","unstructured":"Jochelson MS, Lobbes MBI (2021) Contrast-enhanced mammography: state of the art. Radiology 299:36\u201348. https:\/\/doi.org\/10.1148\/radiol.2021201948","journal-title":"Radiology"},{"key":"681_CR2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1053\/j.sult.2017.08.005","volume":"39","author":"BK Patel","year":"2018","unstructured":"Patel BK, Lobbes MBI, Lewin J (2018) Contrast enhanced spectral mammography: a review. Semin Ultrasound CT MR 39:70\u201379. https:\/\/doi.org\/10.1053\/j.sult.2017.08.005","journal-title":"Semin Ultrasound CT MR"},{"key":"681_CR3","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.2214\/ajr.181.5.1811275","volume":"181","author":"EL Rosen","year":"2003","unstructured":"Rosen EL, Smith-Foley SA, DeMartini WB et al (2003) Accuracy of MRI in the detection of residual breast cancer after neoadjuvant chemotherapy. AJR Am J Roentgenol 181:1275\u20131282. https:\/\/doi.org\/10.2214\/ajr.181.5.1811275","journal-title":"AJR Am J Roentgenol"},{"key":"681_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109883","volume":"142","author":"MBI Lobbes","year":"2021","unstructured":"Lobbes MBI, Smidt ML, Houwers J et al (2021) Contrast enhanced mammography (CEM) versus magnetic resonance imaging (MRI) for staging of breast cancer: the pro CEM perspective. Eur J Radiol 142:109883. https:\/\/doi.org\/10.1016\/j.ejrad.2021.109883","journal-title":"Eur J Radiol"},{"key":"681_CR5","doi-asserted-by":"publisher","first-page":"W267","DOI":"10.2214\/AJR.17.19355","volume":"210","author":"V Sorin","year":"2018","unstructured":"Sorin V, Yagil Y, Shalmon A et al (2018) Contrast-enhanced spectral mammography in women with intermediate breast cancer risk and dense breasts. AJR Am J Roentgenol 210:W267\u2013W274. https:\/\/doi.org\/10.2214\/AJR.17.19355","journal-title":"AJR Am J Roentgenol"},{"key":"681_CR6","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s41747-022-00318-5","volume":"7","author":"DB Taylor","year":"2023","unstructured":"Taylor DB, Langlois C, Partovi S et al (2023) Contrast-enhanced mammography (CEM) versus MRI for breast cancer staging: detection of additional malignant lesions not seen on conventional imaging. Eur Radiol Exp 7:8. https:\/\/doi.org\/10.1186\/s41747-022-00318-5","journal-title":"Eur Radiol Exp"},{"key":"681_CR7","doi-asserted-by":"publisher","first-page":"832","DOI":"10.2214\/AJR.07.3606","volume":"119","author":"DM Witten","year":"1973","unstructured":"Witten DM, Hirsch FD, Hartman GW (1973) Acute reactions to urographic contrast medium: incidence, clinical characteristics and relationship to history of hypersensitivity states. AJR Am J Roentgenol 119:832\u2013840. https:\/\/doi.org\/10.2214\/AJR.07.3606","journal-title":"AJR Am J Roentgenol"},{"key":"681_CR8","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1007\/s00330-017-5247-4","volume":"28","author":"AJ van der Molen","year":"2018","unstructured":"van der Molen AJ, Reimer P, Dekkers IA et al (2018) Post-contrast acute kidney injury part 2: risk stratification, role of hydration and other prophylactic measures, patients taking metformin and chronic dialysis patients: recommendations for updated ESUR contrast medium safety committee guidelines. Eur Radiol 28:2856\u20132869. https:\/\/doi.org\/10.1007\/s00330-017-5247-4","journal-title":"Eur Radiol"},{"key":"681_CR9","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/s00330-010-2026-x","volume":"21","author":"HS Thomsen","year":"2011","unstructured":"Thomsen HS (2011) Recent hot topics in contrast media. Eur Radiol 21:492\u2013495. https:\/\/doi.org\/10.1007\/s00330-010-2026-x","journal-title":"Eur Radiol"},{"key":"681_CR10","doi-asserted-by":"publisher","first-page":"e230021","DOI":"10.1148\/rg230021","volume":"43","author":"RM Lorente-Ramos","year":"2023","unstructured":"Lorente-Ramos RM, Azpeitia-Arm\u00e1n J, Oliva-Fonte C, P\u00e9rez-Bartolom\u00e9 A, Azpeitia Hern\u00e1ndez