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 8, 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

Adaptive learning for relevance feedback: application to digital mammography.

Jung Hun Oh1, Yongyi Yang, Issam El Naqa

  • 1Department of Radiation Oncology, Washington University School of Medicine, St. Louis, Missouri 63110, USA.

Medical Physics
|October 1, 2010
PubMed
Summary

This study introduces an adaptive content-based image retrieval (CBIR) system using incremental learning for mammograms. The system enhances image retrieval accuracy and pathology matching in medical databases.

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

Early Salivary Gland Shrinkage Is Associated With an Increased Risk of Acute Xerostomia in Head and Neck Cancer Radiation Therapy.

Advances in radiation oncology·2026
Same author

Artificial intelligence for optimization of immunotherapy: current applications and transformative potential.

Frontiers in immunology·2026
Same author

Imaging Biomarkers in Radiotherapy.

Cancers·2026
Same author

OncoPT: long-context transformer models for in hospital tumor phenotype extraction from pathology reports.

NPJ digital medicine·2026
Same author

Launching <i>BJR</i>|<i>Artificial intelligence</i>: an editorial.

BJR artificial intelligence·2026
Same author

A differentiated effector T cell repertoire defines a functionally high-risk group of smoldering myeloma patients.

Blood cancer journal·2026

Area of Science:

  • Medical Imaging
  • Computer Science
  • Machine Learning

Background:

  • Medical image databases are growing rapidly, necessitating efficient retrieval systems.
  • Current content-based image retrieval (CBIR) techniques have limited success in biomedicine.
  • Mammographic image retrieval requires specialized and accurate systems.

Purpose of the Study:

  • To present an adaptive content-based image retrieval (CBIR) system for mammographic databases.
  • To improve the performance and accuracy of image retrieval in mammograms.
  • To address the limitations of existing CBIR systems in biomedical applications.

Main Methods:

  • Proposed a novel relevance feedback approach using incremental learning with support vector machine (SVM) regression.

Related Experiment Videos

Last Updated: Jun 8, 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

  • Introduced a local perturbation method to enhance the relevance feedback system.
  • Utilized two mammogram datasets (76 and 200 images) for validation, with scoring based on geometry and expert radiological findings.

    • Main Results:

    • The relevance feedback strategy significantly improved retrieval precision for both datasets.
    • Achieved high efficiency compared to offline SVM, with an average precision of 0.48 and AUC of 0.79 for the 200-image dataset.
    • Demonstrated a pathology matching rate exceeding 80% after relevance feedback.

    Conclusions:

    • The proposed adaptive CBIR system is more accurate than non-feedback models for mammographic image retrieval.
    • The system excels in pathology matching, improving diagnostic relevance.
    • The approach is effective for online relevance feedback applications in medical imaging.