{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:10:28Z","timestamp":1784182228328,"version":"3.55.0"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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. Radiol."],"abstract":"<jats:p>\n                    Radiology artificial intelligence (AI) is increasingly developed on large external datasets and deployed across institutions, but real-world model performance may vary substantially after implementation. Imaging AI interacts with a local ecosystem shaped by scanner hardware, acquisition protocols, reconstruction methods, technologist practices, disease prevalence, patient demographics, reporting conventions, and clinical workflow. These factors can produce domain shift, degrade calibration, alter false-positive and false-negative patterns, and affect clinical utility. In this article, we argue that radiology AI should move beyond a \u201cplug-and-play\u201d deployment paradigm toward institution-calibrated AI stewardship. We propose an institution-specific radiology AI performance profile, conceptually analogous to a local antibiogram, to summarize how AI tools perform within a specific clinical environment. Unlike prior MLOps and radiology AI governance frameworks, the proposed profile translates lifecycle management into a radiology-specific, locally maintainable artifact that captures technical context, clinical context, performance metrics, reference standards, equity checks, workflow effects, and governance triggers. The framework applies not only to diagnostic decision support, but also to research cohort generation and radiology education, where local reporting language, imaging protocols, and case mix may strongly influence model reliability. We emphasize that institution-specific calibration does not require every hospital to develop AI models\n                    <jats:italic>de novo<\/jats:italic>\n                    . Rather, externally developed, vendor-based, and foundation-model approaches should be paired with local validation, cautious threshold adjustment, calibration when applicable, surveillance for drift and protocol changes, and multidisciplinary governance. Responsible radiology AI deployment should therefore ask not only whether a model is accurate, but whether it remains accurate, relevant, equitable, and useful locally over time.\n                  <\/jats:p>","DOI":"10.3389\/fradi.2026.1902217","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:40:00Z","timestamp":1784180400000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["From plug-and-play to institution-calibrated radiology AI: a practical framework for operationalizing local validation, monitoring and governance"],"prefix":"10.3389","volume":"6","author":[{"given":"Muhammad","family":"Awais","sequence":"first","affiliation":[{"name":"Department of Radiology, Aga Khan University Hospital","place":["Karachi, Sindh, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul","family":"Rehman","sequence":"additional","affiliation":[{"name":"Department of Medicine, TidalHealth Peninsula Regional","place":["Salisbury, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"P1041","DOI":"10.1016\/j.jacr.2025.05.016","article-title":"AI in action: a road map from the radiology AI council for effective model evaluation and deployment","volume":"22","author":"Trivedi","year":"2025","journal-title":"J Am Coll Radiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"P965","DOI":"10.1016\/j.jacr.2025.12.028","article-title":"Factors impacting the performance of deep learning detection of pulmonary emboli","volume":"23","author":"Sorin","year":"2025","journal-title":"J Am Coll Radiol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"8803","DOI":"10.1097\/MS9.0000000000004166","article-title":"Assessing the generalizability of artificial intelligence in radiology: a systematic review of performance across different clinical settings","volume":"87","author":"Suleman","year":"2025","journal-title":"Ann Med Surg"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/tbme.2021.3117407","article-title":"Domain adaptation for medical image analysis: a survey","volume":"69","author":"Guan","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"B5","author":"Krishnan","year":""},{"key":"B6","doi-asserted-by":"publisher","first-page":"1342937","DOI":"10.3389\/fpubh.2024.1342937","article-title":"Resilience-aware MLOps for AI-based medical diagnostic system","volume":"12","author":"Moskalenko","year":"2024","journal-title":"Front Public Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"939292","DOI":"10.3389\/fdgth.2022.939292","article-title":"Clinical deployment environments: five pillars of translational machine learning for health","volume":"4","author":"Harris","year":"2022","journal-title":"Front Digit Health"},{"key":"B8","doi-asserted-by":"publisher","first-page":"20374","DOI":"10.1109\/ACCESS.2024.3521279","article-title":"MLHOps: machine learning health operations","volume":"13","author":"Khattak","year":"2024","journal-title":"IEEE Access"},{"key":"B9","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1177\/08465371231222229","article-title":"Developing, purchasing, implementing and monitoring AI tools in radiology: practical considerations. A multi-society statement from the ACR, CAR, ESR, RANZCR & RSNA","volume":"75","author":"Brady","year":"2024","journal-title":"Can Assoc Radiol J"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e240225","DOI":"10.1148\/ryai.240225","article-title":"Clinical, cultural, computational, and regulatory considerations to deploy AI in radiology: perspectives of RSNA and MICCAI experts","volume":"6","author":"Linguraru","year":"2024","journal-title":"Radiol Artif Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"6828","DOI":"10.1007\/s00330-025-11654-6","article-title":"Medical machine learning operations: a framework to facilitate clinical AI development and deployment in radiology","volume":"35","author":"de Almeida","year":"2025","journal-title":"Eur Radiol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"ooac094","DOI":"10.1093\/jamiaopen\/ooac094","article-title":"ACR\u2019s connect and AI-LAB technical framework","volume":"5","author":"Brink","year":"2022","journal-title":"JAMIA Open"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2026.04.024","article-title":"ACR\u2019s assess-AI: a registry for real-world performance monitoring of clinical imaging AI","author":"Coombs","year":"2026","journal-title":"J Am Coll Radiol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1016\/j.jacr.2025.02.008","article-title":"The road map for ACR practice accreditation for radiology artificial intelligence","volume":"22","author":"Larson","year":"2025","journal-title":"J Am Coll Radiol"},{"key":"B15","volume-title":"Regulatory Considerations on Artificial Intelligence for Health","year":"2023"},{"key":"B16","volume-title":"Artificial Intelligence (AI) Technologies to Aid Opportunistic Detection of Vertebral Fragility Fractures: Early Value Assessment (HealthTech Guidance HTG760)","year":"2025"},{"key":"B17","doi-asserted-by":"publisher","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 Imaging"},{"key":"B18","year":""}],"container-title":["Frontiers in Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1902217\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:40:01Z","timestamp":1784180401000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1902217\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":18,"alternative-id":["10.3389\/fradi.2026.1902217"],"URL":"https:\/\/doi.org\/10.3389\/fradi.2026.1902217","relation":{},"ISSN":["2673-8740"],"issn-type":[{"value":"2673-8740","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"article-number":"1902217"}}