AI in Radiology: Adoption, Bias, Interoperability, Federated Learning and What Comes Next

Описание

How close is AI to real clinical adoption in radiology and medical imaging?In this episode of Imaging Informatics Unplugged, Jason Nagels talks with Dr. Khaled Younis about where AI and machine learning really stand today in radiology, why adoption is still uneven, and what needs to happen next.Dr. Younis brings deep experience across AI research, clinical imaging, and global standards. You can learn more about his work here:https://medaiconsult.com/https://www.linkedin.com/in/dryounis/The conversation digs into the biggest barriers holding imaging AI back, including clinical validation, FDA and regulatory scrutiny, interoperability challenges across PACS, RIS, EHR, DICOM, HL7 and FHIR, as well as bias, trust, explainability and real-world deployment. It also looks at how early CAD systems compare with today’s deep learning era, why many AI vendors still treat standards as an afterthought, and how IHE and ISO are shaping the future of trustworthy AI in imaging.You’ll also hear a practical discussion on federated learning, multi-site collaboration, synthetic data, tumor segmentation, structured AI results, and the role of standards in making AI outputs usable across clinical workflows. Dr. Younis shares where he sees the biggest opportunities ahead, including real-time decision support, AI-assisted intervention, multimodal data integration, and more open, interoperable healthcare ecosystems.If you’re looking to build a stronger foundation in imaging informatics, workflows, and standards like DICOM, HL7, FHIR, and IHE, visit:https://www.nagelsconsulting.com/You can also check out the CIIP Foundations program for a structured, practical approach to understanding how these concepts apply in real-world imaging environments.Topics coveredAI in radiology adoptionMedical imaging AI barriersFDA approval and post-market surveillanceInteroperability in radiology AIIHE profiles and AI resultsISO and trustworthy AIBias in healthcare AIFederated learning in medical imagingSynthetic data for AI trainingStructured reporting and