Comparative Evaluation of DeepLabCut Convolutional Neural Network Architectures for High-Precision Markerless Tracking in the Mouse Staircase Test
Bioengineering · 13.02.2026 · 13 (2) · 215
DOI: 10.3390/bioengineering13020215 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 13.02.2026. Verfasst von Valentin Fernandez und 3 weiteren Autor:innen. Beteiligte Einrichtung: LNEC INSERM U1084, University of Poitiers, 86073 Poitiers, France. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Precise quantification of fine motor behaviour is essential for understanding neural circuit function and for evaluating therapeutic interventions in neurological disorders. While markerless pose estimation frameworks such as DeepLabCut (DLC) have transformed behavioural phenotyping, the choice of convolutional neural network (CNN) backbone has a critical impact on tracking performance, particularly in tasks involving small distal joints and frequent occlusions. In this study, we present the first systematic comparison of nine CNN architectures implemented in DLC for lateral-view analysis of skilled reaching movements in the Montoya Staircase test, a gold-standard assay for forelimb dexterity in rodent models of stroke and neurodegenerative disease. Using a dataset comprising both control and primary motor cortex (M1)–lesioned mice, we evaluated model performance across six key dimensions: spatial accuracy (RMSE, PCK@5 px), mean average precision (mAP), robustness to occlusions, inference speed, and GPU memory usage. Our results demonstrate that multi-scale DLCRNet architectures substantially outperform conventional backbones. DLCRNet_ms5 achieved the highest overall accuracy, while DLCRNet_stride16_ms5 provided the most favourable balance between precision and computational efficiency. These findings provide practical methodological guidance for neuroscience laboratories and highlight the importance of CNN architecture selection for the reliable quantification of fine motor behaviour in preclinical research.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- LNEC INSERM U1084, University of Poitiers, 86073 Poitiers, France.
- LMA CNRS 7348, University of Poitiers, 86073 Poitiers, France.
- XLIM CNRS 7252, University of Poitiers, 86073 Poitiers, France.
ORCID-Profile: Afsaneh Gaillard, Christine Fernandez-Maloigne
Zitieren
APA
Fernandez, V., Bonnin, L., Gaillard, A., & Fernandez-Maloigne, C. (2026). Comparative Evaluation of DeepLabCut Convolutional Neural Network Architectures for High-Precision Markerless Tracking in the Mouse Staircase Test. Bioengineering, 13(2), 215. https://doi.org/10.3390/bioengineering13020215
Vancouver
Fernandez V, Bonnin L, Gaillard A, Fernandez-Maloigne C. Comparative Evaluation of DeepLabCut Convolutional Neural Network Architectures for High-Precision Markerless Tracking in the Mouse Staircase Test. Bioengineering. 2026;13(2):215. doi:10.3390/bioengineering13020215
BibTeX
@article{Fernandez2026,
author = {Fernandez, Valentin and Bonnin, Landoline and Gaillard, Afsaneh and Fernandez-Maloigne, Christine},
title = {Comparative Evaluation of DeepLabCut Convolutional Neural Network Architectures for High-Precision Markerless Tracking in the Mouse Staircase Test},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {2},
pages = {215},
doi = {10.3390/bioengineering13020215}
}
EUVIMED