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: Mar 15, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Task-Driven Dictionary Learning Based on Mutual Information for Medical Image Classification.

Idit Diamant, Eyal Klang, Michal Amitai

    IEEE Transactions on Bio-Medical Engineering
    |September 9, 2016
    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

    Computer-aided diagnosis of eyelid skin tumours: new observations.

    Canadian journal of ophthalmology. Journal canadien d'ophtalmologie·2026
    Same author

    Use of AI agents to assess preoperative frailty in cancer patients.

    npj digital surgery·2026
    Same author

    Clinical agents fail silently on patient identity.

    International journal of medical informatics·2026
    Same author

    Large language models integrated into brain-computer interfaces for communication and control: a systematic review.

    Biomedical physics & engineering express·2026
    Same author

    Sociodemographic bias in large language model clinical trial screening.

    Journal of the American Medical Informatics Association : JAMIA·2026
    Same author

    Sociodemographic Variability in Pediatric Emergency Decisions by AI.

    Pediatrics·2026
    Same journal

    Fast Prospective Motion Correction for MRI Based on Electromagnetic Induction Coils with Low Footprint and In-place Calibration.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Digital Twin Modeling of MR Gradient Coils for Accurate Gradient Safety Evaluation of Implantable Medical Devices.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    A Method for Improving Human Joint Moment Estimation during Lower Limb Rehabilitation Training Based on sEMG Signals.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Assessment of skin stiffness in systemic sclerosis using optical coherence elastography: A comparative study with histology and clinical parameters.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    Modeling Dyadic Interdependence in Endocrine Functioning: A Multilevel Machine Learning Study of Adults with Cancer and Their Caregivers.

    IEEE transactions on bio-medical engineering·2026
    Same journal

    A Kalman Filter-Based Framework for Granger Causality Assessment: Application in Tracking Maternal-Fetal Heart Rate Coupling.

    IEEE transactions on bio-medical engineering·2026
    See all related articles

    A new bag-of-visual-words (BoVW) method enhances medical image classification by learning task-specific visual words. This approach improves accuracy and identifies relevant image regions without needing explicit annotations.

    Area of Science:

    • Computer Vision
    • Medical Imaging Analysis
    • Machine Learning

    Background:

    • Automated medical image classification is crucial for diagnosis.
    • Traditional bag-of-visual-words (BoVW) methods have limitations in adapting to specific medical tasks.
    • There is a need for improved feature selection in medical image analysis.

    Purpose of the Study:

    • To introduce a novel variant of the bag-of-visual-words (BoVW) method for enhanced automated medical image classification.
    • To improve the BoVW model by learning a task-driven dictionary of relevant visual words.
    • To develop relevance maps for visualizing and localizing classification decisions.

    Main Methods:

    • Implemented a mutual information-based criterion to learn a task-driven dictionary for the BoVW model.

    Related Experiment Videos

    Last Updated: Mar 15, 2026

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

    Published on: October 10, 2018

    8.9K
  • Applied the enhanced BoVW approach to chest X-ray pathology identification, liver lesion classification in CT images, and breast microcalcification classification.
  • Generated relevance maps to interpret the algorithm's decision-making process.

    • Main Results:

    • Achieved improved classification performance across all tested medical imaging tasks compared to the classical BoVW method.
    • Demonstrated significant improvements in area under the curve for enlarged mediastinum identification (0.876 vs. 0.855).
    • Reported a 4% improvement in microcalcification classification and enhanced sensitivity (6%) and specificity (2%) for liver lesions.

    Conclusions:

    • The proposed BoVW variant significantly improves medical image classification accuracy.
    • The method effectively identifies informative visual words and relevant image regions without requiring explicit annotations.
    • This approach offers valuable computer-aided support for medical experts in image analysis.