Article Text

PDF
THU0583 Does Eye Gaze Tracking Have the Ability to Assess How Rheumatologists Evaluate Musculoskeletal Ultrasound Images?
  1. A. Kosevoi-Tichie1,
  2. F. Berghea1,2,
  3. V. Vlad1,
  4. M. Abobului1,2,
  5. M. Trandafir1,
  6. T. Gudu1,
  7. A. Peltea1,
  8. M. Duna1,
  9. L. Groseanu1,
  10. C. Patrascu1,
  11. R. Ionescu1
  12. on behalf of RCRD
  1. 1Rheumatology, Sf. Maria Hospital
  2. 2Carol Davila University Of Medicine And Pharmacy, Bucharest, Romania

Abstract

Background Eye gaze tracking (EGT) is a method used to measure eye position and eye movement, defined as visual attention. Much existing research has used the connection between visual attention and EGT in a broad spectrum of fields such as psychology or cognitive linguistics. The application of EGT in terms of evaluating the knowledge and expertise of individuals has been widely ignored, although a strong frame of study has indicated that this method may be weighed as unbiased indicator of the focus of visual attention.

Objectives To evaluate the ability of EGT in assessing quantitatively and qualitatively how rheumatologists analyze musculoskeletal ultrasound images (MSUS).

Methods 11 young rheumatologists in training were evaluated in December 2014. Two experts in this field were also asked to participate. 12 ultrasound images of different rheumatologic pathologies were used (displayed on 21inch HD monitor), and 6 other different images were used in order to calibrate the machine. The images were analyzed using The Eye Tribe (Hardware) and Eyeproof (Software). The data was analyzed using SPSS and Microsoft Excel.

For every ultrasound image 1 to 5 regions of interest were set by a team of MSUS experts. Items assessed were: Total time of evaluation (TTE), time spent to reach the first region of interest (TSRF), time spent upon the region of interest (TSUR), ratio of time spent in the region of interest (ROI) and time spent outside the region of interest, number of elements identified in the region of interest versus the rest of the image.

Results Total time of evaluation - mean (SD) - for experts was 5,4 (1,3) seconds versus 8,9 (2,7) seconds for unexperienced rheumatologists. Time spent to reach the first region of interest for experts was 0,6 (0,8) msec and 3,2 (2,1) msec for non-experts. The unexperienced sonographers focused on a higher number of elements outside the region of interest than experts: 8,6 (3,8) vs. 2 (0,5). There was no significant difference between the two groups of evaluators regarding the time spent upon the region of interest.

Conclusions Experienced sonographers spend less time than unexperienced ones when assessing an ultrasound image (mainly because they focus quicker on the ROIs). Once focused on a particular ROI both groups tend to act similarly. EGT can be a useful tool in assessing the way ultrasound images are visually analyzed and can be used to improve MSUS training and optimize the visual analyze pattern of the sonographer.

References

  1. Robert H. Tai, John F. Loehr, Friederick J. Bringham An exploroation of the use of eye-gaze tracking to study problem-solving on standarized science assessments. International Journal of Research&Method in Education, volume 29, Issue 2, 2006.

  2. Carlos H. Morimoto, Marcio R.M. Mimica Eye gaze tracking techniques for interactive applications. Computer Vision and Image understanding Vol 98, issue 1, April 2005

  3. Olmeda, R. A. (2002) Using eye movements to differentiate students with and without ADHD in a simple reading task. Unpublished manuscript, Charlottesville, VA, The University of Virginia

Acknowledgements RCRD team.

Disclosure of Interest None declared

Statistics from Altmetric.com

Request permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.