{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:59:28Z","timestamp":1781243968386,"version":"3.54.1"},"reference-count":66,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Tumor heterogeneity poses a significant challenge for predicting responses to cancer therapy, highlighting the need for the development of biomarkers to guide personalized treatment. Contrast-enhanced ultrasound (CEUS) imaging is an established method to assess tumor perfusion, which directly affects drug delivery and therapeutic efficacy, as poorly perfused tumors often limit the penetration of chemo- and immunotherapeutics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a deep learning framework using CEUS imaging to predict the response of tumors to chemo-immunotherapy in murine models of breast cancer, fibrosarcoma, and melanoma. A convolutional neural network (CEUS-CNN) was trained on a dataset of 587 pre-treatment CEUS images to classify tumors as responsive, stable, or non-responsive based on RECIST version 1.1 (Response Evaluation Criteria in Solid Tumors) criteria (175 responsive cases, 136 stable, and 276 non-responsive). Additionally, synthetic data were created for the responsive and stable classes to address class disparity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our framework attained an overall test accuracy of 0.877 (0.941 for responsive, 0.615 for stable, 0.963 for non-responsive) using only real data. The addition of synthetic data led to improved model performance, with a notable impact on the previously underperforming stable class. Our strategy enhanced the predictive capability of our model, raising the average test accuracy to 0.930 (1.000 for responsive, 0.769 for stable, 0.963 for non-responsive).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings support CEUS imaging as a possible imaging biomarker of response to cancer therapy and further indicate that the incorporation of synthetic data can enhance model effectiveness, particularly for underrepresented classes. Together, they highlight the potential value of integrating AI with CEUS for personalized cancer treatment strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1805416","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:45:27Z","timestamp":1781243127000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning prediction of chemo-immunotherapy response using tumor perfusion ultrasound images"],"prefix":"10.3389","volume":"9","author":[{"given":"Kyprianos","family":"Dimou","sequence":"first","affiliation":[{"name":"Cancer Biophysics Laboratory, Department of Mechanical and Manufacturing Engineering, University of Cyprus","place":["Nicosia, Cyprus"]},{"name":"Department of Research and Innovation, German Oncology Center, European University Cyprus","place":["Limassol, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Floris","family":"Alexandrou","sequence":"additional","affiliation":[{"name":"AnaBioSi-Data Ltd.","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiannis","family":"Roussakis","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, German Oncology Center, European University Cyprus","place":["Limassol, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Constantinos","family":"Zamboglou","sequence":"additional","affiliation":[{"name":"German Oncology Center, European University Cyprus","place":["Limassol, Cyprus"]},{"name":"Department of Radiation Oncology, University of Freiburg - Medical Center","place":["Freiburg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Triantafyllos","family":"Stylianopoulos","sequence":"additional","affiliation":[{"name":"Cancer Biophysics Laboratory, Department of Mechanical and Manufacturing Engineering, University of Cyprus","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chrysovalantis","family":"Voutouri","sequence":"additional","affiliation":[{"name":"Cancer Biophysics Laboratory, Department of Mechanical and Manufacturing Engineering, University of Cyprus","place":["Nicosia, Cyprus"]},{"name":"AnaBioSi-Data Ltd.","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"ref1","first-page":"239","volume-title":"Privacy in Statistical Databases. Lecture Notes in Computer Science","author":"Abowd","year":"2008"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s10115-012-0487-8","article-title":"A review of feature selection methods on synthetic data","volume":"34","author":"Bol\u00f3n-Canedo","year":"2013","journal-title":"Knowl. Inf. Syst."