OpenMSK: A modular open-source framework for comprehensive analysis of imaging biomarkers in knee osteoarthritis.
5 affiliations
- 1Department of Radiology, Stanford University, CA, USA.
- 2Department of Bioengineering, Stanford University, CA, USA.
- 3College of Osteopathic Medicine of the Pacific, Western University of Health Sciences, CA, USA.
- 4Department of Clinical Physiology, Nuclear Medicine & PET, Rigshospitalet, Copenhagen University Hospital, Denmark.
- 5Department of Orthopaedic Surgery, Stanford University, CA, USA.
Abstract
Objective
To develop and validate a fully automated, extendable, open-source AI-driven pipeline capable of knee magnetic resonance imaging (MRI) segmentation and quantitative extraction of MRI and positron emission tomography (PET) imaging biomarkers.Design
For model training, open-source knee MRI data from 347 knees acquired across 7 scanners using multiple gradient-echo sequences were used. An independent test set of 20 knees from 3T PET-MRI examinations were used for evaluation in this prospective reliability and agreement study. The pipeline segmented femoral, tibial, and patellar bones and cartilage, and medial and lateral menisci using three different deep learning models. Quantitative outputs included cartilage thickness and T₂ relaxation times, meniscus volume and T₂∗ relaxation times, bone shape scores, and static and kinetic subchondral bone PET measures. Manual segmentations from two annotators served as reference standards. Segmentation performance was assessed using Dice similarity coefficients (DSC), average symmetric surface distances, and volume differences. Quantitative outcome agreement was evaluated using intraclass correlation coefficients (ICC), Pearson correlations, and root mean square error.Results
Automated segmentations demonstrated high spatial agreement with manual annotations, with DSCs ranging from 0.84 to 0.98 across all tissues. Quantitative PET-MRI biomarkers generally demonstrated high agreement, although confidence intervals were wide for several biomarkers.Conclusion
OpenMSK enables multi-tissue knee segmentation and generation of quantitative MRI and PET biomarkers, with performance assessed against two independent annotators and across different U-Net-based segmentation architectures. As a freely available, modular platform, OpenMSK lowers technical barriers to whole-joint quantitative imaging and provides a standardized foundation for OA research and clinical translation.
Related
- Comprehensive regulatory and developmental landscape of cell–scaffold combination therapies for osteoarthritis
- Identification of Mitochondrial Dynamics-Related Genes as Diagnostic Biomarkers for Osteoarthritis Using Weighted Gene Co-expression Network Analysis and Machine Learning
- Effects of Mobilization with Movement Versus Sham Mobilization on Inflammatory Biomarkers and Clinical Outcomes in Patients with Knee Osteoarthritis: A Randomized Double-Blind Clinical Trial
- Biomarkers and Risk Prediction in Cardiovascular–Kidney–Metabolic Syndrome: A Comprehensive Review
- Synovial oxidative stress biomarkers are not associated with radiological severity in knee osteoarthritis: a prospective cross-sectional study.
BibTeX
@article{goyal2026openmsk,
title = {{OpenMSK: A modular open-source framework for comprehensive analysis of imaging biomarkers in knee osteoarthritis.}},
author = {Ananya Goyal and Francesca Belibi and Vyoma Sahani and Rune Pedersen and Yael Vainberg and Ashley Williams and Constance Chu and Bryan Haddock and Garry E Gold and Akshay S Chaudhari and Feliks Kogan and Anthony A Gatti},
journal = {Osteoarthritis and cartilage open},
year = {2026},
month = oct,
doi = {10.1016/j.ocarto.2026.100886},
url = {https://europepmc.org/article/MED/42904093},
note = {CC BY},
}
RIS
TY - JOUR
TI - OpenMSK: A modular open-source framework for comprehensive analysis of imaging biomarkers in knee osteoarthritis.
AU - Ananya Goyal
AU - Francesca Belibi
AU - Vyoma Sahani
AU - Rune Pedersen
AU - Yael Vainberg
AU - Ashley Williams
AU - Constance Chu
AU - Bryan Haddock
AU - Garry E Gold
AU - Akshay S Chaudhari
AU - Feliks Kogan
AU - Anthony A Gatti
PY - 2026
DA - 2026/10/09
JO - Osteoarthritis and cartilage open
DO - 10.1016/j.ocarto.2026.100886
UR - https://europepmc.org/article/MED/42904093
AB - Objective To develop and validate a fully automated, extendable, open-source AI-driven pipeline capable of knee magnetic resonance imaging (MRI) segmentation and quantitative extraction of MRI and positron emission tomography (PET) imaging biomarkers.Design For model training, open-source knee MRI data from 347 knees acquired across 7 scanners using multiple gradient-echo sequences were used. An independent test set of 20 knees from 3T PET-MRI examinations were used for evaluation in this prospective reliability and agreement study. The pipeline segmented femoral, tibial, and patellar bones and cartilage, and medial and lateral menisci using three different deep learning models. Quantitative outputs included cartilage thickness and T₂ relaxation times, meniscus volume and T₂∗ relaxation times, bone shape scores, and static and kinetic subchondral bone PET measures. Manual segmentations from two annotators served as reference standards. Segmentation performance was assessed using Dice similarity coefficients (DSC), average symmetric surface distances, and volume differences. Quantitative outcome agreement was evaluated using intraclass correlation coefficients (ICC), Pearson correlations, and root mean square error.Results Automated segmentations demonstrated high spatial agreement with manual annotations, with DSCs ranging from 0.84 to 0.98 across all tissues. Quantitative PET-MRI biomarkers generally demonstrated high agreement, although confidence intervals were wide for several biomarkers.Conclusion OpenMSK enables multi-tissue knee segmentation and generation of quantitative MRI and PET biomarkers, with performance assessed against two independent annotators and across different U-Net-based segmentation architectures. As a freely available, modular platform, OpenMSK lowers technical barriers to whole-joint quantitative imaging and provides a standardized foundation for OA research and clinical translation.
SN - 2665-9131
ER -