napari-TurboBox: Interactive Multi-Viewer Bounding Box Annotation for AI-Guided Volumetric Bioimaging
Abstract
Promptable segmentation models turn one 3D bounding box into an instance mask. Box placement therefore limits how fast microscopy volumes with thousands of objects are annotated. Each box must be checked in several synchronized viewers, but napari-bbox shares no state between viewers. An edit must update every viewer and slows down with more boxes. napari-TurboBox instead holds one shared copy of the boxes for all viewers. In a four-viewer layout, napari-TurboBox needs a few milliseconds per mouse move to update the three slice viewers up to 104 boxes. The same update in napari-bbox leaves the 33 ms budget beyond about 103 boxes and takes 159 ms at 104. Boxes stay axis-aligned and export to COCO and YOLO as per-slice 2D boxes. napari-TurboBox is a pure-Python plugin for napari 0.6.6 to 0.9. The code is available at https://github.com/N-Friederich/napari-turbobox under the Apache 2.0 licence, and version 0.1.0 is archived at https://doi.org/10.5281/zenodo.23090828 on Zenodo.
Related
- A general route to volumetric segmentation under annotation scarcity
- muDM: A Queryable Multi-Resolution Data Model for Vector Geometry in Spatial Bioimaging
- Bioimaging With Fluorescent Nucleic‐Acid Aptamers for the Specific Detection and Quantification of Pseudomonas aeruginosa Alone and in Heterogeneous Bacterial Populations
- Influence of PEGylation and Surface Charge on Biodistribution of Shortwave Infrared Emitting Nanoparticles for In Vivo Bioimaging
- Cerebrovascular Structure-Flow Gradients Revealed by Volumetric Ultrasound Localization Microscopy
BibTeX
@misc{friederich2026napariturbobox,
title = {{napari-TurboBox: Interactive Multi-Viewer Bounding Box Annotation for AI-Guided Volumetric Bioimaging}},
author = {Nils Friederich and Philip Kohle and Maximilian Beichter and Mona Wellhäusser and Marcel Stahl and Pascal Zwick and Angelo Jovin Yamachui Sitcheu and Thomas Lautenschlager and David Exler and Linus Schilpp and Stephan Allgeier and Andreas Specker and Lennart Hilbert and Ralf Mikut},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22413},
eprint = {2610.22413},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22413},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - napari-TurboBox: Interactive Multi-Viewer Bounding Box Annotation for AI-Guided Volumetric Bioimaging
AU - Nils Friederich
AU - Philip Kohle
AU - Maximilian Beichter
AU - Mona Wellhäusser
AU - Marcel Stahl
AU - Pascal Zwick
AU - Angelo Jovin Yamachui Sitcheu
AU - Thomas Lautenschlager
AU - David Exler
AU - Linus Schilpp
AU - Stephan Allgeier
AU - Andreas Specker
AU - Lennart Hilbert
AU - Ralf Mikut
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.22413
UR - https://arxiv.org/abs/2610.22413
AB - Promptable segmentation models turn one 3D bounding box into an instance mask. Box placement therefore limits how fast microscopy volumes with thousands of objects are annotated. Each box must be checked in several synchronized viewers, but napari-bbox shares no state between viewers. An edit must update every viewer and slows down with more boxes. napari-TurboBox instead holds one shared copy of the boxes for all viewers. In a four-viewer layout, napari-TurboBox needs a few milliseconds per mouse move to update the three slice viewers up to 10^4 boxes. The same update in napari-bbox leaves the 33 ms budget beyond about 10^3 boxes and takes 159 ms at 10^4. Boxes stay axis-aligned and export to COCO and YOLO as per-slice 2D boxes. napari-TurboBox is a pure-Python plugin for napari 0.6.6 to 0.9. The code is available at https://github.com/N-Friederich/napari-turbobox under the Apache 2.0 licence, and version 0.1.0 is archived at https://doi.org/10.5281/zenodo.23090828 on Zenodo.
ER -