Comparative evaluation of YOLOv8, YOLOv11, and RT-DETR for automated microcarrier colonization assessment in bioreactor cell cultures
Frontiers in Bioengineering and Biotechnology · 09.07.2026 · 14
DOI: 10.3389/fbioe.2026.1849366 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 09.07.2026. Verfasst von Manuel T Fernández de Sevilla und 11 weiteren Autor:innen. Beteiligte Einrichtung: Cell Therapies Science Department, Takeda Madrid Cell Therapy Technology Center, Madrid, Spain. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Monitoring microcarrier colonization during mesenchymal stromal cell (MSC) expansion in bioreactors is essential for process control. Current manual quantification methods are time-consuming, subjective, and prone to inter-operator variability. This study presents a proof-of-concept evaluation of deep learning-based object detection for automated microcarrier colonization quantification in bioreactor cell cultures Methods Three state-of-the-art architectures—YOLOv8, YOLOv11, and RT-DETR—were compared within a unified experimental framework. A dataset of 699 fluorescence microscopy images containing 46,982 annotated microcarriers (classified as colonized or non-colonized) was used for training and evaluation. Model selection followed a three-stage Successive Halving Algorithm (SHA) strategy to efficiently identify the best-performing architecture across 12 configurations without requiring high-end computational infrastructure. COCO-pretrained transfer learning was applied across all models.
Results
YOLOv8-l emerged as the top-performing model, achieving mAP50–95 of 0.855 on validation and 0.787 on test, with a colonization estimation error (Mean Absolute Error) of 11.75%. The dataset size proved sufficient for CNN-based architectures, while also revealing the higher data demands of transformer-based detectors.
Discussion
These results demonstrate that automated deep learning pipelines can reliably quantify microcarrier colonization, offering a practical alternative to manual assessment in cell therapy manufacturing. The findings also suggest that newer YOLO models do not necessarily yield improvements in domain-specific biomedical tasks
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cell Therapies Science Department, Takeda Madrid Cell Therapy Technology Center, Madrid, Spain.
- iBET - Instituto de Biologia Experimental e Tecnológica, Oeiras, Portugal.
- Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal.
Zitieren
APA
Fernández de Sevilla, M. T., Valero, R., Menéndez, B., García Domínguez, G., Blanco Sánchez, C., Canales, N., Menta Hernández, R., Costa, M. H. G., Serra, M., Lombardo, E., Avivar-Valderas, A., & Mancheño-Corvo, P. (2026). Comparative evaluation of YOLOv8, YOLOv11, and RT-DETR for automated microcarrier colonization assessment in bioreactor cell cultures. Frontiers in Bioengineering and Biotechnology, 14. https://doi.org/10.3389/fbioe.2026.1849366
Vancouver
Fernández de Sevilla MT, Valero R, Menéndez B, García Domínguez G, Blanco Sánchez C, Canales N, et al. Comparative evaluation of YOLOv8, YOLOv11, and RT-DETR for automated microcarrier colonization assessment in bioreactor cell cultures. Frontiers in Bioengineering and Biotechnology. 2026;14. doi:10.3389/fbioe.2026.1849366
BibTeX
@article{FernndezdeSevilla2026,
author = {Fernández de Sevilla, Manuel T and Valero, Raúl and Menéndez, Beatriz and García Domínguez, Gonzalo and Blanco Sánchez, Cristina and Canales, Natalia and Menta Hernández, Ramón and Costa, Marta H G and Serra, Margarida and Lombardo, Eleuterio and Avivar-Valderas, Alvaro and Mancheño-Corvo, Pablo},
title = {Comparative evaluation of YOLOv8, YOLOv11, and RT-DETR for automated microcarrier colonization assessment in bioreactor cell cultures},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2026},
volume = {14},
doi = {10.3389/fbioe.2026.1849366}
}
EUVIMED