MRI-CORE: A Foundation Model for Magnetic Resonance Imaging
This addresses data efficiency for medical imaging researchers and clinicians, enabling more accessible AI tools, but it is incremental as it builds on existing foundation model concepts applied to MRI.
The authors tackled the challenge of training deep learning models for MRI with limited labeled data by introducing MRI-CORE, a vision foundation model trained on over 6 million MRI slices, which achieved notable improvements in 13 segmentation tasks, image classification, and zero-shot segmentation.
The widespread use of Magnetic Resonance Imaging (MRI) in combination with deep learning shows promise for many high-impact automated diagnostic and prognostic tools. However, training new models requires large amounts of labeled data, a challenge due to high cost of precise annotations and data privacy. To address this issue, we introduce the MRI-CORE, a vision foundation model trained using more than 6 million slices from over 110 thousand MRI volumes across 18 body locations. Our experiments show notable improvements in performance over state-of-the-art methods in 13 data-restricted segmentation tasks, as well as in image classification, and zero-shot segmentation, showing the strong potential of MRI-CORE to enable data-efficient development of artificial intelligence models. We also present data on which strategies yield most useful foundation models and a novel analysis relating similarity between pre-training and downstream task data with transfer learning performance. Our model is publicly available with a permissive license.