Neural shape models enable cohort-scale simulation of knee cartilage mechanics
Abstract
Knee osteoarthritis affects over 350 million people worldwide, is a leading cause of disability, and carries substantial costs. Cartilage mechanical load is believed to play a critical role in osteoarthritis pathophysiology, yet clinical biomechanics research uses external measures of joint loading that do not capture tissue-level load. We developed a fully-automated pipeline that builds biomechanical knee models from a single MRI using deep learning-based segmentation and neural shape models, and elastic foundation contact to simulate gait. Applied to 756 knees from the Osteoarthritis Initiative, each simulated under the same 10 standardized gaits, the pipeline converged in 99.6% of 7,560 simulations. Medial tibial pressure decreased from healthy to incident to mild osteoarthritis as disease-related shape changes enlarged contact area, an effect reproduced in simulations of synthetic knees. Yet within knees, medial cartilage thinned fastest over six years in regions of highest pressure, with stronger relationships in incident and mild osteoarthritis knees. Automated simulations provided cohort-scale, tissue-level support for mechanical theories of osteoarthritis progression and a framework for prospectively quantifying cartilage load to guide mechanical interventions.
Related
- Clinically adaptable size cartilage grafts generated from human embryonic stem cells enable tracheal repair in a porcine model
- A deep neural network-enhanced multi-scale coupled model of patient-specific acoustic wave propagation for mechanotransduction stimulation of healthy and osteoarthritic knee articular cartilage.
- Comprehensive Driving Assessment to Enable Driving Resumption in Adults Recovering From Critical Illness: A Prospective Cohort Study
- Simulation based-inference of epidemiological and phylodynamic models via Neural Posterior Estimation
- A prospective cohort study on ultrasound simulation training in gynecology and obstetrics using pelvic, fetometry, and breast models
BibTeX
@misc{gatti2026neural,
title = {{Neural shape models enable cohort-scale simulation of knee cartilage mechanics}},
author = {Anthony A. Gatti and Kathryn R. Marusich and Allison Clouthier and McKenzie S. White and Carmichael Ong and Amir Esrafilian and Colin Smith and Julie Kolesar and Tian Tan and Scott Uhlrich and Constance Chu and Seth Sherman and Garry E. Gold and Scott L. Delp and Feliks Kogan and Akshay S. Chaudhari},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.29.26366866},
url = {https://www.medrxiv.org/content/10.64898/2026.10.29.26366866v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Neural shape models enable cohort-scale simulation of knee cartilage mechanics
AU - Anthony A. Gatti
AU - Kathryn R. Marusich
AU - Allison Clouthier
AU - McKenzie S. White
AU - Carmichael Ong
AU - Amir Esrafilian
AU - Colin Smith
AU - Julie Kolesar
AU - Tian Tan
AU - Scott Uhlrich
AU - Constance Chu
AU - Seth Sherman
AU - Garry E. Gold
AU - Scott L. Delp
AU - Feliks Kogan
AU - Akshay S. Chaudhari
PY - 2026
DA - 2026/10/29
PB - medRxiv
DO - 10.64898/2026.10.29.26366866
UR - https://www.medrxiv.org/content/10.64898/2026.10.29.26366866v1
AB - Knee osteoarthritis affects over 350 million people worldwide, is a leading cause of disability, and carries substantial costs. Cartilage mechanical load is believed to play a critical role in osteoarthritis pathophysiology, yet clinical biomechanics research uses external measures of joint loading that do not capture tissue-level load. We developed a fully-automated pipeline that builds biomechanical knee models from a single MRI using deep learning-based segmentation and neural shape models, and elastic foundation contact to simulate gait. Applied to 756 knees from the Osteoarthritis Initiative, each simulated under the same 10 standardized gaits, the pipeline converged in 99.6% of 7,560 simulations. Medial tibial pressure decreased from healthy to incident to mild osteoarthritis as disease-related shape changes enlarged contact area, an effect reproduced in simulations of synthetic knees. Yet within knees, medial cartilage thinned fastest over six years in regions of highest pressure, with stronger relationships in incident and mild osteoarthritis knees. Automated simulations provided cohort-scale, tissue-level support for mechanical theories of osteoarthritis progression and a framework for prospectively quantifying cartilage load to guide mechanical interventions.
ER -