Hiroyuki Sekiguchi, Presenter: Nothing to Disclose

Masahiro Yakami MD, PhD, Abstract Co-Author: Nothing to Disclose

Koji Fujimoto MD, PhD, Abstract Co-Author: Nothing to Disclose

Takeshi Kubo MD, Abstract Co-Author: Nothing to Disclose

Yutaka Emoto MD, PhD, Abstract Co-Author: Nothing to Disclose

Kaori Togashi MD, PhD, Abstract Co-Author: Research Grant, Bayer AG Research Grant, DAIICHI SANKYO Group Research Grant, Eisai Co, Ltd Research Grant, FUJIFILM Holdings Corporation Research Grant, Nihon Medi-Physics Co, Ltd Research Grant, Shimadzu Corporation Research Grant, Toshiba Corporation Research Grant, Covidien AG

Koji Sakai, Abstract Co-Author: Nothing to Disclose

Ryo Sakamoto, Abstract Co-Author: Nothing to Disclose

Gakuto Aoyama, Abstract Co-Author: Nothing to Disclose

Masami Kawagishi, Abstract Co-Author: Nothing to Disclose

Yoshio Iizuka, Abstract Co-Author: Nothing to Disclose

Hiroyuki Yamamoto, Abstract Co-Author: Nothing to Disclose

Performance of a current eye-tracking system in clinical settings can be improved with use of our eye-tracing unit.

An eye-tracking system has great potential for innovative diagnostic applications such as an oversight indication system. However, current eye-tracking systems are impractical in clinical settings because they cannot cover the entire diagnostic screen, especially in the height direction. We solved this problem by employing a self-directed eye-tracing unit that automatically tilts the base of the eye-tracking system according to the observer's eye position.  

We calibrated the eye-tracking system (X120; Tobii Technology, Stockholm, Sweden) against a diagnostic screen that consisted of two 20-inch lengthwise monitors. Then, eye-tracking data from daily radiograms were interpreted by three radiologists. The recording time for each data set was about 3 hours. During the data acquisition session, our head-tracking unit was switched on and off at 10-minute intervals. Finally, we compared the number of times the eye-tracking system lost the radiologist's viewpoint both with the support of the eye-tracing unit and without this support. The improved ratios when using the eye-tracing unit were 26%, 17% and 3% for radiologists A, B and C, respectively.  

This unit had a large effect on the results of radiologists A and B, while it had almost no effect on that of radiologist C. We therefore examined a viewpoint pattern for each radiologist and found that radiologist A divided the screen into three parts in the height direction and looked at them almost evenly. Radiologists B and C divided the screen into two parts in the height direction. We also found that radiologist C looked at images displayed mainly on upper parts of the screen. Therefore, his head was considered to have been almost stable during his diagnosis, and that is the reason why our eye-tracing unit had no effect on the results of radiologist C. For radiologists who use the entire diagnostic screen, this unit is helpful in improving the capacity of the eye-tracking system.  

Sekiguchi, H, Yakami, M, Fujimoto, K, Kubo, T, Emoto, Y, Togashi, K, Sakai, K, Sakamoto, R, Aoyama, G, Kawagishi, M, Iizuka, Y, Yamamoto, H, Improving the Practical Capability of an Eye-tracking System in Clinical Settings.  Radiological Society of North America 2013 Scientific Assembly and Annual Meeting, December 1 - December 6, 2013 ,Chicago IL. http://archive.rsna.org/2013/13015405.html