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

Combining classifiers using their receiver operating characteristics and maximum likelihood estimation.

Steven Haker1, William M Wells, Simon K Warfield

  • 1Surgical Planning Lab, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, 02115, USA. haker@bwh.harvard.edu

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

Outcome Prediction in Pediatric Traumatic Brain Injury Utilizing Social Determinants of Health and Machine Learning Methods.

AJNR. American journal of neuroradiology·2025
Same author

Deep Learning-based Time-to-event Analysis of Depression and Asthma using the All of Us Research Program.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2025
Same author

Endovascular treatment of sigmoid Sinus diverticulum in patients with pulsatile tinnitus.

Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences·2025
Same author

Medical foundation large language models for comprehensive text analysis and beyond.

NPJ digital medicine·2025
Same author

Challenges and opportunities for advancing functional MRI in clinical practice.

Brain : a journal of neurology·2025
Same author

Predicting positive <i>Clostridioides difficile</i> test results using large-scale longitudinal data of demographics and medication history.

Heliyon·2025
Same journal

LiftReg: Limited Angle 2D/3D Deformable Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Inverse Consistency by Construction for Multistep Deep Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Can Crowdsourced Annotations Improve AI-based Congestion Scoring For Bedside Lung Ultrasound?

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Equivariant Filters for Efficient Tracking in 3D Imaging.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Lobar Lung Density Embeddings with a Transformer encoder (LobTe) to predict emphysema progression in COPD.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

uniGradICON: A Foundation Model for Medical Image Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
See all related articles

This study presents a novel method for combining diagnostic test results. The approach uses Receiver Operating Characteristic (ROC) analysis to create a combined rule for independent classifiers, improving diagnostic accuracy.

Area of Science:

  • Medical imaging
  • Machine learning
  • Diagnostic accuracy

Background:

  • Multiple diagnostic tests (classifiers) are common in medicine, especially in image analysis.
  • Combining classifiers can improve diagnostic performance, but optimal combination strategies are complex.
  • Existing methods often require classifiers trained on a common dataset, limiting their application.

Purpose of the Study:

  • To introduce a simple strategy for combining results from classifiers that were not jointly trained.
  • To leverage Receiver Operating Characteristic (ROC) analysis for classifier combination.
  • To provide insights into ROC analysis applications in medical imaging.

Main Methods:

  • Developed a strategy for combining independent classifiers, assuming conditional independence.

Related Experiment Videos

  • Utilized maximum likelihood analysis to determine a combination rule.
  • Calculated a combined Receiver Operating Characteristic (ROC) curve for evaluating performance.

    • Main Results:

    • The proposed method enables classifier combination without requiring a shared training dataset.
    • The strategy effectively determines combination rules based on ROC operating points.
    • Demonstrated the utility of ROC analysis for combining independent classifiers.

    Conclusions:

    • A straightforward method for combining independent classifiers using ROC analysis is presented.
    • This approach offers a valuable tool for enhancing diagnostic accuracy in medical imaging.
    • The findings contribute to the understanding and application of ROC analysis in clinical settings.