J (2023) Contrast-enhanced mammography artifacts and pitfalls: tips and tricks to avoid misinterpretation. Radiographics 43:e230021. https:\/\/doi.org\/10.1148\/rg230021","journal-title":"Radiographics"},{"key":"681_CR11","doi-asserted-by":"publisher","first-page":"234","DOI":"10.48550\/arXiv.1505.04597","volume":"9351","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. Med Image Comput Comput Assist Interv 9351:234\u2013241. https:\/\/doi.org\/10.48550\/arXiv.1505.04597","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"681_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102398","volume":"116","author":"A Rofena","year":"2024","unstructured":"Rofena A, Carlucci G, Righi A et al (2024) A deep learning approach for virtual contrast enhancement in contrast enhanced spectral mammography. Comput Med Imaging Graph 116:102398. https:\/\/doi.org\/10.1016\/j.compmedimag.2024.102398","journal-title":"Comput Med Imaging Graph"},{"key":"681_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.665807","volume":"11","author":"R Kalantar","year":"2021","unstructured":"Kalantar R, Abdi AH, Mahdavi SS et al (2021) CT-based pelvic T1-weighted MR image synthesis using UNet, UNet++ and cycle-consistent generative adversarial network (cycle-GAN). Front Oncol 11:665807. https:\/\/doi.org\/10.3389\/fonc.2021.665807","journal-title":"Front Oncol"},{"key":"681_CR14","unstructured":"American College of Radiology (ACR) (2022) Breast imaging reporting and data system atlas (BI-RADS atlas). American College of Radiology, Reston, VA, USA. Available via ACR https:\/\/www.acr.org\/media\/ACR\/Files\/RADS\/BI-RADS\/BIRADS_CEM_2022.pdf. Accessed 14 Mar 2024"},{"key":"681_CR15","doi-asserted-by":"publisher","first-page":"534","DOI":"10.3390\/bioengineering10050534","volume":"10","author":"GI Quintana","year":"2023","unstructured":"Quintana GI, Li Z, Vancamberg L, Mougeot M, Desolneux A, Muller S (2023) Exploiting patch sizes and resolutions for multi-scale deep learning in mammogram image classification. Bioengineering 10:534. https:\/\/doi.org\/10.3390\/bioengineering10050534","journal-title":"Bioengineering"},{"key":"681_CR16","doi-asserted-by":"publisher","first-page":"778","DOI":"10.48550\/arXiv.1512.03385","volume":"770","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit 770:778. https:\/\/doi.org\/10.48550\/arXiv.1512.03385","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"681_CR17","doi-asserted-by":"publisher","unstructured":"Cardoso MJ, Li W, Brown R et al (2022) Monai: an open-source framework for deep learning in healthcare. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2211.02701","DOI":"10.48550\/arXiv.2211.02701"},{"key":"681_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1148\/radiol.11102156","volume":"260","author":"V King","year":"2011","unstructured":"King V, Brooks JD, Bernstein JL, Reiner AS, Pike MC, Morris EA (2011) Background parenchymal enhancement at breast MR imaging and breast cancer risk. Radiology 260:50\u201360. https:\/\/doi.org\/10.1148\/radiol.11102156","journal-title":"Radiology"},{"key":"681_CR19","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.clinimag.2023.06.019","volume":"101","author":"C Bennett","year":"2023","unstructured":"Bennett C, Woodard S, Zamora K (2023) A pictorial guide to artifacts on contrast mammography: how to avoid pitfalls and improve interpretation. Clin Imaging 101:215\u2013222. https:\/\/doi.org\/10.1016\/j.clinimag.2023.06.019","journal-title":"Clin Imaging"},{"key":"681_CR20","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1007\/s00330-022-08617-6","volume":"32","author":"RM Mann","year":"2022","unstructured":"Mann RM, Athanasiou A, Balleyguier C et al (2022) Breast cancer screening in women with extremely dense breasts: recommendations of the European Society of Breast Imaging (EUSOBI). Eur Radiol 32:4036\u20134045. https:\/\/doi.org\/10.1007\/s00330-022-08617-6","journal-title":"Eur