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1038\/nrc.2016.153","article-title":"Precision diagnostics: moving towards protein biomarker signatures of clinical utility in cancer","volume":"17","author":"Borrebaeck","year":"2017","journal-title":"Nat. Rev. Cancer"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1810.10863","article-title":"GAN augmentation: augmenting training data using generative adversarial networks","author":"Bowles","year":"2018","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4126","DOI":"10.3390\/s21124126","article-title":"Deep neural architectures for contrast enhanced ultrasound (CEUS) focal liver lesions automated diagnosis","volume":"21","author":"C\u0103leanu","year":"2021","journal-title":"Sensors"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"3114","DOI":"10.1007\/s00261-023-03984-0","article-title":"Machine learning for malignant versus benign focal liver lesions on US and CEUS: a meta-analysis","volume":"48","author":"Campello","year":"2023","journal-title":"Abdom Radiol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2516","DOI":"10.1038\/ncomms3516","article-title":"Angiotensin inhibition enhances drug delivery and potentiates chemotherapy by decompressing tumour blood vessels","volume":"4","author":"Chauhan","year":"2013","journal-title":"Nat. Commun."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41551-021-00751-8","article-title":"Synthetic data in machine learning for medicine and healthcare","volume":"5","author":"Chen","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1002\/mrm.28689","article-title":"Deep learning-based T1-enhanced selection of linear attenuation coefficients (DL-TESLA) for PET\/MR attenuation correction in dementia neuroimaging","volume":"86","author":"Chen","year":"2021","journal-title":"Magn. Reson. Med."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.3390\/s19051181","article-title":"SynSys: a synthetic data generation system for healthcare applications","volume":"19","author":"Dahmen","year":"2019","journal-title":"Sensors"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"21465","DOI":"10.1007\/s00521-021-05982-z","article-title":"Synthetic data generation using DCGAN for improved traffic sign recognition","volume":"34","author":"Dewi","year":"2022","journal-title":"Neural Comput. & Applic."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.ejca.2008.10.026","article-title":"New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1)","volume":"45","author":"Eisenhauer","year":"2009","journal-title":"Eur. J. Cancer"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2018.09.013","article-title":"GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification","volume":"321","author":"Frid-Adar","year":"2018","journal-title":"Neurocomputing"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"4845","DOI":"10.1007\/s10994-022-06268-8","article-title":"The class imbalance problem in deep learning","volume":"113","author":"Ghosh","year":"2024","journal-title":"Mach. Learn."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/TMI.2016.2553401","article-title":"Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique","volume":"35","author":"Greenspan","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1512.03385","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1502.03167","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.ccell.2014.10.006","article-title":"Antiangiogenesis strategies revisited: from starving tumors to alleviating hypoxia","volume":"26","author":"Jain","year":"2014","journal-title":"Cancer Cell"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1146\/annurev-bioeng-071813-105259","article-title":"The role of mechanical forces in tumor growth and therapy","volume":"16","author":"Jain","year":"2014","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.neucom.2016.01.074","article-title":"Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset","volume":"194","author":"Jun","year":"2016","journal-title":"Neurocomputing"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1038\/s42003-024-07268-1","article-title":"Mechanical forces inducing oxaliplatin resistance in pancreatic cancer can be targeted by autophagy inhibition","volume":"7","author":"Kalli","year":"2024","journal-title":"Commun Biol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1016\/j.trecan.2023.07.006","article-title":"Beyond matrix stiffness: targeting force-induced cancer drug resistance","volume":"9","author":"Kalli","year":"2023","journal-title":"Trends Cancer"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"011501","DOI":"10.1063\/5.0183302","article-title":"Toward innovative approaches for exploring the mechanically regulated tumor-immune microenvironment","volume":"8","author":"Kalli","year":"2024","journal-title":"APL Bioeng"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12880-023-01072-9","article-title":"Ceusia-breast: computer-aided diagnosis with contrast enhanced ultrasound image analysis for breast lesions","volume":"23","author":"Kondo","year":"2023","journal-title":"BMC Med. Imaging"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"116962","DOI":"10.1016\/j.eswa.2022.116962","article-title":"What makes multi-class imbalanced problems difficult? An experimental study","volume":"199","author":"Lango","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1007\/s11517-018-1924-y","article-title":"Image synthesis-based multi-modal image registration framework by using deep fully convolutional networks","volume":"57","author":"Liu","year":"2019","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1007\/s00330-019-06553-6","article-title":"Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound","volume":"30","author":"Liu","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"vbac037","DOI":"10.1093\/bioadv\/vbac037","article-title":"COT: an efficient and accurate method for detecting marker genes among many subtypes","volume":"2","author":"Lu","year":"2022","journal-title":"Bioinform. Adv."