Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. A Dataset For Understanding Radiologist-artificial Intelligence Collaboration.
  1. Home
  3. A Dataset For Understanding Radiologist-artificial Intelligence Collaboration.

Related Experiment Video

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

744

A Dataset for Understanding Radiologist-Artificial Intelligence Collaboration.

Alex Moehring1, Manasi Kutwal2, Ray Huang2

  • 1Purdue University, Daniels School of Business, West Lafayette, IN, 47907, US. moehring@purdue.edu.

Scientific Data
|May 3, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces Collab-CXR, a large dataset for human-AI collaboration in chest X-ray interpretation. It reveals how radiologists use AI, impacting diagnostic accuracy and efficiency.

More Related Videos

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.1K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.3K

Related Experiment Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

744
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.1K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiology

Background:

  • Chest X-ray interpretation is complex, with potential for AI assistance.
  • Understanding human-AI collaboration is crucial for integrating AI into clinical workflows.
  • Existing datasets lack comprehensive comparisons of collaborative performance.

Purpose of the Study:

  • To introduce the Collab-CXR dataset, a novel resource for studying human-AI collaboration in chest X-ray interpretation.
  • To provide data on radiologist performance with and without AI assistance and clinical history.
  • To enable research into factors influencing collaborative effectiveness and diagnostic outcomes.

Main Methods:

  • Experimentally collected data from 227 radiologists assessing 324 historical chest X-ray cases.
  • Utilized a custom interface for probabilistic assessments of 104 thoracic pathologies.
  • Varied information conditions: AI assistance (yes/no) and clinical history (yes/no).

    • Main Results:

    • Collab-CXR is the largest dataset comparing human-AI collaborative performance against human or AI alone in radiology.
    • Rich metadata includes radiologist characteristics and decision-making processes.
    • Data supports within-subject and between-subject analyses for diverse research questions.

    Conclusions:

    • The Collab-CXR dataset facilitates rigorous investigation of human-AI integration in medical imaging.
    • Findings can inform AI tool development, implementation strategies, and optimize collaborative workflows.
    • Ultimately aims to improve patient care through enhanced diagnostic accuracy and efficiency.