Accurate and fast segmentation of filaments and membranes in micrographs and tomograms with TARDIS
2024

Fast and Accurate Segmentation of Biomolecules with TARDIS

Sample size: 13000 publication Evidence: high

Author Information

Author(s): Kiewisz Robert, Fabig Gunar, Conway Will, Johnston Jake, Kostyuchenko Victor A., Bařinka Cyril, Clarke Oliver, Magaj Magdalena, Yazdkhasti Hossein, Vallese Francesca, Lok Shee-Mei, Redemann Stefanie, Müller-Reichert Thomas, Bepler Tristan

Primary Institution: Cold Spring Harbor Laboratory

Hypothesis

Can TARDIS improve the annotation of structures in cryogenic electron microscopy images?

Conclusion

TARDIS provides a fast and accurate method for segmenting biomolecular structures in high-resolution imaging.

Supporting Evidence

  • TARDIS can segment over 13,000 tomograms from the CZI Cryo-Electron Tomography data portal.
  • The framework is modular and can be adapted for new structures and imaging modalities.

Takeaway

TARDIS is a tool that helps scientists quickly and accurately label tiny structures in pictures of biomolecules.

Methodology

TARDIS uses deep learning for semantic segmentation and a geometric model for instance segmentation.

Digital Object Identifier (DOI)

10.1101/2024.12.19.629196

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication