{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T10:12:46Z","timestamp":1791972766497,"version":"4.3.4"},"reference-count":25,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:00:00Z","timestamp":1764115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mayo Clinic Department of Radiology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>The field of radiology is experiencing rapid adoption of large language models (LLMs), yet their tendency to generate hallucinations (plausible but incorrect information) remains a significant barrier to trust. This comprehensive review evaluates emerging agentic artificial intelligence (AI) approaches, including multi-agent role-based systems, retrieval-augmented generation (RAG), and uncertainty quantification, to assess their potential for reducing hallucinations in radiology workflows. Evidence from 2024 to 2025 demonstrates that agentic AI can improve diagnostic accuracy and reduce error rates, though these methods remain computationally demanding and lack comprehensive clinical validation. Multi-agent frameworks enable cross-validation through role-based specialization and systematic workflow orchestration, while RAG strategies enhance accuracy by grounding responses in verified medical literature. Within multi-agent systems, uncertainty quantification enables agents to communicate confidence levels to one another, allowing them to appropriately weigh each other\u2019s contributions during collaborative analysis. While multi-agent frameworks and RAG strategies show significant promise, practical deployment will require careful integration with human oversight, robust evaluation metrics tailored to medical imaging tasks, and regulatory adaptation to ensure safe clinical use in diverse patient populations and imaging modalities.<\/jats:p>","DOI":"10.3390\/bioengineering12121303","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T11:43:22Z","timestamp":1764157402000},"page":"1303","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3223-9059","authenticated-orcid":false,"given":"Sara","family":"Salehi","sequence":"first","affiliation":[{"name":"Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5848-7072","authenticated-orcid":false,"given":"Yashbir","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0163-0963","authenticated-orcid":false,"given":"Kelly K.","family":"Horst","sequence":"additional","affiliation":[{"name":"Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8226-2319","authenticated-orcid":false,"given":"Quincy A.","family":"Hathaway","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-6095","authenticated-orcid":false,"given":"Bradley J.","family":"Erickson","sequence":"additional","affiliation":[{"name":"Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"ref_1","first-page":"123","article-title":"From Chat to Act: Large Language Model Agents and Agentic AI as the Next Frontier of AI in Rheumatology","volume":"64","author":"Benavent","year":"2025","journal-title":"Rheumatology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e59505","DOI":"10.2196\/59505","article-title":"Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook","volume":"26","author":"AlSaad","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e2432022","DOI":"10.2214\/AJR.24.32022","article-title":"ChatGPT and Large Language Models in Radiology: Perspectives From the Field","volume":"223","author":"Bahl","year":"2024","journal-title":"Am. J. Roentgenol."},{"key":"ref_4","unstructured":"Zuo, K., and Jiang, Y. (2024). MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1007\/s00330-025-11484-6","article-title":"Human-AI Collaboration in Large Language Model-Assisted Brain MRI Differential Diagnosis: A Usability Study","volume":"35","author":"Kim","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref_6","unstructured":"Seth, A., Manocha, D., and Agarwal, C. (2024). Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models. arXiv."},{"key":"ref_7","unstructured":"Das, A.B., Sakib, S.K., and Ahmed, S. (2025). Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities. arXiv."},{"key":"ref_8","unstructured":"Lin, Z., Niu, Z., Wang, Z., and Xu, Y. (2024). Interpreting and Mitigating Hallucination in MLLMs Through Multi-Agent Debate. arXiv."},{"key":"ref_9","unstructured":"Zhang, S., Sambara, S., Banerjee, O., Acosta, J., Fahrner, L.J., and Rajpurkar, P. (2024). RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Pandit, S., Xu, J., Hong, J., Wang, Z., Chen, T., Xu, K., and Ding, Y. (2025). MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. arXiv.","DOI":"10.18653\/v1\/2025.emnlp-main.143"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s41746-025-01802-z","article-title":"Retrieval-Augmented Generation Elevates Local LLM Quality in Radiology Contrast Media Consultation","volume":"8","author":"Wada","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_12","unstructured":"Banerjee, O., Zhou, H.Y., Adithan, S., Kwak, S., Wu, K., and Rajpurkar, P. (2024). Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generation. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sun, X., Li, J., Zhong, Y., Zhao, D., and Yan, R. (2025, January 6\u201311). Towards Detecting LLMs Hallucination via Markov Chain-Based Multi-Agent Debate Framework. Proceedings of the ICASSP 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Hyderabad, India.","DOI":"10.1109\/ICASSP49660.2025.10889448"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yoffe, L., Amayuelas, A., and Wang, W.Y. (2024). DebUnc: Improving Large Language Model Agent Communication with Uncertainty Metrics. arXiv.","DOI":"10.18653\/v1\/2025.findings-emnlp.1265"},{"key":"ref_15","unstructured":"Kalai, A.T., Nachum, O., Vempala, S.S., and Zhang, E. (2025). Why Language Models Hallucinate. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bennai, M.T., Guessoum, Z., Mazouzi, S., Cormier, S., and Mezghiche, M. (2023). Multi-agent medical image segmentation: A survey. Comput. Methods Programs Biomed., 232.","DOI":"10.1016\/j.cmpb.2023.107444"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7998","DOI":"10.1007\/s00330-022-08784-6","article-title":"Radiology artificial intelligence: A systematic review and evaluation of methods (RAISE)","volume":"32","author":"Kelly","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13244-025-01905-x","article-title":"Guiding AI in radiology: ESR\u2019s recommendations for effective implementation of the European AI Act","volume":"16","author":"Kotter","year":"2025","journal-title":"Insights Into Imaging"},{"key":"ref_19","first-page":"1","article-title":"Transparency of medical artificial intelligence systems","volume":"17","author":"Kim","year":"2025","journal-title":"Nat. Rev. Bioeng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ruan, C., Huang, C., and Yang, Y. (March, January 27). Comprehensive evaluation of multimodal ai models in medical imaging diagnosis: From data augmentation to preference-based comparison. Proceedings of the 2025 13th International Conference on Bioinformatics and Computational Biology (ICBCB), Seoul, Republic of Korea. (2025, February).","DOI":"10.1109\/ICBCB64873.2025.11198079"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chow, J.C., and Li, K. (2025). Large language models in medical chatbots: Opportunities, challenges, and the need to address AI risks. Information, 16.","DOI":"10.3390\/info16070549"},{"key":"ref_22","unstructured":"Jin, W., Vincent, N., and Hamarneh, G. (2025, November 17). Position: AI for Just Work: Constructing Diverse Imaginations of AI beyond \u201cReplacing Humans\u201d. Available online: https:\/\/openreview.net\/forum?id=n1rqG1LnRF."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Singh, Y., Andersen, J.B., Hathaway, Q.A., Vera-Garcia, D.V., Keishing, V., Venkatesh, S.K., Salehi, S., Povero, D., Wallace, M.B., and Gores, G.J. (2025). Leveraging Multimodal Foundation Models in Biliary Tract Cancer Research. Tomography, 11.","DOI":"10.3390\/tomography11090096"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Salehi, S., Singh, Y., Habibi, P., and Erickson, B.J. (2025). Beyond Single Systems: How Multi-Agent AI Is Reshaping Ethics in Radiology. Bioengineering, 12.","DOI":"10.3390\/bioengineering12101100"},{"key":"ref_25","unstructured":"Zhu, Y., He, Z., Hu, H., Zheng, X., Zhang, X., Wang, Z., Gao, J., Ma, L., and Yu, L. (2025). MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks. arXiv."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1303\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T12:25:27Z","timestamp":1764159927000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1303"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":25,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bioengineering12121303"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12121303","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]}}}