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 Experiment Videos

Toward automatic phenotyping of developing embryos from videos.

Feng Ning1, Damien Delhomme, Yann LeCun

  • 1Courant Institute of Mathematical Sciences, New York University, New York, NY 10003, USA. fengning@cs.nyu.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|September 30, 2005
PubMed
Summary

We developed a trainable system for analyzing C. elegans embryo development videos. This automated system accurately detects, segments, and locates cells and nuclei in microscopic images for phenotyping.

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

Effects of Complex and Contrast Training on Lower Limb Explosive Power and Eccentric Strength in Elite Male Track and Field Athletes: A 24-Week Randomized Trial.

Journal of strength and conditioning research·2026
Same author

Genome evolution in parthenogenetic nematodes shaped by chromosome rearrangements and introgression.

Genome research·2026
Same author

Multi-modal AI for comprehensive breast cancer prognostication.

Nature communications·2026
Same author

Participant perceptions of the impact of the ModPad program on molecular diagnostic capacity building and public health practices.

Frontiers in public health·2026
Same author

Chitinase-like proteins de-N-glycosylating CD36 modify cholesterol metabolism in atherosclerotic macrophages.

Nature communications·2026
Same author

Association between dietary patterns and depressive symptoms in Chinese adults.

Asia Pacific journal of clinical nutrition·2026

Area of Science:

  • Developmental biology
  • Computational biology
  • Image analysis

Background:

  • Accurate analysis of C. elegans embryo development is crucial for understanding cellular processes.
  • Manual analysis of microscopic videos is time-consuming and prone to errors.
  • Automated systems are needed to facilitate high-throughput phenotyping.

Purpose of the Study:

  • To develop a trainable system for automated analysis of C. elegans embryo videos.
  • To detect, segment, and locate cells and nuclei in microscopic images.
  • To serve as a central component for a fully automated phenotyping system.

Main Methods:

  • A convolutional neural network was trained to classify pixels into five categories: cell wall, cytoplasm, nucleus membrane, nucleus, and outside medium.

Related Experiment Videos

  • An energy-based model was used to refine the convolutional network's output by enforcing local consistency constraints.
  • Elastic models of C. elegans embryos at different developmental stages were matched to the generated label images.

    • Main Results:

    • The system successfully automates the detection, segmentation, and localization of cells and nuclei in C. elegans embryo videos.
    • The integration of convolutional and energy-based models improves the accuracy of image analysis.
    • The system provides a foundation for fully automated phenotyping of embryo development.

    Conclusions:

    • The described trainable system offers an efficient and accurate method for analyzing C. elegans embryo development.
    • Automated image analysis significantly enhances the capacity for high-throughput phenotyping.
    • This system has the potential to accelerate research in developmental biology and related fields.