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

Computer-displayed eye position as a visual aid to pulmonary nodule interpretation.

H L Kundel1, C F Nodine, E A Krupinski

  • 1Department of Radiology, University of Pennsylvania, Philadelphia 19104-6086.

Investigative Radiology
|August 1, 1990
PubMed
Summary

Computer-aided detection using eye-tracking visual feedback significantly improves nodule identification on chest radiographs. This AI tool highlights potential missed nodules, enhancing radiologist accuracy in detecting lung abnormalities.

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

Characteristics of trainee interpretation time during simulated screening mammography.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Embracing diversity in radiography: What can we learn from our colleagues?

Radiography (London, England : 1995)·2018
Same author

MRI characteristics associated with high-grade myxoid liposarcoma.

Clinical radiology·2017
Same author

Bayesian estimation of cerebral perfusion using reduced-contrast-dose dynamic susceptibility contrast perfusion at 3T.

AJNR. American journal of neuroradiology·2014
Same author

Predictive role of imaging in sentinel lymph node dissection for melanoma.

Lymphology·2014
Same author

The Medical Image Perception Society XIV conference.

The British journal of radiology·2012

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging Analysis

Background:

  • Lung nodules are frequently missed on initial chest radiograph readings, with approximately 30% going undetected.
  • Missed nodules often receive prolonged visual attention, suggesting a need for improved detection aids.

Purpose of the Study:

  • To evaluate the effectiveness of a computer-aided detection (CAD) system providing visual feedback based on eye-position data for improving nodule detection on chest radiographs.

Main Methods:

  • Six radiology residents reviewed 40 chest images, with eye-position and gaze duration recorded.
  • Participants were divided into two groups: one received visual feedback highlighting potential nodules, the other did not.
  • A crossover design was used, with participants switching conditions after two months to control for practice effects.

Related Experiment Videos

Main Results:

  • Readers utilizing visual feedback demonstrated a 16% improvement in nodule detection accuracy, as measured by the alternative free-response operating characteristic (AFROC) curve area (A1).
  • The same readers showed no improvement when reviewing images without visual feedback.

Conclusions:

  • Visual feedback generated by an eye-tracking-based computer algorithm is an effective aid for enhancing radiologist performance in detecting lung nodules on chest radiographs.
  • This technology has the potential to reduce missed diagnoses and improve patient outcomes in thoracic imaging.