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

Improved dynamic-programming-based algorithms for segmentation of masses in mammograms.

Alfonso Rojas Domínguez1, Asoke K Nandi

  • 1Department of Electrical Engineering and Electronics, The University of Liverpool, Brownlow Hill, Liverpool, L69 3GJ, United Kingdom.

Medical Physics
|December 13, 2007
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

Artificial neural networks fighting real neural decline: a systematic review of AI in Alzheimer's research.

Artificial intelligence review·2026
Same author

Diffusion Tensor Magnetic Resonance Image Registration Based on Parallel Dual-Channel VoxelMorph.

IEEE journal of biomedical and health informatics·2025
Same author

Brain-Inspired Meta-Learning for Few-Shot Bearing Fault Diagnosis.

IEEE transactions on neural networks and learning systems·2025
Same author

A texture enhanced attention model for defect detection in thermal protection materials.

Scientific reports·2025
Same author

Three-dimensional reconstruction method for layered structures based on a frequency modulated continuous wave terahertz radar.

Optics express·2024
Same author

Unified Flowing Normality Learning for Rotating Machinery Anomaly Detection in Continuous Time-Varying Conditions.

IEEE transactions on cybernetics·2024
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
See all related articles

Two new algorithms, Improved-DPBT (IDPBT) and ID2PBT, enhance breast mass segmentation accuracy in mammography. These improved methods outperform the original DPBT algorithm by producing more optimally segmented regions.

Area of Science:

  • Medical Physics
  • Image Analysis
  • Computer-Aided Diagnosis

Background:

  • Accurate segmentation of breast masses in mammography is crucial for diagnosis.
  • The dynamic programming-based boundary tracing (DPBT) algorithm offers a framework for this task.
  • Existing DPBT algorithms rely on assumptions that may limit performance across diverse datasets.

Purpose of the Study:

  • To develop and evaluate novel boundary tracing algorithms for improved breast mass segmentation.
  • To address limitations in the original DPBT algorithm's cost function and parameter selection.
  • To enhance the accuracy and robustness of mammographic image segmentation.

Main Methods:

  • Modification of the local cost function computation within the DPBT framework, leading to the Improved-DPBT (IDPBT) algorithm.

Related Experiment Videos

  • Development of a dynamic parameter selection procedure for the cost function, creating the ID2PBT algorithm.
  • Experimental validation using 349 mammographic images, comparing IDPBT and ID2PBT against the original DPBT algorithm.

    • Main Results:

    • Both IDPBT and ID2PBT algorithms demonstrated superior performance compared to the original DPBT algorithm.
    • Improvements were most significant at high segmentation accuracy values, indicating more optimal region segmentation.
    • The new algorithms produced more optimally segmented regions rather than just a general increase in average quality.

    Conclusions:

    • The developed IDPBT and ID2PBT algorithms represent significant advancements in breast mass segmentation.
    • Dynamic adjustment of cost function parameters enhances algorithm adaptability and performance.
    • These improved algorithms hold promise for more accurate computer-aided diagnosis in mammography.