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

Graph embedding to improve supervised classification and novel class detection: application to prostate cancer.

Anant Madabhushi1, Jianbo Shi, Mark Rosen

  • 1Rutgers University, Piscataway, NJ 08854, USA. anantm@rci.rutgers.edu

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|May 12, 2006
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

CardioMorph Atlas: a statistical approach to evaluate association between pulmonary tuberculosis and cardiac morphology from chest X-rays.

EBioMedicine·2026
Same author

Peri-aortic fat to assess cardiovascular aging using an AI-driven radiomic biomarker.

European heart journal·2026
Same author

Racial and ethnic disparities in clinical outcomes of HER2-positive metastatic breast cancer treated with antibody-drug conjugates.

Journal of the National Cancer Institute·2026
Same author

Retinal OCTA-derived microvascular remodeling is associated with coronary microvascular dysfunction in women with ischemia and no obstructive coronary artery disease: A pilot study.

American journal of preventive cardiology·2026
Same author

AI-Based Pathology classifier Predicts Sensitivity to Enzalutamide in Metastatic Hormone-Sensitive Prostate Cancer: A Biomarker Analysis of the ENZAMET Trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Precision medicine's inevitable trajectory toward rare-disease-sized cohorts: implications for machine learning and deep learning.

The Lancet. Digital health·2026

This study introduces graph embedding to enhance supervised classification accuracy by refining data labels. The novel visualization method aids in understanding class relationships and identifying new classes, demonstrated in prostate cancer MRI detection.

Area of Science:

  • Computational biology
  • Machine learning
  • Medical imaging analysis

Background:

  • High-dimensional data visualization is crucial for understanding complex datasets.
  • Supervised classification accuracy is often limited by unreliable object class labels.
  • Graph embedding techniques offer potential for improving data representation and classification.

Purpose of the Study:

  • To apply graph embedding for improving supervised classification accuracy, particularly with uncertain labels.
  • To develop a novel visualization method for class embeddings to reveal inter-class relationships.
  • To demonstrate the method's utility in a real-world medical imaging application.

Main Methods:

  • Utilized graph embedding to refine initial training set class labels, improving prior class distributions.

Related Experiment Videos

  • Developed a novel visualization technique for class embeddings to analyze inter-class relationships.
  • Applied the enhanced classification and visualization method to high-resolution MRI data for prostatic adenocarcinoma detection.

    • Main Results:

    • Demonstrated improved classification accuracy through refined class labels using graph embedding.
    • The novel visualization effectively illustrated inter-class relationships and suggested potential new classes.
    • Successfully detected prostatic adenocarcinoma using the proposed method on high-resolution MRI scans.

    Conclusions:

    • Graph embedding offers a powerful approach to enhance supervised classification accuracy, especially when labels are ambiguous.
    • The proposed visualization technique provides intuitive insights into data structure and class distributions.
    • This method shows significant promise for medical image analysis and disease detection, such as in prostate cancer.