},{"key":"ref31","first-page":"11","article-title":"The real deal about synthetic data","volume":"63","author":"Lucini","year":"2022","journal-title":"MIT Sloan Manag. Rev."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"107295","DOI":"10.1016\/j.compbiomed.2023.107295","article-title":"Early diagnosis and personalised treatment focusing on synthetic data modelling: novel visual learning approach in healthcare","volume":"164","author":"Mahmoud","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1148\/rg.2020190183","article-title":"Contrast-enhanced US for the interventional radiologist: current and emerging applications","volume":"40","author":"Malone","year":"2020","journal-title":"Radiographics"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.3390\/diagnostics13061062","article-title":"An automated method for classifying liver lesions in contrast-enhanced ultrasound imaging based on deep learning algorithms","volume":"13","author":"M\u0103muleanu","year":"2023","journal-title":"Diagnostics"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1038\/s41571-019-0308-z","article-title":"Improving cancer immunotherapy using nanomedicines: progress, opportunities and challenges","volume":"17","author":"Martin","year":"2020","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2202","DOI":"10.3390\/s21062202","article-title":"Hepatocellular carcinoma automatic diagnosis within CEUS and B-mode ultrasound images using advanced machine learning methods","volume":"21","author":"Mitrea","year":"2021","journal-title":"Sensors"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"101626","DOI":"10.1016\/j.xcrm.2024.101626","article-title":"Modulating cancer mechanopathology to restore vascular function and enhance immunotherapy","volume":"5","author":"Mpekris","year":"2024","journal-title":"Cell Rep Med"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1016\/j.jconrel.2022.12.016","article-title":"Translational nanomedicine potentiates immunotherapy in sarcoma by normalizing the microenvironment","volume":"353","author":"Mpekris","year":"2023","journal-title":"J. Control. Release"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2001917","DOI":"10.1002\/advs.202001917","article-title":"Normalizing the microenvironment overcomes vessel compression and resistance to Nano-immunotherapy in breast Cancer lung metastasis","volume":"8","author":"Mpekris","year":"2021","journal-title":"Adv. Sci."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"3728","DOI":"10.1073\/pnas.1919764117","article-title":"Combining microenvironment normalization strategies to improve cancer immunotherapy","volume":"117","author":"Mpekris","year":"2020","journal-title":"Proc. Natl. Acad. Sci."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.jconrel.2022.03.008","article-title":"Normalizing tumor microenvironment with nanomedicine and metronomic therapy to improve immunotherapy","volume":"345","author":"Mpekris","year":"2022","journal-title":"J. Control. Release"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1001\/jamaoncol.2019.0892","article-title":"Total neoadjuvant therapy with FOLFIRINOX in combination with losartan followed by Chemoradiotherapy for locally advanced pancreatic Cancer: a phase 2 clinical trial","volume":"5","author":"Murphy","year":"2019","journal-title":"JAMA Oncol."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"7165","DOI":"10.1038\/s41467-022-34744-1","article-title":"Polymeric micelles effectively reprogram the tumor microenvironment to potentiate nano-immunotherapy in mouse breast cancer models","volume":"13","author":"Panagi","year":"2022","journal-title":"Nat. Commun."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1910","DOI":"10.7150\/thno.36936","article-title":"TGF-\u03b2 inhibition combined with cytotoxic nanomedicine normalizes triple negative breast cancer microenvironment towards anti-tumor immunity","volume":"10","author":"Panagi","year":"2020","journal-title":"Theranostics"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"46140","DOI":"10.1038\/srep46140","article-title":"Tranilast-induced stress alleviation in solid tumors improves the efficacy of chemo- and nanotherapeutics in a size-independent manner","volume":"7","author":"Papageorgis","year":"2017","journal-title":"Sci. Rep."