{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T02:06:33Z","timestamp":1793844393753,"version":"4.6.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioMed Eng OnLine"],"DOI":"10.1186\/s12938-025-01486-2","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:34:20Z","timestamp":1765305260000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Benchmarking Vision LLMs in fetal ultrasound interpretation: a five-point expert evaluation of standard vs. custom prompts"],"prefix":"10.1186","volume":"25","author":[{"given":"Wala","family":"ELsharif","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmood","family":"Alzubaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Tukur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullatif","family":"Magram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatima","family":"Anver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aysha","family":"Hamza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Safia","family":"Said","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rukhayya","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mowafa","family":"Househ","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Agus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,9]]},"reference":[{"key":"1486_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.8831","author":"LJ Salomon","year":"2011","unstructured":"Salomon LJ, Alfirevic Z, Berghella V, Bilardo C, Hernandez-Andrade E, Johnsen S, et al. Practice guidelines for performance of the routine mid-trimester fetal ultrasound scan. Ultrasound Obstet Gynecol. 2011. https:\/\/doi.org\/10.1002\/uog.8831.","journal-title":"Ultrasound Obstet Gynecol"},{"key":"1486_CR2","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD007058.pub3","author":"M Whitworth","year":"2015","unstructured":"Whitworth M, Bricker L, Mullan C. Ultrasound for fetal assessment in early pregnancy. Cochrane Database Syst Rev. 2015. https:\/\/doi.org\/10.1002\/14651858.CD007058.pub3.","journal-title":"Cochrane Database Syst Rev"},{"key":"1486_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2022.104713","author":"M Alzubaidi","year":"2022","unstructured":"Alzubaidi M, Agus M, Alyafei K, Althelaya KA, Shah U, Abd-Alrazaq A, et al. Toward deep observation: a systematic survey on artificial intelligence techniques to monitor fetus via ultrasound images. iScience. 2022. https:\/\/doi.org\/10.1016\/j.isci.2022.104713.","journal-title":"iScience"},{"key":"1486_CR4","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et\u00a0al. Language models are few-shot learners. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS \u201920. Red Hook, NY, USA: Curran Associates Inc.; 2020."},{"key":"1486_CR5","first-page":"1","volume":"24","author":"A Chowdhery","year":"2024","unstructured":"Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, et al. PaLM: scaling language modeling with pathways. J Mach Learn Res. 2024;24:1.","journal-title":"J Mach Learn Res"},{"key":"1486_CR6","unstructured":"Alayrac JB, Donahue J, Luc P, Miech A, Barr I, Hasson Y, et\u00a0al. Flamingo: a visual language model for few-shot learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. NIPS \u201922. Red Hook, NY, USA: Curran Associates Inc.; 2024."},{"key":"1486_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-024-01246-y","author":"C Bluethgen","year":"2024","unstructured":"Bluethgen C, Chambon P, Delbrouck JB, van der Sluijs R, Po\u0142acin M, Zambrano Chaves JM, et al. A vision-language foundation model for the generation of realistic chest X-ray images. Nat Biomed Eng. 2024. https:\/\/doi.org\/10.1038\/s41551-024-01246-y.","journal-title":"Nat Biomed Eng"},{"key":"1486_CR8","doi-asserted-by":"publisher","unstructured":"Van M, Verma P, Wu X. On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study. In: 2024 IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE). 2024 IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE); 2024. 172-6. https:\/\/doi.org\/10.1109\/CHASE60773.2024.00029.","DOI":"10.1109\/CHASE60773.2024.00029"},{"issue":"10","key":"1486_CR9","doi-asserted-by":"publisher","first-page":"10TR01","DOI":"10.1088\/1361-6560\/ad387d","volume":"69","author":"M Hu","year":"2024","unstructured":"Hu M, Qian J, Pan S, Li Y, Qiu RLJ, Yang X, et al. Advancing medical imaging with language models: featuring a spotlight on ChatGPT. Phys Med Biol. 2024;69(10):10TR01. https:\/\/doi.org\/10.1088\/1361-6560\/ad387d.","journal-title":"Phys Med Biol"},{"key":"1486_CR10","doi-asserted-by":"publisher","first-page":"108238","DOI":"10.1016\/j.compbiomed.2024.108238","volume":"171","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Shen Z, Jiao R. Segment anything model for medical image segmentation: current applications and future directions. Comput Biol Med. 2024;171:108238.","journal-title":"Comput Biol Med"},{"key":"1486_CR11","unstructured":"Yan Z, Zhang K, Zhou R, He L, Li X, Sun L. Multimodal ChatGPT for medical applications: an experimental study of GPT-4V. 2023. arXiv preprint arXiv:2310.19061."