OrthoDiffusion: A Generalizable Multi-Task Diffusion Foundation Model for Musculoskeletal MRI Interpretation

TL;DR

OrthoDiffusion is a diffusion-based foundation model that leverages self-supervised learning on unlabeled knee MRI scans to perform multi-task musculoskeletal MRI interpretation, demonstrating high accuracy, robustness, and transferability across joints and clinical settings.

Contribution

This work introduces a novel multi-view diffusion model that learns robust anatomical features from unlabeled MRI data for diverse diagnostic tasks, advancing the application of foundation models in medical imaging.

Findings

Achieves high accuracy in knee structure segmentation and abnormality detection.

Maintains performance with limited labeled data (as low as 10%).

Transfers effectively to other joints like ankle and shoulder.

Abstract

Musculoskeletal disorders represent a significant global health burden and are a leading cause of disability worldwide. While MRI is essential for accurate diagnosis, its interpretation remains exceptionally challenging. Radiologists must identify multiple potential abnormalities within complex anatomical structures across different imaging planes, a process that requires significant expertise and is prone to variability. We developed OrthoDiffusion, a unified diffusion-based foundation model designed for multi-task musculoskeletal MRI interpretation. The framework utilizes three orientation-specific 3D diffusion models, pre-trained in a self-supervised manner on 15,948 unlabeled knee MRI scans, to learn robust anatomical features from sagittal, coronal, and axial views. These view-specific representations are integrated to support diverse clinical tasks, including anatomical segmentation and multi-label diagnosis. Our evaluation demonstrates that OrthoDiffusion achieves excellent performance in the segmentation of 11 knee structures and the detection of 8 knee abnormalities. The model exhibited remarkable robustness across different clinical centers and MRI field strengths, consistently outperforming traditional supervised models. Notably, in settings where labeled data was scarce, OrthoDiffusion maintained high diagnostic precision using only 10\% of training labels. Furthermore, the anatomical representations learned from knee imaging proved highly transferable to other joints, achieving strong diagnostic performance across 11 diseases of the ankle and shoulder. These findings suggest that diffusion-based foundation models can serve as a unified platform for multi-disease diagnosis and anatomical segmentation, potentially improving the efficiency and accuracy of musculoskeletal MRI interpretation in real-world clinical workflows.