Abstract
Vision foundation models (VFMs) are increasingly being developed for radiological imaging, yet their definition, development, and evaluation remain heterogeneous. We conducted a PRISMA-Scr scoping review of peer-reviewed studies published between January 2017 and March 2026 describing foundation models trained exclusively on radiological imaging data.
Data Scale and Heterogeneity
Sixty-seven studies were included and mapped across three pillars: data scale and heterogeneity, architectural and pretraining scalability, and downstream transferability and generalization. Datasets primarily covered brain MRI, thoracoabdominal CT, and chest X-ray, ranging from fewer than 100,000 samples to multi-million-image cohorts.
Architecture and Pretraining
Transformer-based architectures and self-supervised pretraining predominated, particularly masked image modeling, contrastive learning, and multi-stage approaches. Evaluation focused mainly on segmentation and classification, whereas cross-center, cross-scanner, anatomical, and modality-shift validation was inconsistently reported.
Clinical Translation
Alignment with FUTURE-AI principles was uneven. Overall, radiology-specific VFMs show promising transferability, but clinical translation remains constrained by limited data representativeness, heterogeneous benchmarks, incomplete reporting, and insufficient deployment-oriented evaluation.
Blogger's Review: The development of vision foundation models in radiology is advancing, but achieving clinical application requires addressing issues of data quality and consistency in evaluation standards. Future research must emphasize data representativeness and practical application outcomes to enhance the clinical translation of VFMs.