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

Population-based incremental interactive concept learning for image retrieval by stochastic string segmentations.

Sennay Ghebreab1, C Carl Jaffe, Arnold W M Smeulders

  • 1Biomedical Imaging Group Rotterdam, Room Ee2167, Department of Radiology, Erasmus MC Rotterdam, Dr. Molewaterplein 50, 3015 GE Rotterdam, The Netherlands. s.ghebreab@erasmusmc.nl

IEEE Transactions on Medical Imaging
|June 12, 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

Integration of proteomics with CT-based qualitative and radiomic features in high-grade serous ovarian cancer patients: an exploratory analysis.

European radiology·2020
Same author

A 3D-Printed Patient-Specific Phantom for External Beam Radiation Therapy of Prostate Cancer.

Journal of engineering and science in medical diagnostics and therapy·2019
Same author

Scene complexity modulates degree of feedback activity during object detection in natural scenes.

PLoS computational biology·2019
Same author

Point Light Source Position Estimation From RGB-D Images by Learning Surface Attributes.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2017
Same author

Radiogenomics of High-Grade Serous Ovarian Cancer: Multireader Multi-Institutional Study from the Cancer Genome Atlas Ovarian Cancer Imaging Research Group.

Radiology·2017
Same author

The time course of natural scene perception with reduced attention.

Journal of neurophysiology·2015

This study introduces a novel concept-based medical image retrieval method. It accurately retrieves cervical vertebrae X-rays by learning user preferences for precise and efficient image searching.

Area of Science:

  • Medical Imaging
  • Computer Science
  • Artificial Intelligence

Background:

  • Existing semantic-based medical image retrieval methods struggle with content complexity and user subjectivity.
  • Personalized and accurate retrieval is crucial for effective medical image analysis.

Purpose of the Study:

  • To propose a novel concept-based medical image retrieval method that surpasses existing semantic approaches.
  • To develop a system that personalizes image retrieval based on user-specific concepts and preferences.

Main Methods:

  • Objects are described using continuous boundary features, and concepts are represented by stochastic characteristics of object populations.
  • A population-based incremental learning technique combined with relevance feedback is used for concept customization.

Related Experiment Videos

  • A single parameter controls the exploration-exploitation balance in concept customization for efficient search.

    • Main Results:

    • The method achieved precise and accurate results in direct searches on a database of cervical vertebrae X-rays.
    • The approach efficiently and effectively explored the search space in open-ended searches.
    • Demonstrated successful concept-based image retrieval on 292 digitized X-ray images with abnormalities.

    Conclusions:

    • The proposed concept-based method offers a flexible and effective approach to medical image retrieval.
    • This technique enhances retrieval accuracy and efficiency by incorporating user subjectivity and preferences.
    • The method holds promise for improving the analysis of complex medical image datasets.