A physics-informed deep learning framework for estimating muscle activation patterns following Achilles tendon repair
Journal of Applied Physiology · 01.08.2026 · 141 (2) · 366-382
DOI: 10.1152/japplphysiol.00274.2026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Physiology, erschienen am 01.08.2026. Verfasst von Diwei Chen und 13 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Sports Science, Ningbo University, Ningbo, People's Republic of China. Hauptthemen laut MEDLINE: Achilles Tendon, Muscle, Skeletal, Deep Learning, Tendon Injuries. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National key R&D program of China, Joint fund of zhejiang provincial natural science foundation of China, Zhejiang provincial key project of education science planing.
Abstract (Originalsprache)
This study presents a physics-informed deep learning framework for reconstructing soleus activation after Achilles tendon repair from clinically accessible kinematics and limited EMG. The model outperformed conventional approaches in physiological fidelity and identified delayed, terminal-stance-dominant soleus recruitment with altered coactivation, offering a scalable and noninvasive approach for monitoring postoperative neuromuscular recovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Sports Science, Ningbo University, Ningbo, People's Republic of China.
- Research Academy of Grand Health, Ningbo University, Ningbo, People's Republic of China.
- Zhejiang Engineering Research Center for New Technologies and Applications of Helium-Free Magnetic Resonance Imaging, Ningbo No. 2 Hospital, Ningbo, People's Republic of China.
- ANTA kids, ANTA (China) Co., Ltd, Xiamen, People's Republic of China.
- Department of Physical Education and Sport, Faculty of Sport Sciences, University of Granada, Granada, Spain.
- Research Academy of Medicine Combining Sports, Ningbo No. 2 Hospital, Ningbo, People's Republic of China.
ORCID-Profile: Dong Sun, Bálint Kovács, Yaodong Gu
Förderung
- National key R&D program of China
- Joint fund of zhejiang provincial natural science foundation of China
- Zhejiang provincial key project of education science planing
- Zhejiang engineering research center for new technologies and applications of helium-free magnetic resonance imaging open fund project 2024
- Scientific research fund of zhejiang provincial education department
- Ningbo key research and development program
- Zhejiang rehabilitation medical association scientific research special fund
- Research academy of medicine combining sports, ningbo
Zitieren
APA
Chen, D., Sun, D., Li, Y., Zhao, R., Li, F., Zhou, Z., Wang, D., Song, Y., Cen, X., Yuan, Y., Kovács, B., Goda, T. J., Fang, J., & Gu, Y. (2026). A physics-informed deep learning framework for estimating muscle activation patterns following Achilles tendon repair. Journal of Applied Physiology, 141(2), 366-382. https://doi.org/10.1152/japplphysiol.00274.2026
Vancouver
Chen D, Sun D, Li Y, Zhao R, Li F, Zhou Z, et al. A physics-informed deep learning framework for estimating muscle activation patterns following Achilles tendon repair. Journal of Applied Physiology. 2026;141(2):366-382. doi:10.1152/japplphysiol.00274.2026
BibTeX
@article{Chen2026,
author = {Chen, Diwei and Sun, Dong and Li, Yufei and Zhao, Rui and Li, Fengping and Zhou, Zhanyi and Wang, Dongxu and Song, Yang and Cen, Xuanzhen and Yuan, Yi and Kovács, Bálint and Goda, Tibor J and Fang, Junjie and Gu, Yaodong},
title = {A physics-informed deep learning framework for estimating muscle activation patterns following Achilles tendon repair},
journal = {Journal of Applied Physiology},
year = {2026},
volume = {141},
number = {2},
pages = {366--382},
doi = {10.1152/japplphysiol.00274.2026}
}
EUVIMED