Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

ActiTect: a generalizable machine learning pipeline for REM sleep behavior disorder screening through standardized actigraphy.

NPJ digital medicine·2026
Same author

Histo-Miner: Deep learning based tissue features extraction pipeline from H&E whole slide images of cutaneous squamous cell carcinoma.

PLoS computational biology·2026
Same author

Deep Imputation for Skeleton data (DISK) for behavioral science.

Nature methods·2025
Same author

Imaging mass cytometry dataset of small-cell lung cancer tumors and tumor microenvironments.

BMC research notes·2025
Same author

Explainable, federated deep learning model predicts disease progression risk of cutaneous squamous cell carcinoma.

NPJ precision oncology·2025
Same author

CSF1R<sup>+</sup> myeloid-monocytic cells drive CAR-T cell resistance in aggressive B cell lymphoma.

Cancer cell·2025

Related Experiment Video

Updated: Jul 24, 2025

Isotropic Light-Sheet Microscopy and Automated Cell Lineage Analyses to Catalogue Caenorhabditis elegans Embryogenesis with Subcellular Resolution
08:16

Isotropic Light-Sheet Microscopy and Automated Cell Lineage Analyses to Catalogue Caenorhabditis elegans Embryogenesis with Subcellular Resolution

Published on: June 6, 2019

8.3K

WormSwin: Instance segmentation of C. elegans using vision transformer.

Maurice Deserno1,2,3, Katarzyna Bozek4,5,6

  • 1Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, North Rhine-Westphalia, Germany. maurice.deserno@uni-koeln.de.

Scientific Reports
|July 7, 2023
PubMed
Summary
This summary is machine-generated.

WormSwin accurately segments individual Caenorhabditis elegans (C. elegans) from crowded videos using a transformer neural network. This breakthrough enables detailed study of worm behavior, even for complex interactions like mating.

More Related Videos

A Simple Microfluidic Chip for Long-Term Growth and Imaging of Caenorhabditis elegans
10:45

A Simple Microfluidic Chip for Long-Term Growth and Imaging of Caenorhabditis elegans

Published on: April 11, 2022

2.0K
Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans
08:47

Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans

Published on: July 5, 2019

9.7K

Related Experiment Videos

Last Updated: Jul 24, 2025

Isotropic Light-Sheet Microscopy and Automated Cell Lineage Analyses to Catalogue Caenorhabditis elegans Embryogenesis with Subcellular Resolution
08:16

Isotropic Light-Sheet Microscopy and Automated Cell Lineage Analyses to Catalogue Caenorhabditis elegans Embryogenesis with Subcellular Resolution

Published on: June 6, 2019

8.3K
A Simple Microfluidic Chip for Long-Term Growth and Imaging of Caenorhabditis elegans
10:45

A Simple Microfluidic Chip for Long-Term Growth and Imaging of Caenorhabditis elegans

Published on: April 11, 2022

2.0K
Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans
08:47

Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans

Published on: July 5, 2019

9.7K

Area of Science:

  • Biotechnology
  • Computational Biology
  • Neuroscience

Background:

  • Quantitative behavioral studies require accurate tracking of individual organisms.
  • Challenges include organism overlap and occlusion in large-scale recordings.
  • Existing methods struggle with complex scenarios like interacting Caenorhabditis elegans (C. elegans).

Purpose of the Study:

  • To develop an automated method for segmenting individual C. elegans from crowded video recordings.
  • To enable large-scale, quantitative behavioral analysis of C. elegans.
  • To overcome limitations of current segmentation techniques for interacting worms.

Main Methods:

  • Utilized a transformer neural network architecture named WormSwin.
  • Trained and validated the model on diverse video and image datasets from multiple labs.
  • Evaluated performance on the BBBC010 benchmark dataset.

Main Results:

  • Achieved high accuracy in segmenting individual C. elegans, with an average precision of 0.990.
  • Demonstrated comparable performance to existing benchmarks.
  • Successfully segmented challenging overlapping postures of mating worms.

Conclusions:

  • WormSwin provides an accurate and efficient solution for C. elegans segmentation.
  • The method facilitates previously inaccessible behavioral studies.
  • Opens new avenues for understanding C. elegans collective and individual behaviors.