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

Integrating image data into biomedical text categorization.

Hagit Shatkay1, Nawei Chen, Dorothea Blostein

  • 1School of Computing, Queen's University, Kingston, Ontario, Canada. shatkay@cs.queensu.ca

Bioinformatics (Oxford, England)
|July 29, 2006
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

Modelling and analysis of the HIV/AIDS epidemic with fast and slow asymptomatic infections in China from 2008 to 2021.

Mathematical biosciences and engineering : MBE·2023
Same author

Enhancing biomedical search interfaces with images.

Bioinformatics advances·2023
Same author

Characterizing a Common Class of Spontaneous Movements.

International journal of therapeutic massage & bodywork·2022
Same author

Toward ECG-based analysis of hypertrophic cardiomyopathy: a novel ECG segmentation method for handling abnormalities.

Journal of the American Medical Informatics Association : JAMIA·2022
Same author

Domain-Informed Neural Networks for Interaction Localization Within Astroparticle Experiments.

Frontiers in artificial intelligence·2022
Same author

Translational drug-interaction corpus.

Database : the journal of biological databases and curation·2022
Same journal

Probabilistic RNA designability via interpretable ensemble approximation and dynamic decomposition.

Bioinformatics (Oxford, England)·2026
Same journal

Quantifying domain-specific relevance of computational biology Wikipedia articles using TF-IDF and cosine similarity.

Bioinformatics (Oxford, England)·2026
Same journal

GATSBI: improving context-aware protein embeddings through biologically motivated data splits.

Bioinformatics (Oxford, England)·2026
Same journal

BiMba: using Vision Mamba to predict protein sites that bind other proteins.

Bioinformatics (Oxford, England)·2026
Same journal

ProMeta: a meta-learning framework for robust disease diagnosis and prediction from plasma proteomics.

Bioinformatics (Oxford, England)·2026
Same journal

Is a Win-Win possible? Achieving pareto-optimal privacy-utility balance in fine-tuned genome language model embeddings against embedding reconstruction attacks.

Bioinformatics (Oxford, England)·2026
See all related articles

This study explores using image data to improve biomedical document categorization. Integrating image features with text analysis shows strong potential for enhancing information retrieval and curation tasks.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Information Retrieval

Background:

  • Biomedical article categorization is crucial for curation and text mining.
  • Current methods primarily rely on text content, overlooking valuable image information.
  • Image features, like figure captions, have proven useful in prior text mining contests.

Purpose of the Study:

  • To investigate the utility of image-derived features for biomedical document categorization.
  • To develop and evaluate a method for integrating image and text information.
  • To enhance the accuracy and efficiency of biomedical document triage.

Main Methods:

  • Extracting features directly from image data within biomedical articles.
  • Developing a classification approach using image-derived features alone.

Related Experiment Videos

  • Combining image features with traditional text-based features for a hybrid classification model.
  • Applying the method to the TREC Genomics track 2004 triage task.

    • Main Results:

    • Preliminary results indicate that image-derived features can be effectively used for categorization.
    • Integrating image features with text significantly enhances classification performance.
    • The proposed method shows strong potential for complementing existing text-based categorization approaches.

    Conclusions:

    • Image data offers valuable, complementary information for biomedical document categorization.
    • A hybrid approach combining image and text features can improve the accuracy of document triage and curation.
    • This methodology has the potential to significantly advance biomedical text mining and information management.