Unimodal imaging foundation models and vision-language models in MRI: A systematic review of emerging methods and clinical applications.
Authors
Affiliations (11)
Affiliations (11)
- Biomedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
- Biomedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
- Department of Orthopedics, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
- Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
- Department of General Surgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, China.
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
- Department of Neuroradiology, University Medical Center Mainz, Johannes Gutenberg University, Langenbeckstr. 1, 55131 Mainz, Germany.
- Department of Oncology and Haemato-Oncology, University of Milan, Milano, Italy; Division of Radiology, IRCCS European Institute of Oncology, Milan, Italy.
- East River Medical Imaging, New York, NY 10021, USA; Department of Radiology, Cornell Medicine, New York, NY 10065, USA.
- Biomedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
- Biomedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA. Electronic address: [email protected].
Abstract
Artificial intelligence in medical imaging is shifting from task-specific algorithms toward adaptable foundation models (FMs) and vision-language models (VLMs). However, applying these models to MRI remains challenging because clinical interpretation requires integrating multi-parametric, volumetric imaging across multiple sequences with clinical context. This systematic review evaluates 35 studies on unimodal FMs and multimodal VLMs in MRI, summarizing emerging architectures, downstream applications, and challenges to clinical translation. Current research is concentrated in neuroimaging, with diagnostic classification representing the most mature application. Segmentation and outcome prediction also show promise, whereas automated report generation remains limited by poor clinical fidelity despite strong linguistic fluency. Broader adoption is hindered by heterogeneous MRI acquisition, limited large-scale paired image-text datasets, and inadequate safety-focused evaluation metrics. Advancing clinical translation will require standardized multicenter datasets, stronger integration with electronic health records and pathology, robust evaluation frameworks, and improved model explainability.