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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Self-supervised contrastive learning enables robust electrocardiogram-based cardiac classification.

Heart rhythm O2·2026
Same author

Differential profiles of motor dysfunction in amnestic versus non-amnestic mild cognitive impairment - The Vietnam Era Twin Study of Aging.

Neuroscience·2026
Same author

Mucus plugs in chronic obstructive pulmonary disease are heterogeneous in size and shape and occur in relatively large airways.

American journal of respiratory and critical care medicine·2026
Same author

Predicting Ventricular Arrhythmia in Myocardial Ischemia Using Machine Learning.

Computing in cardiology·2026
Same author

Changes in the Neighborhood Built Environment and Chronic Health Conditions in Washington, DC, in 2014-2019: Longitudinal Analysis.

JMIR formative research·2025
Same author

SPIROMICS HF: Rationale, Design, and Reproducibility of Measures.

Circulation. Heart failure·2025

Related Experiment Video

Updated: Jul 21, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation.

Ricardo Bigolin Lanfredi1, Joyce D Schroeder2, Tolga Tasdizen1

  • 1Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, United States.

Frontiers in Radiology
|July 26, 2023
PubMed
Summary

Researchers used eye-tracking data from radiologists to train convolutional neural networks (CNNs) for chest x-ray (CXR) analysis. This method enhances model interpretability by localizing abnormalities without affecting classification accuracy.

Keywords:
annotationchest x-ray (CXR)eye trackinggazeinterpretabilitylocalization

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.7K
Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.4K

Related Experiment Videos

Last Updated: Jul 21, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.7K
Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.4K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in radiology
  • Computer vision

Background:

  • Convolutional neural networks (CNNs) are effective for chest x-ray (CXR) analysis.
  • Interpretable AI models that localize abnormalities using bounding boxes are crucial but limited by costly data acquisition.
  • Eye-tracking (ET) data offers a potential alternative for training localization models.

Purpose of the Study:

  • To investigate the utility of radiologist eye-tracking (ET) data for training CNNs to localize abnormalities in CXR images.
  • To improve the interpretability of CNNs for CXR analysis without compromising classification performance.

Main Methods:

  • Collected ET data from radiologists during CXR report dictation.
  • Extracted ET data snippets associated with specific keywords.
  • Used these ET data snippets to supervise the localization of abnormalities within CNNs.
  • Evaluated the impact on both model interpretability and image-level classification accuracy.

Main Results:

  • The proposed method successfully utilized ET data to train CNNs for abnormality localization.
  • Model interpretability was enhanced through improved localization capabilities.
  • Image-level classification performance remained unaffected by the incorporation of ET-supervised localization.

Conclusions:

  • Eye-tracking data can be effectively leveraged to train interpretable CNNs for CXR analysis.
  • This approach provides a cost-effective method for improving AI model localization capabilities.
  • The findings suggest a promising direction for developing more transparent and reliable AI tools in medical imaging.