A semantic segmentation model to predict subcellular glycogen localization using transmission electron microscopy images
PLOS One · 17.06.2026 · 21 (6) · e0351502
DOI: 10.1371/journal.pone.0351502 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 17.06.2026. Verfasst von Anders A Hansen und 7 weiteren Autor:innen. Beteiligte Einrichtung: University of Southern Denmark, Department of Sports Science and Clinical Biomechanics, Odense M, Denmark. Hauptthemen laut MEDLINE: Glycogen, Microscopy, Electron, Transmission, Muscle, Skeletal. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danmarks Frie Forskningsfond.
Abstract (Originalsprache)
Transmission electron microscopy (TEM) is the gold standard for assessing subcellular glycogen localization in skeletal muscle fibres, but conventional manual analysis is extremely time-consuming and limits large-scale studies. Here, we developed and validated a deep learning–based semantic segmentation approach to automate quantification of glycogen particles across defined subcellular compartments in human skeletal muscle. Skeletal muscle biopsies were obtained from seven healthy men under conditions of normal, depleted, and supercompensated glycogen content. TEM images were acquired from myofibrillar and subsarcolemmal regions and manually annotated to train two complementary attention U-Net models: a region model identifying subcellular structures (intermyofibrillar space, intramyofibrillar regions including A-band, I-band and Z-disc, and mitochondria) and a glycogen model detecting individual glycogen particles. Combining the two models enabled estimation of compartment-specific glycogen areal densities. The model’s outcome was evaluated against manual point-counting. At the fibre level, estimates based on 10–12 images per region achieved biases below 15% and coefficient of variation below 26% for all compartments. Importantly, model-derived total glycogen volume density showed strong concordance with biochemically determined muscle glycogen content across biopsies. In conclusion, this validated semantic segmentation workflow provides an objective and highly time-efficient tool for quantifying subcellular glycogen distribution in skeletal muscle. The model substantially reduces analysis time and enables high-throughput investigations of compartmentalized glycogen metabolism, with model weights and code made openly available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- University of Southern Denmark, Department of Sports Science and Clinical Biomechanics, Odense M, Denmark.
- University of Southern Denmark, Department of Biochemistry and Molecular Biology, Odense M, Denmark.
- Norwegian School of Sport Sciences, Department of Physical Performance, Oslo, Norway.
- Odense University Hospital, Steno Diabetes Center Odense, Odense, Denmark.
- The August Krogh Section for Human and Molecular Physiology, Department of Nutrition, Exercise and Sports, University of Copenhagen, Copenhagen, Denmark.
ORCID-Profile: Anders A Hansen, Joachim Nielsen
Förderung
- Danmarks Frie Forskningsfond
Zitieren
APA
Hansen, A. A., Egebjerg, J. M., Solem, K., Kolnes, K. J., Wüstner, D., Wojtaszewski, J. F. P., Jensen, J., & Nielsen, J. (2026). A semantic segmentation model to predict subcellular glycogen localization using transmission electron microscopy images. PLOS One, 21(6), e0351502. https://doi.org/10.1371/journal.pone.0351502
Vancouver
Hansen AA, Egebjerg JM, Solem K, Kolnes KJ, Wüstner D, Wojtaszewski JFP, et al. A semantic segmentation model to predict subcellular glycogen localization using transmission electron microscopy images. PLOS One. 2026;21(6):e0351502. doi:10.1371/journal.pone.0351502
BibTeX
@article{Hansen2026,
author = {Hansen, Anders A and Egebjerg, Jacob M and Solem, Kristian and Kolnes, Kristoffer J and Wüstner, Daniel and Wojtaszewski, Jørgen F P and Jensen, Jørgen and Nielsen, Joachim},
title = {A semantic segmentation model to predict subcellular glycogen localization using transmission electron microscopy images},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0351502},
doi = {10.1371/journal.pone.0351502}
}
EUVIMED