Modeling human eye behavior during mammographic scanning: preliminary results

We investigate the use of an inexpensive and unobtrusive eye-tracking system to explore relationships between visual scanning patterns, pupillary response, and the clinical diagnoses of mammographic experts. One radiologist and three radiological technicians each examined a series of 14 mammograms for indications of abnormalities associated with breast cancer. The status of each mammogram was verified by biopsy. The eye-tracking system was used to measure and record eye position and pupil diameter as a function of time as the subjects scanned the mammograms. Three treatments were applied to the scan data to model the experts' eye behaviors. These included quantification of dwell time and pupil diameter as a function diagnostic accuracy in regions of the mammogram where abnormalities existed or were perceived; independent clustering of lookpoints without respect to abnormalities; and analysis of scan transitions between lookpoint clusters. Results of the analysis were consistent with extensive prior studies of eye-scan measures recorded during the diagnosis of abnormalities on chest radiograms. This preliminary investigation provides a proof of concept for use of the eye-tracking technology, experimental protocols, and analysis methodologies as the basis for expanded mammographic studies, with the promise of eventual adaptation as a source of diagnostic information in clinical practice.