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

Deep learning-based Desikan-Killiany parcellation of the brain using diffusion MRI.

Scientific reports·2026
Same author

Alport Syndrome is a Partial Tubulointerstitial Disease of the Kidney.

Kidney international reports·2026
Same author

Spatial transcriptomics expression prediction from histopathology based on cross-modal mask reconstruction and contrastive learning.

Medical image analysis·2025
Same author

Continual learning in medical image analysis: A comprehensive review of recent advancements and future prospects.

Medical image analysis·2025
Same author

Domain-incremental white blood cell classification with privacy-aware continual learning.

Scientific reports·2025
Same author

Physics-Inspired Generative Models in Medical Imaging.

Annual review of biomedical engineering·2025

Related Experiment Video

Updated: Aug 29, 2025

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

9.8K

Learning to Segment Fine Structures Under Image-Level Supervision With an Application to Nematode Segmentation.

Long Chen, Martin Strauch, Matthias Daub

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |September 10, 2022
    PubMed
    Summary

    This study introduces a new deep learning method for segmenting fine biological structures using only image-level labels. The approach improves accuracy for challenging tasks like identifying nematodes in soil samples.

    More Related Videos

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.6K
    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
    08:49

    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

    Published on: August 1, 2022

    3.7K

    Related Experiment Videos

    Last Updated: Aug 29, 2025

    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

    9.8K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.6K
    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
    08:49

    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

    Published on: August 1, 2022

    3.7K

    Area of Science:

    • Computer Vision
    • Bioimage Analysis
    • Machine Learning

    Background:

    • Image segmentation models often require extensive pixel-level annotations, increasing effort.
    • Current models trained with image-level labels struggle with segmenting fine biological structures.
    • Automated soil sample screening requires accurate segmentation of small organisms like nematodes.

    Purpose of the Study:

    • To develop a deep network for segmenting fine biological structures using only image-level labels.
    • To improve the performance gap in segmenting small-scale biological features.
    • To apply the method to automated soil sample screening for nematodes and cysts.

    Main Methods:

    • Proposed a deep network architecture incorporating Global Weighted Pooling (GWP).
    • Integrated segmentation refinement using low-level image cues.
    • Trained and evaluated the model on datasets of nematodes (worms + eggs) and nematode cysts.

    Main Results:

    • Achieved a 79.72% Dice coefficient for nematode segmentation.
    • Achieved a 58.51% Dice coefficient for nematode cyst segmentation.
    • Demonstrated successful segmentation of fine structures with limited annotation.

    Conclusions:

    • The proposed deep network effectively segments fine biological structures using only image-level labels.
    • Global Weighted Pooling and low-level cue refinement enhance segmentation accuracy for small objects.
    • The method shows promise for automated screening applications in soil analysis.