A generalizable large-scale foundation model for musculoskeletal radiographs

2026-02-03

AI Summary

This work addresses the limitations of existing AI models for musculoskeletal X-ray analysis, which are often task-specific, reliant on extensive labeled data, and exhibit poor generalization. To overcome these challenges, the authors present SKELEX, a foundational self-supervised model pretrained on 1.2 million diverse X-ray images. SKELEX establishes the first unified representation capable of spanning multiple diseases and anatomical regions without task-specific fine-tuning. The model supports a broad range of downstream diagnostic tasks, features zero-shot anomaly localization, and incorporates an interpretable region-guided prediction mechanism. Evaluated across twelve distinct tasks, SKELEX significantly outperforms baseline methods, demonstrates robust performance on external datasets, and has been deployed in a web application for bone tumor prediction.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Artificial intelligence (AI) has shown promise in detecting and characterizing musculoskeletal diseases from radiographs. However, most existing models remain task-specific, annotation-dependent, and limited in generalizability across diseases and anatomical regions. Although a generalizable foundation model trained on large-scale musculoskeletal radiographs is clinically needed, publicly available datasets remain limited in size and lack sufficient diversity to enable training across a wide range of musculoskeletal conditions and anatomical sites. Here, we present SKELEX, a large-scale foundation model for musculoskeletal radiographs, trained using self-supervised learning on 1.2 million diverse, condition-rich images. The model was evaluated on 12 downstream diagnostic tasks and generally outperformed baselines in fracture detection, osteoarthritis grading, and bone tumor classification. Furthermore, SKELEX demonstrated zero-shot abnormality localization, producing error maps that identified pathologic regions without task-specific training. Building on this capability, we developed an interpretable, region-guided model for predicting bone tumors, which maintained robust performance on independent external datasets and was deployed as a publicly accessible web application. Overall, SKELEX provides a scalable, label-efficient, and generalizable AI framework for musculoskeletal imaging, establishing a foundation for both clinical translation and data-efficient research in musculoskeletal radiology.

Problem

• musculoskeletal radiographs
• foundation model
• generalizability
• self-supervised learning
• data diversity

Innovation

• foundation model
• self-supervised learning
• zero-shot localization
• musculoskeletal radiographs
• generalizable AI