Purchase this article with an account.
Po-He Tseng, Ian Cameron, Doug Munoz, Laurent Itti; Screening attentional-related diseases based on correlation between salience and gaze. Journal of Vision 2009;9(8):372. doi: 10.1167/9.8.372.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
Several studies have shown that eye movements and certain complex visual functions are influenced by diseases such as Parkinson's Disease (PD), Attention Deficit Hyperactivity Disorder (ADHD) and Fetal Alcohol Spectrum Disorder (FASD). Here we examine how bottom-up (stimulus-driven) attentional selection mechanisms may differ between patient and control populations, and we take advantage of the difference to develop classifiers to differentiate patients from controls. We tracked gaze of five groups of observers (16 control children, aged 7–13; 14 ADHD children, aged 9–15; 10 FASD children, aged 9–15; 16 control elderly, aged 66–82; and 11 PD elderly, aged 53–73) while they freely viewed MTV-style videos. These stimuli are composed of short (2–4 seconds) clips of natural scenes, strung together without semantic continuity, which may reduce top-down (contextual) expectations and emphasize bottom-up influences on gaze allocations at the scene change. We used a saliency model to compute bottom-up saliency maps for every video frame. Saliency maps can be computed from a full set of features (color, intensity, orientation, flicker, motion) or from individual features. Support-vector-machine classifiers were built for each feature contributing to the saliency map and for the combination of them. Leave-one-out was used to train and test the classifiers. Two classification experiments were performed: (1) among ADHD, FASD and control children; (2) between PD and control elderly. The best classification accuracy of individual classifier in experiment 1 and 2 were 67.5% and 88.9% respectively. Classifiers were combined by a majority-vote boosting strategy to increase the classification accuracy (experiment 1 - 95%; experiment 2 - 100%). This study demonstrates that bottom-up attention mechanisms are greatly influenced by PD, ADHD and FASD, and the difference can serve as a probable screening/diagnosis tool for clinical applications.
This PDF is available to Subscribers Only