Radiol"},{"key":"681_CR21","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1148\/radiol.2021203633","volume":"299","author":"SGA Veenhuizen","year":"2021","unstructured":"Veenhuizen SGA, den DekkerBM, Mann RM et al (2021) Supplemental breast MRI for women with extremely dense breasts: results of the second screening round of the DENSE trial. Radiology 299:278\u2013286. https:\/\/doi.org\/10.1148\/radiol.2021203633","journal-title":"Radiology"},{"key":"681_CR22","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/s41747-024-00516-3","volume":"8","author":"G Gennaro","year":"2024","unstructured":"Gennaro G, Vatteroni G, Bernardi D, Caumo F (2024) Performance of dual-energy subtraction in contrast-enhanced mammography for three different manufacturers: a phantom study. Eur Radiol Exp 8:113. https:\/\/doi.org\/10.1186\/s41747-024-00516-3","journal-title":"Eur Radiol Exp"},{"key":"681_CR23","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1186\/s41747-024-00447-z","volume":"8","author":"G Gennaro","year":"2024","unstructured":"Gennaro G, Genio SD, Manco G, Caumo F (2024) Phantom-based analysis of variations in automatic exposure control across three mammography systems: implications for radiation dose and image quality in mammography, DBT, and CEM. Eur Radiol Exp 8:49. https:\/\/doi.org\/10.1186\/s41747-024-00447-z","journal-title":"Eur Radiol Exp"},{"key":"681_CR24","doi-asserted-by":"publisher","unstructured":"Nguyen LX, Kim D, Cho J et al (2023) A new chapter for medical image generation: the stable diffusion method. Proc Int Conf Inf Netw. https:\/\/doi.org\/10.1109\/ICOIN56518.2023.10049010","DOI":"10.1109\/ICOIN56518.2023.10049010"},{"key":"681_CR25","doi-asserted-by":"publisher","unstructured":"Kalantar R, Abdi AH, Mahdavi SS et al (2023) MED-INPAINT: medical image synthesis using multi-level conditional inpainting with a denoising diffusion probabilistic model and adaptive contrast priors. Proc IEEE Int Conf Med Artif Intell. https:\/\/doi.org\/10.1109\/MedAI59581.2023.00061","DOI":"10.1109\/MedAI59581.2023.00061"},{"key":"681_CR26","doi-asserted-by":"publisher","unstructured":"Zhang R, Isola P, Efros AA et al (2018) The unreasonable effectiveness of deep features as a perceptual metric. Proc IEEE Conf Comput Vision Pattern Recognit. IEEE, pp 586\u2013595. https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"681_CR27","doi-asserted-by":"publisher","unstructured":"Heusel M, Ramsauer H, Unterthiner T et al (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst. https:\/\/doi.org\/10.48550\/arXiv.1706.08500","DOI":"10.48550\/arXiv.1706.08500"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00681-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00681-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00681-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:51:07Z","timestamp":1773658267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00681-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["681"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00681-7","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"29 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"ES is a member of the Scientific Editorial Board of\n                      European Radiology Experimental\n                      (section: Artificial intelligence, augmented reality, computer science, and radiomics) and, as such, did not participate in the selection or review processes for this article. The remaining authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This retrospective study was reviewed and approved on (approval date: 11\/09\/2024) by the local Institutional Review Board (approval number: ID 6921) of Fondazione Policlinico Universitario Agostino Gemelli IRCCS (FPG), Rome, Italy. The ethics committee waived the requirement of written informed consent for participation.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"31"}}