A generalizable large-scale foundation model for musculoskeletal radiographs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Shinn, Lee, Soobin, Shin, Kyoungseob, Kim, Han-Soo, Kim, Yongsung, Kim, Minsu, Nam, Juhong, Ko, Somang, Kwon, Daeheon, Huh, Wook, Han, Ilkyu, Kwon, Sunghoon
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912871688962048
author Kim, Shinn
Lee, Soobin
Shin, Kyoungseob
Kim, Han-Soo
Kim, Yongsung
Kim, Minsu
Nam, Juhong
Ko, Somang
Kwon, Daeheon
Huh, Wook
Han, Ilkyu
Kwon, Sunghoon
author_facet Kim, Shinn
Lee, Soobin
Shin, Kyoungseob
Kim, Han-Soo
Kim, Yongsung
Kim, Minsu
Nam, Juhong
Ko, Somang
Kwon, Daeheon
Huh, Wook
Han, Ilkyu
Kwon, Sunghoon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03076
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A generalizable large-scale foundation model for musculoskeletal radiographs
Kim, Shinn
Lee, Soobin
Shin, Kyoungseob
Kim, Han-Soo
Kim, Yongsung
Kim, Minsu
Nam, Juhong
Ko, Somang
Kwon, Daeheon
Huh, Wook
Han, Ilkyu
Kwon, Sunghoon
Computer Vision and Pattern Recognition
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.
title A generalizable large-scale foundation model for musculoskeletal radiographs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.03076