},{"key":"1486_CR12","doi-asserted-by":"crossref","unstructured":"Hartsock I, Rasool G. Vision-language models for medical report generation and visual question answering: a review. 2024. https:\/\/arxiv.org\/abs\/2403.02469.","DOI":"10.3389\/frai.2024.1430984"},{"key":"1486_CR13","doi-asserted-by":"publisher","first-page":"129290","DOI":"10.1016\/j.neucom.2024.129290","volume":"621","author":"J Li","year":"2025","unstructured":"Li J, Gao Z, Wang C, Pu B, Li K. A rule-guided interpretable lightweight framework for fetal standard ultrasound plane capture and biometric measurement. Neurocomputing. 2025;621:129290.","journal-title":"Neurocomputing"},{"key":"1486_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-025-03400-6","author":"MC Fiorentino","year":"2025","unstructured":"Fiorentino MC, Migliorelli G, Villani FP, Frontoni E, Moccia S. Contrastive prototype federated learning against noisy labels in fetal standard plane detection. Int J Comput Assist Radiol Surg. 2025. https:\/\/doi.org\/10.1007\/s11548-025-03400-6.","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"1486_CR15","doi-asserted-by":"publisher","first-page":"103614","DOI":"10.1016\/j.media.2025.103614","volume":"104","author":"Q Men","year":"2025","unstructured":"Men Q, Zhao H, Drukker L, Papageorghiou AT, Noble JA. ScanAhead: simplifying standard plane acquisition of fetal head ultrasound. Med Image Anal. 2025;104:103614.","journal-title":"Med Image Anal"},{"key":"1486_CR16","doi-asserted-by":"publisher","first-page":"e2400478","DOI":"10.1200\/PO-24-00478","volume":"8","author":"J Lammert","year":"2024","unstructured":"Lammert J, Dreyer T, Mathes S, Kuligin L, Borm KJ, Schatz UA, et al. Expert-guided large language models for clinical decision support in precision oncology. JCO Precis Oncol. 2024;8:e2400478.","journal-title":"JCO Precis Oncol"},{"key":"1486_CR17","unstructured":"Jiang B, Li L, Li X, Li Z, Feng X, Kong L, et\u00a0al. Understanding the role of LLMs in multimodal evaluation benchmarks. 2024. https:\/\/arxiv.org\/abs\/2410.12329."},{"key":"1486_CR18","doi-asserted-by":"crossref","unstructured":"Yan LKQ, Li M, Zhang Y, Yin CH, Fei C, Peng B, et\u00a0al. Large language model benchmarks in medical tasks. 2024. https:\/\/arxiv.org\/abs\/2410.21348.","DOI":"10.31219\/osf.io\/8j7d3"},{"key":"1486_CR19","unstructured":"Zhang S, Sambara S, Banerjee O, Acosta J, Fahrner LJ, Rajpurkar P. Radflag: a black-box hallucination detection method for medical vision language models. 2024. arXiv preprint arXiv:2411.00299."},{"key":"1486_CR20","doi-asserted-by":"publisher","DOI":"10.1101\/2024.09.27.24314506","author":"A Li","year":"2024","unstructured":"Li A, Shrestha R, Jegatheeswaran T, Chan HO, Hong C, Joshi R. Mitigating hallucinations in large language models: a comparative study of RAG-enhanced vs. Human-generated medical templates. medRxiv. 2024. https:\/\/doi.org\/10.1101\/2024.09.27.24314506.","journal-title":"medRxiv"},{"key":"1486_CR21","unstructured":"Das AB, Sakib SK, Ahmed S. Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities. 2025. arXiv preprint arXiv:2508.07031."},{"issue":"1","key":"1486_CR22","doi-asserted-by":"publisher","first-page":"e59823","DOI":"10.2196\/59823","volume":"14","author":"D Roustan","year":"2025","unstructured":"Roustan D, Bastardot F, et al. The clinicians\u2019 guide to large language models: a general perspective with a focus on hallucinations. Interact J Med Res. 2025;14(1):e59823.","journal-title":"Interact J Med Res"},{"issue":"2","key":"1486_CR23","first-page":"75","volume":"31","author":"B Ko\u00e7ak","year":"2025","unstructured":"Ko\u00e7ak B, Ponsiglione A, Stanzione A, Bluethgen C, Santinha J, Ugga L, et al. Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects. Diagn Interv Radiol. 2025;31(2):75.","journal-title":"Diagn Interv Radiol"},{"key":"1486_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3585745","author":"W Elsharif","year":"2025","unstructured":"Elsharif W, Alzubaidi M, Agus M. Cultural bias in text-to-image models: a systematic review of bias identification, evaluation and mitigation strategies. IEEE Access. 2025. https:\/\/doi.org\/10.1109\/ACCESS.2025.3585745.","journal-title":"IEEE Access"},{"issue":"1","key":"1486_CR25","doi-asserted-by":"publisher","first-page":"4581","DOI":"10.1038\/s41467-022-32186-3","volume":"13","author":"MA Ricci Lara","year":"2022","unstructured":"Ricci Lara MA, Echeveste R, Ferrante E. Addressing fairness in artificial intelligence for medical imaging. Nat Commun. 