Computer-Assisted Visual Search/Decision Aids as a Training Tool for Mammography

Abstract

The primary goal of the project is to develop a computer-assisted visual search (CAVS) mammography training tool that will improve the perceptual and cognitive skills of trainees leading to mammographic expertise. In two years we have completed two studies. The first equates experience by comparing perceptual skills of expert radiologists with lay people searching non-medical pictorial scenes for hidden targets. Results show that expert radiology search and detection strategies do not transfer to the non-medical search and detection tasks. Thus, radiology expertise consists of specific perceptual and cognitive skills that develop primarily from experience reading medical x-ray images. The second study examines the roles of training and experience on the acquisition of mammography expertise. We compared reading performance of experienced mammographers with residents at different levels of training and technologists with little training or experience reading mammograms. Results show, first that performance is a linear increasing function of log reading experience, second that mammography training provides insufficient reading experience to meet clinical standards of performance, third that expert mammography performance is characterized by a speed-accuracy relationship that is the result of tuning of visual search and recognition skills acquired primary through practice reading mammograms with feedback.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1999
Accession Number
ADA374215

Entities

People

  • Calvin Nodine

Organizations

  • University of Pennsylvania

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Computer Vision
  • Computers
  • Detection
  • Health Services
  • Identification
  • Image Processing
  • Information Processing
  • Information Science
  • Materials
  • Medical Personnel
  • Object Recognition
  • Psychology
  • Recognition
  • Standards
  • Training
  • X Rays

Readers

  • Artificial Intelligence
  • Oncology and Biomarker-Based Cancer Detection.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.