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 Video

Updated: Jun 18, 2026

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

Topology-Aware Segmentation Using Discrete Morse Theory.

Xiaoling Hu1, Yusu Wang2, Li Fuxin3

  • 1Stony Brook University.

... International Conference on Learning Representations
|June 17, 2026
PubMed
Summary
This summary is machine-generated.

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

Copper-mediated amidation of alkenylzirconocenes with acyl azides: formation of enamides.

Organic letters·2013
Same author

JARID1A, JMY, and PTGER4 polymorphisms are related to ankylosing spondylitis in Chinese Han patients: a case-control study.

PloS one·2013
Same author

[The risk factors of ventilator-associated pneumonia in newborn and the changes of isolated pathogens].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2013
Same author

A route to phase controllable Cu2ZnSn(S(1-x)Se(x))4 nanocrystals with tunable energy bands.

Scientific reports·2013
Same author

Efficacy of an infection control program in reducing ventilator-associated pneumonia in a Chinese neonatal intensive care unit.

American journal of infection control·2013
Same author

[Effect of different forms of inorganic nitrogen on the photodegradation of antipyrine in water].

Huan jing ke xue= Huanjing kexue·2013
Same journal

Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt.

... International Conference on Learning Representations·2026
Same journal

TOPODIFFUSIONNET: A TOPOLOGY-AWARE DIFFUSION MODEL.

... International Conference on Learning Representations·2026
Same journal

GEOMETRY OF LONG-TAILED REPRESENTATION LEARNING: REBALANCING FEATURES FOR SKEWED DISTRIBUTIONS.

... International Conference on Learning Representations·2026
Same journal

Probabilistic Geometric Principal Component Analysis with application to neural data.

... International Conference on Learning Representations·2026
Same journal

BRAID: Input-driven nonlinear dynamical modeling of neural-behavioral data.

... International Conference on Learning Representations·2026
Same journal

GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching.

... International Conference on Learning Representations·2026
See all related articles

This study introduces a novel deep learning approach for image segmentation, enhancing topological accuracy using discrete Morse theory (DMT). The method improves vessel connectivity and membrane closure in images, crucial for scientific analysis.

Area of Science:

  • Computer Vision
  • Computational Biology
  • Image Analysis

Background:

  • Per-pixel accuracy in image segmentation is insufficient for analyzing complex structures.
  • Topological correctness (e.g., vessel connectivity, membrane closure) is vital for biomedical and natural image analysis.
  • Existing methods often struggle with maintaining topological integrity.

Purpose of the Study:

  • To develop a novel approach for training deep image segmentation networks with improved topological accuracy.
  • To leverage discrete Morse theory (DMT) for identifying global structures critical for topological correctness.
  • To enhance the performance of segmentation models in challenging regions like weak connections and membranes.

Main Methods:

  • Utilized discrete Morse theory (DMT) to identify 1D skeletons and 2D patches relevant to topological accuracy.

More Related Videos

Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

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

Related Experiment Videos

Last Updated: Jun 18, 2026

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

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

  • Developed a novel loss function incorporating these global structures identified by DMT.
  • Trained deep image segmentation networks using the proposed loss function.

    • Main Results:

    • The novel loss function significantly improved network performance, particularly in topologically challenging areas.
    • Achieved superior performance on both DICE scores (a measure of overlap) and topological metrics across diverse datasets.
    • Demonstrated enhanced accuracy in segmenting fine-scale structures requiring topological integrity.

    Conclusions:

    • The proposed method effectively enhances topological accuracy in deep image segmentation.
    • Discrete Morse theory provides a powerful framework for improving segmentation of structures with complex topology.
    • This approach offers a significant advancement for downstream analysis tasks relying on accurate structural connectivity and closure.