2022;13(1):4581.","journal-title":"Nat Commun"},{"issue":"1","key":"1486_CR26","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1038\/s41746-025-01739-3","volume":"8","author":"MC Fiorentino","year":"2025","unstructured":"Fiorentino MC, Moccia S, Cosmo MD, Frontoni E, Giovanola B, Tiribelli S. Uncovering ethical biases in publicly available fetal ultrasound datasets. Npj Digit Med. 2025;8(1):355.","journal-title":"Npj Digit Med"},{"issue":"13","key":"1486_CR27","doi-asserted-by":"publisher","first-page":"eadq0305","DOI":"10.1126\/sciadv.adq0305","volume":"11","author":"Y Yang","year":"2025","unstructured":"Yang Y, Liu Y, Liu X, Gulhane A, Mastrodicasa D, Wu W, et al. Demographic bias of expert-level vision-language foundation models in medical imaging. Sci Adv. 2025;11(13):eadq0305.","journal-title":"Sci Adv"},{"issue":"1","key":"1486_CR28","doi-asserted-by":"publisher","first-page":"10200","DOI":"10.1038\/s41598-020-67076-5","volume":"10","author":"XP Burgos-Artizzu","year":"2020","unstructured":"Burgos-Artizzu XP, Coronado-Guti\u00e9rrez D, Valenzuela-Alcaraz B, Bonet-Carne E, Eixarch E, Crispi F, et al. Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes. Sci Rep. 2020;10(1):10200.","journal-title":"Sci Rep"},{"issue":"2","key":"1486_CR29","doi-asserted-by":"publisher","first-page":"B11","DOI":"10.1016\/j.ajog.2022.03.039","volume":"227","author":"T Lee","year":"2022","unstructured":"Lee T, Stone J, Jain V, Avtalion N, Wickersham J, Haddock J, et al. Society for maternal-fetal medicine special statement: best-practice recommendations for ultrasound network connectivity. Am J Obstet Gynecol. 2022;227(2):B11-23. https:\/\/doi.org\/10.1016\/j.ajog.2022.03.039.","journal-title":"Am J Obstet Gynecol"},{"issue":"1","key":"1486_CR30","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1097\/AOG.0000000000003049","volume":"133","author":"C Jain","year":"2019","unstructured":"Jain C. ACOG Committee Opinion No. 723: guidelines for diagnostic imaging during pregnancy and lactation. Obstet Gynecol. 2019;133(1):186.","journal-title":"Obstet Gynecol"},{"issue":"6","key":"1486_CR31","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1002\/uog.24888","volume":"59","author":"L Salomon","year":"2022","unstructured":"Salomon L, Alfirevic Z, Berghella V, Bilardo C, Chalouhi G, Costa FDS, et al. ISUOG Practice Guidelines (updated): performance of the routine mid-trimester fetal ultrasound scan. Ultrasound Obstet Gynecol. 2022;59(6):840\u201356.","journal-title":"Ultrasound Obstet Gynecol"},{"key":"1486_CR32","unstructured":"Chiang WL, Zheng L, Sheng Y, Angelopoulos AN, Li T, Li D, et\u00a0al. Chatbot Arena: an open platform for evaluating LLMs by human preference. 2024. https:\/\/arxiv.org\/abs\/2403.04132."},{"key":"1486_CR33","doi-asserted-by":"publisher","DOI":"10.4324\/9781315642956","volume-title":"Designing experiments and analyzing data: a model comparison perspective","author":"SE Maxwell","year":"2017","unstructured":"Maxwell SE, Delaney HD, Kelley K. Designing experiments and analyzing data: a model comparison perspective. London: Routledge; 2017."},{"issue":"2","key":"1486_CR34","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.edurev.2010.12.001","volume":"6","author":"JT Richardson","year":"2011","unstructured":"Richardson JT. Eta squared and partial eta squared as measures of effect size in educational research. Educ Res Rev. 2011;6(2):135\u201347.","journal-title":"Educ Res Rev"},{"issue":"1","key":"1486_CR35","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1111\/j.1541-0420.2005.00389.x","volume":"62","author":"B Rosner","year":"2006","unstructured":"Rosner B, Glynn RJ, Lee MLT. The Wilcoxon signed rank test for paired comparisons of clustered data. Biometrics. 2006;62(1):185\u201392.","journal-title":"Biometrics"},{"issue":"5","key":"1486_CR36","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1111\/all.15700","volume":"78","author":"M Ordak","year":"2023","unstructured":"Ordak M. Multiple comparisons and effect size: statistical recommendations for authors planning to submit an article to allergy. Allergy. 2023;78(5):1145\u20137.","journal-title":"Allergy"},{"issue":"5","key":"1486_CR37","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1111\/opo.12131","volume":"34","author":"RA Armstrong","year":"2014","unstructured":"Armstrong RA. When to use the Bonferroni correction. Ophthalmic Physiol Opt. 2014;34(5):502\u20138.","journal-title":"Ophthalmic Physiol Opt"}],"container-title":["BioMedical Engineering OnLine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-025-01486-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12938-025-01486-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-025-01486-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:33:02Z","timestamp":1768314782000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12938-025-01486-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1486"],"URL":"https:\/\/doi.org\/10.1186\/s12938-025-01486-2","relation":{},"ISSN":["1475-925X"],"issn-type":[{"value":"1475-925X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,9]]},"assertion":[{"value":"10 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6"}}