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

Live-wires using path-graphs.

S König1, J Hesser

  • 1Institute for Computational Medicine, Universities of Mannheim and Heidelberg, Germany skoenig@rumms.uni-mannheim.de

Methods of Information in Medicine
|October 9, 2004
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

Longitudinal Genome-Wide Association Study for Female Fertility Traits in German Holstein Cattle.

Animal genetics·2026
Same author

Knowledge-based automated radiation therapy treatment planning utilizing dose prediction with a 2.5D-U-Net.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025
Same author

Characterization of German sheep production systems and derivation of respective economic values for breeding traits.

Veterinary and animal science·2025
Same author

Internal in-frame translation generates Cas11b, which is important for effective interference in an archaeal CRISPR-Cas system.

Frontiers in microbiology·2025
Same author

Single-Step Breeding Value Estimations and Optimum Contribution Selection in Endangered Dual-Purpose German Black Pied Cattle (DSN) Using a Breed Specific SNP Chip.

Journal of animal breeding and genetics = Zeitschrift fur Tierzuchtung und Zuchtungsbiologie·2025
Same author

Evaluating reproduction traits in a crossbreeding program between indigenous and exotic sheep in semi-arid lands.

Animal : an international journal of animal bioscience·2024
Same journal

Design and methodological development of a digital clinical safety training programme informed by a national framework: a New Zealand case study.

Methods of information in medicine·2026
Same journal

Panic Prediction from Digital Phenotyping: Subject-Level Cross-Validation Reveals Limited Between-Person Generalization.

Methods of information in medicine·2026
Same journal

Agent-Based Modeling Approach for Population Dynamics of the Biological Vector Aedes Aegypti.

Methods of information in medicine·2026
Same journal

A Statistical Framework for Person-centered Analysis of Digital Service Use in Public Health and Social Care.

Methods of information in medicine·2026
Same journal

Assessing the Quality of Electronic Discharge Summaries: A Cross-Sectional Study Using the Validated Spanish Version of the PDQI-9.

Methods of information in medicine·2026
Same journal

A Knowledge Graph-Driven Hypergeometric Efficacy Prediction Model for Classical Traditional Chinese Herbal Formulas.

Methods of information in medicine·2026
See all related articles

The new Path-Graph approach enhances the Live-Wire segmentation method, improving accuracy by reducing misclassified pixels and boundary deviations. The Live-Lane extension does not offer significant benefits when combined with pre-segmented data.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Geometry

Background:

  • Interactive image segmentation methods like Live-Wire are crucial for precise image analysis.
  • Pre-segmentation of data can influence the performance of interactive segmentation algorithms.
  • Graph-based representations are fundamental to many image segmentation techniques.

Purpose of the Study:

  • To introduce and evaluate a novel Path-Graph approach for the 2D Live-Wire segmentation method.
  • To assess the utility of the Live-Lane extension when applied to pre-segmented image data.
  • To compare the performance of the Path-Graph with the traditional Node-Graph in Live-Wire segmentation.

Main Methods:

  • Automatic over-segmentation of image data using region growing and automatic seed point generation.

Related Experiment Videos

  • Application of the Live-Wire algorithm on mosaic data, utilizing homogeneous region outlines for graph construction.
  • Definition of a new Path-Graph structure where standard graph edges become vertices and vertices become edge connectivity.

    • Main Results:

    • The Path-Graph approach enables finer segmentation compared to the Node-Graph.
    • Achieved a 20.66% reduction in incorrectly classified pixels.
    • Reduced mean boundary deviation by 11.61%, with a minor performance loss of 2.41% due to Live-Lane computations.

    Conclusions:

    • The redefined Path-Graph significantly enhances the quality of Live-Wire segmentation.
    • The Live-Lane extension, when used with pre-segmentation, does not provide justifiable advantages for the analyzed data.