Foundation models for radiology: fundamentals, applications, opportunities, challenges, risks, and prospects.
Authors
Affiliations (9)
Affiliations (9)
- University Hospital Basel, Department of Diagnostic and Interventional Neuroradiology, Basel, Switzerland.
- University Children's Hospital Basel, Department of Pediatric Radiology, Basel, Switzerland.
- University Hospital Zurich, Institute for Diagnostic and Interventional Radiology, Zurich, Switzerland.
- Department of Medicine, Surgery and Dentistry, University of Salerno, Baronissi, Italy.
- University of Crete School of Medicine, Artificial Intelligence and Translational Imaging (ATI) Lab, Department of Radiology, Crete, Greece.
- Foundation for Research and Technology (ICS-FORTH), Institute of Computer Science, Computational Biomedicine Lab, Crete, Greece.
- Karolinska Institute, Department of Clinical Science, Intervention and Technology (CLINTEC), Division of Radiology, Stockholm, Sweden.
- University of Naples Federico II, Department of Advanced Biomedical Sciences, Naples, Italy.
- Başakşehir Çam and Sakura City Hospital, Department of Radiology, İstanbul, Türkiye.
Abstract
Foundation models (FMs) represent a significant evolution in artificial intelligence (AI), impacting diverse fields. Within radiology, this evolution offers greater adaptability, multimodal integration, and improved generalizability compared with traditional narrow AI. Utilizing large-scale pre-training and efficient fine-tuning, FMs can support diverse applications, including image interpretation, report generation, integrative diagnostics combining imaging with clinical/laboratory data, and synthetic data creation, holding significant promise for advancements in precision medicine. However, clinical translation of FMs faces several substantial challenges. Key concerns include the inherent opacity of model decision-making processes, environmental and social sustainability issues, risks to data privacy, complex ethical considerations, such as bias and fairness, and navigating the uncertainty of regulatory frameworks. Moreover, rigorous validation is essential to address inherent stochasticity and the risk of hallucination. This international collaborative effort provides a comprehensive overview of the fundamentals, applications, opportunities, challenges, and prospects of FMs, aiming to guide their responsible and effective adoption in radiology and healthcare.