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: Apr 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.9K

Region based stellate features combined with variable selection using AdaBoost learning in mammographic

Dae Hoe Kim1, Jae Young Choi2, Yong Man Ro1

  • 1Image and Video Systems Laboratory, Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-Gu, Daejeon 305-701, Republic of Korea.

Computers in Biology and Medicine
|December 3, 2014
PubMed
Summary

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

The comparison of two pendrin inhibitors, YS-01 and PDSinh-C01, in lipopolysaccharide-induced acute lung injury.

Scientific reports·2026
Same author

Prospective Midterm Outcomes of the PULSTA Self-Expandable Transcatheter Pulmonary Valve: The PULSTA CE Approval Study.

Circulation. Cardiovascular interventions·2026
Same author

A complete human pancreatic cancer genome.

bioRxiv : the preprint server for biology·2026
Same author

Rare missense variants in <i>MYO7A</i> and <i>OTOP2</i> genes in a South Korean Meniere's disease cohort.

Journal of medical genetics·2026
Same author

Auditory genotype-phenotype correlation of patients with variants in STRC.

Scientific reports·2025
Same author

Pendrin inhibition is associated with protective effect of prone positioning in a ventilator-induced lung injury mouse model.

Scientific reports·2025

A new method uses region-based stellate features to improve the detection of malignant masses on mammograms. This approach enhances classification accuracy for spiculated masses, outperforming existing methods.

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Accurate differentiation of spiculated malignant masses from normal tissues on mammograms is crucial for early cancer detection.
  • Existing feature extraction methods may not fully capture the complex patterns of spiculated masses.

Purpose of the Study:

  • To develop and evaluate a novel method for extracting region-based stellate features for improved mammographic mass classification.
  • To incorporate a variable selection algorithm to optimize feature subsets for enhanced diagnostic performance.

Main Methods:

  • A region of interest (ROI) is divided into core, inner, and outer subregions for feature extraction.
  • Region-based stellate features are computed based on statistical characteristics of these subregions.
Keywords:
AdaBoostComputer-aided detectionMammographyRegion-based stellate featuresSpiculated massesVariable selection metric

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.7K

Related Experiment Videos

Last Updated: Apr 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.9K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.7K
  • An AdaBoost-based variable selection algorithm with a new importance metric is employed.

    • Main Results:

    • The proposed region-based stellate features significantly outperform state-of-the-art methods in classifying spiculated masses.
    • Features extracted from automatically segmented ROIs demonstrated superior performance.
    • Combining region-based stellate features with the proposed variable selection strategy markedly improved classification and detection.

    Conclusions:

    • The developed region-based stellate features offer a powerful tool for enhancing the accuracy of mammographic analysis.
    • The integration of AdaBoost-based variable selection further refines the classification of malignant masses.
    • This method shows significant potential for improving computer-aided detection systems for breast cancer.