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"2892","DOI":"10.1016\/j.csbj.2024.07.005","article-title":"Synthetic data generation methods in healthcare: a review on open-source tools and methods","volume":"23","author":"Pezoulas","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2307.01952","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"24506","DOI":"10.18632\/oncotarget.15534","article-title":"Pirfenidone normalizes the tumor microenvironment to improve chemotherapy","volume":"8","author":"Polydorou","year":"2017","journal-title":"Oncotarget"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"2808","DOI":"10.3390\/math12182808","article-title":"Next-generation diagnostics: the impact of synthetic data generation on the detection of breast cancer from ultrasound imaging","volume":"12","author":"Rai","year":"2024","journal-title":"Mathematics"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1109\/TMI.2015.2482920","article-title":"Improving computer-aided detection using <?Pub _newline?> convolutional neural networks and random view aggregation","volume":"35","author":"Roth","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2208.12242","article-title":"DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz","year":"2022","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1038\/d41587-019-00019-2","article-title":"Pancreatic cancer provides testbed for first mechanotherapeutics","volume":"37","author":"Sheridan","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref54","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Machine Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"15101","DOI":"10.1073\/pnas.1213353109","article-title":"Causes, consequences, and remedies for growth-induced solid stress in murine and human tumors","volume":"109","author":"Stylianopoulos","year":"2012","journal-title":"Proc. Natl. Acad. Sci."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.trecan.2018.02.005","article-title":"Reengineering the physical microenvironment of tumors to improve drug delivery and efficacy: from mathematical modeling to bench to bedside","volume":"4","author":"Stylianopoulos","year":"2018","journal-title":"Trends Cancer"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s13735-021-00218-1","article-title":"A review on deep learning in medical image analysis","volume":"11","author":"Suganyadevi","year":"2022","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: full training or fine tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref59","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1109\/TUFFC.2022.3161719","article-title":"Interpretable machine learning for characterization of focal liver lesions by contrast-enhanced ultrasound","volume":"69","author":"Turco","year":"2022","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/s40477-021-00651-2","article-title":"Characterizing breast masses using an integrative framework of machine learning and CEUS-based radiomics","volume":"25","author":"Varghese","year":"2022","journal-title":"J. Ultrasound"},{"key":"ref61","doi-asserted-by":"publisher","first-page":"100258","DOI":"10.1016\/j.xops.2022.100258","article-title":"SynthEye: investigating the impact of synthetic data on artificial intelligence-assisted gene diagnosis of inherited retinal disease","volume":"3","author":"Veturi","year":"2023","journal-title":"Ophthalmol. Sci."},{"key":"ref62","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.actbio.2023.06.007","article-title":"Ultrasound stiffness and perfusion markers correlate with tumor volume responses to immunotherapy","volume":"167","author":"Voutouri","year":"2023","journal-title":"Acta Biomater."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"2000289","DOI":"10.1002\/adtp.202000289","article-title":"Endothelin inhibition potentiates Cancer immunotherapy revealing mechanical biomarkers predictive of response","volume":"4","author":"Voutouri","year":"2021","journal-title":"Adv. Ther."},{"key":"ref64","doi-asserted-by":"publisher","first-page":"3441","DOI":"10.1016\/j.jbiomech.2014.09.019","article-title":"Evolution of osmotic pressure in solid tumors","volume":"47","author":"Voutouri","year":"2014","journal-title":"J. Biomech."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"e0193801","DOI":"10.1371\/journal.pone.0193801","article-title":"Accumulation of mechanical forces in tumors is related to hyaluronan content and tissue stiffness","volume":"13","author":"Voutouri","year":"2018","journal-title":"PLoS One"},{"key":"ref66","first-page":"8198","article-title":"Learning from synthetic data for crowd counting in the wild","author":"Wang","year":"2019","journal-title":"Proc IEEECVF Conf Comput Vis Pattern Recognit"},{"key":"ref67","doi-asserted-by":"publisher","first-page":"55","DOI":"10.2214\/AJR.09.2553","article-title":"Contrast-enhanced ultrasound: what is the evidence and what are the obstacles?","volume":"193","author":"Wilson","year":"2009","journal-title":"Am. J. Roentgenol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1805416\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:45:30Z","timestamp":1781243130000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1805416\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":66,"alternative-id":["10.3389\/frai.2026.1805416"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1805416","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]},"article-number":"1805416"}}