EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Synthetic data enables human-grade microtubule analysis with foundation models for segmentation

Mario Koddenbrock iD, Justus Westerhoff iD, Dominik Fachet iD, Simone Reber, Felix A Gers, Erik Rodner

PLOS Computational Biology · 05.05.2026 · 22 (5) · e1013901

DOI: 10.1371/journal.pcbi.1013901 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 05.05.2026. Verfasst von Mario Koddenbrock und 5 weiteren Autor:innen. Beteiligte Einrichtung: KI Werkstatt, Hochschule für Technik und Wirtschaft Berlin (HTW), Berlin, Germany. Hauptthemen laut MEDLINE: Microtubules, Image Processing, Computer-Assisted. Die Arbeit nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Max-Planck-Gesellschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Studying microtubules (MTs) and their mechanical properties is central to understanding intracellular transport, cell division, and drug action. While important, experts still need to spend many hours manually segmenting these filamentous structures. The suitability of state-of-the-art methods for this task cannot be systematically assessed, as large-scale labeled datasets are missing. We address this gap by introducing the synthetic dataset SynthMT , produced by tuning a novel image generation pipeline on real-world interference reflection microscopy (IRM) frames of in vitro reconstituted MTs without requiring human annotations. In our benchmark, we evaluate nine fully automated methods for MT analysis in both zero- and Hyperparameter Optimization (HPO)-based few-shot settings. Across both settings, classical algorithms and current foundation models still struggle to achieve the accuracy required for biological downstream analysis on in vitro MT IRM images that humans perceive as visually simple. However, a notable exception is the recently introduced SAM3 model. After HPO on only ten random SynthMT images, its text-prompted version SAM3Text achieves near-perfect and in some cases super-human performance on unseen, real data. This indicates that fully automated MT segmentation has become feasible when method configuration is effectively guided by synthetic data. To enable progress, we publicly release the dataset, the generation pipeline, and the evaluation framework.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MicrotubulesImage Processing, Computer-AssistedHumansAlgorithmsComputational BiologyMicroscopy

Autor:innen und Institutionen

  • KI Werkstatt, Hochschule für Technik und Wirtschaft Berlin (HTW), Berlin, Germany.
  • Berliner Hochschule für Technik (BHT), Berlin, Germany.
  • Max Planck Institute for Infection Biology, Berlin,‌‌ Germany.
  • Merantix Momentum GmbH, Berlin, ‌‌Germany.

ORCID-Profile: Mario Koddenbrock, Justus Westerhoff, Dominik Fachet

Förderung

  • Deutsche Forschungsgemeinschaft
  • Max-Planck-Gesellschaft

Zitieren

APA

Koddenbrock, M., Westerhoff, J., Fachet, D., Reber, S., Gers, F. A., & Rodner, E. (2026). Synthetic data enables human-grade microtubule analysis with foundation models for segmentation. PLOS Computational Biology, 22(5), e1013901. https://doi.org/10.1371/journal.pcbi.1013901

Vancouver

Koddenbrock M, Westerhoff J, Fachet D, Reber S, Gers FA, Rodner E. Synthetic data enables human-grade microtubule analysis with foundation models for segmentation. PLOS Computational Biology. 2026;22(5):e1013901. doi:10.1371/journal.pcbi.1013901

BibTeX
@article{Koddenbrock2026,
  author = {Koddenbrock, Mario and Westerhoff, Justus and Fachet, Dominik and Reber, Simone and Gers, Felix A and Rodner, Erik},
  title = {Synthetic data enables human-grade microtubule analysis with foundation models for segmentation},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {5},
  pages = {e1013901},
  doi = {10.1371/journal.pcbi.1013901}
}
Kostenlos starten →