EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A generalist deep-learning volume segmentation tool for volume electron microscopy of biological samples

Yuyao Huang, Nickhil Jadav, Georgia Rutter, Lech Szymanski, Mihnea Bostina, Duane P Harland

Journal of Structural Biology · 2025-09 · 217 (3) · 108214

DOI: 10.1016/j.jsb.2025.108214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Structural Biology, 2025-09. Verfasst von Yuyao Huang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Microbiology & Immunology, University of Otago, Dunedin 9016, New Zealand. Hauptthemen laut MEDLINE: Deep Learning, Software, Image Processing, Computer-Assisted, Microscopy, Electron. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Business, Innovation and Employment, Ministry for Business Innovation and Employment.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present the Volume Segmentation Tool (VST), a deep learning software tool that implements volumetric image segmentation in volume electron microscopy image stack data from a wide range of biological sample types. VST automates the handling of data preprocessing, data augmentation, and network building, as well as the configuration for model training, while adapting to the specific dataset. We have tried to make VST more accessible by designing it to operate entirely on local hardware and have provided a browser-based interface with additional features for visualizations of the networks and augmented datasets. VST can utilise contour map prediction to support instance segmentation on top of semantic segmentation. Through examples from various resin-embedded sample derived transmission electron microscopy and scanning electron microscopy datasets, we demonstrate that VST achieves state of the art performance compared to existing approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSoftwareImage Processing, Computer-AssistedMicroscopy, ElectronImaging, Three-DimensionalHumansMicroscopy, Electron, ScanningMicroscopy, Electron, TransmissionVolume Electron Microscopy

Stichwörter der Autor:innen

Image analysisInstance segmentationMachine learningSemantic segmentationSoftware toolsVolume electron microscopy

Autor:innen und Institutionen

  • Department of Microbiology & Immunology, University of Otago, Dunedin 9016, New Zealand.
  • School of Computing, University of Otago, Dunedin 9016, New Zealand.
  • Department of Microbiology & Immunology, University of Otago, Dunedin 9016, New Zealand. Electronic address: mihnea.bostina@otago.ac.nz.
  • Smart Foods & Bioproducts Science Group, AgResearch, Lincoln 7608, New Zealand; Biomolecular Interaction Centre (BIC), Te Pokapū Taunekeneke Rāpoi Ngota, New Zealand. Electronic address: Duane.Harland@agresearch.co.nz.

Förderung

  • Ministry of Business, Innovation and Employment
  • Ministry for Business Innovation and Employment

Zitieren

APA

Huang, Y., Jadav, N., Rutter, G., Szymanski, L., Bostina, M., & Harland, D. P. (2025). A generalist deep-learning volume segmentation tool for volume electron microscopy of biological samples. Journal of Structural Biology, 217(3), 108214. https://doi.org/10.1016/j.jsb.2025.108214

Vancouver

Huang Y, Jadav N, Rutter G, Szymanski L, Bostina M, Harland DP. A generalist deep-learning volume segmentation tool for volume electron microscopy of biological samples. Journal of Structural Biology. 2025;217(3):108214. doi:10.1016/j.jsb.2025.108214

BibTeX
@article{Huang2025,
  author = {Huang, Yuyao and Jadav, Nickhil and Rutter, Georgia and Szymanski, Lech and Bostina, Mihnea and Harland, Duane P},
  title = {A generalist deep-learning volume segmentation tool for volume electron microscopy of biological samples},
  journal = {Journal of Structural Biology},
  year = {2025},
  volume = {217},
  number = {3},
  pages = {108214},
  doi = {10.1016/j.jsb.2025.108214}
}
Kostenlos starten →