DeLTA 3.0: A modern segmentation and tracking tool for microscopy images

Abstract

Time-lapse microscopy is a popular approach for quantifying single-cell dynamics. Analyzing image sequences requires two steps: segmentation (locating the cells) and tracking (following them). DeLTA (Deep Learning for Time-lapse Analysis) is a Python package that performs segmentation and tracking. Initially developed to handle images of bacteria growing within the "mother machine," (Wang et al., 2010) a popular microfluidic device for single-cell analysis that constrains cells to grow in one dimension (Lugagne et al., 2020), it was later extended to handle cells growing in 2D (O'Connor et al., 2022). After three years of experience and feedback, we are releasing version 3.0 -a major overhaul to achieve four objectives: enhance usability for scientists, improve modularity and adaptability for developers, integrate features like growth rate computation and lineage manipulation, and adopt modern open-source development practices.

TEM Agent: enhancing transmission electron microscopy with modern AI tools
Morgan K. Wall, Alexander J. Pattison, Edward S. Barnard +2
npj Computational Materials10 Jun 2026Peer-reviewedCC BYFull text14 citedStructural biologyOpenAlex
Automating Nanoparticle Analysis in Transmission Electron Microscopy with Synthetically Trained Segmentation Models
Natalia Sá, Andrew Stewart
ChemRxiv13 Oct 2026PreprintCC BYStructural biologyChemRxiv
A method for correcting background non-uniformity while preserving specimen-level information in Fourier ptychographic microscopy images
L. Copeland, K. F. E. Polland, L. Walker +4
bioRxiv21 Oct 2026PreprintCC BY-NDFull textBiophysicsbioRxiv
A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms
Clarisse Uwizeye, Serena Flori, Joanell Angulo +4
Cell Reports Methods9 Sep 2026Peer-reviewedCC BY 4.0Full textBiophysicsHAL
Rapid volumetric reconstruction and tracking for Fourier light-field microscopy enables real-time calcium imaging in freely behaving Hydra.
R. Adkins, R. Hausen, J. Noss +2
bioRxiv17 Sep 2026PreprintCC BYFull textBiophysicsbioRxiv

Cite

BibTeX RIS

BibTeX

@article{andreani2026delta,
  title = {{DeLTA 3.0: A modern segmentation and tracking tool for microscopy images}},
  author = {Virgile Andreani and Jean-Baptiste Lugagne and Owen M O’connor and Mary J Dunlop},
  journal = {Journal of Open Source Software},
  year = {2026},
  month = oct,
  doi = {10.21105/joss.10279},
  url = {https://inria.hal.science/hal-05805961v1},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - DeLTA 3.0: A modern segmentation and tracking tool for microscopy images
AU  - Virgile Andreani
AU  - Jean-Baptiste Lugagne
AU  - Owen M O’connor
AU  - Mary J Dunlop
PY  - 2026
DA  - 2026/10/16
JO  - Journal of Open Source Software
DO  - 10.21105/joss.10279
UR  - https://inria.hal.science/hal-05805961v1
AB  - Time-lapse microscopy is a popular approach for quantifying single-cell dynamics. Analyzing image sequences requires two steps: segmentation (locating the cells) and tracking (following them). DeLTA (Deep Learning for Time-lapse Analysis) is a Python package that performs segmentation and tracking. Initially developed to handle images of bacteria growing within the "mother machine," (Wang et al., 2010) a popular microfluidic device for single-cell analysis that constrains cells to grow in one dimension (Lugagne et al., 2020), it was later extended to handle cells growing in 2D (O'Connor et al., 2022). After three years of experience and feedback, we are releasing version 3.0 -a major overhaul to achieve four objectives: enhance usability for scientists, improve modularity and adaptability for developers, integrate features like growth rate computation and lineage manipulation, and adopt modern open-source development practices.
SN  - 1942-3926
ER  -

Abstract

Related

Cite