Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Depth-induced Saliency Comparison Network for Diagnosis of Alzheimer's Disease via Jointly Analysis of Visual Stimuli and Eye Movements

Yu Liu, Wenlin Zhang, Shaochu Wang, Fangyu Zuo, Peiguang Jing, Yong Ji

TL;DR

An Depth-induced saliency comparison network for eye movement analysis, which may be used for diagnosis the Alzheimers disease, and introduces serial attention module (SEA) to emphasis the most abnormal eye movement behaviors to reduce personal bias for a more robust result.

Abstract

Early diagnosis of Alzheimer's Disease (AD) is very important for following medical treatments, and eye movements under special visual stimuli may serve as a potential non-invasive biomarker for detecting cognitive abnormalities of AD patients. In this paper, we propose an Depth-induced saliency comparison network (DISCN) for eye movement analysis, which may be used for diagnosis the Alzheimers disease. In DISCN, a salient attention module fuses normal eye movements with RGB and depth maps of visual stimuli using hierarchical salient attention (SAA) to evaluate comprehensive saliency maps, which contain information from both visual stimuli and normal eye movement behaviors. In addition, we introduce serial attention module (SEA) to emphasis the most abnormal eye movement behaviors to reduce personal bias for a more robust result. According to our experiments, the DISCN achieves consistent validity in classifying the eye movements between the AD patients and normal controls.

Depth-induced Saliency Comparison Network for Diagnosis of Alzheimer's Disease via Jointly Analysis of Visual Stimuli and Eye Movements

TL;DR

An Depth-induced saliency comparison network for eye movement analysis, which may be used for diagnosis the Alzheimers disease, and introduces serial attention module (SEA) to emphasis the most abnormal eye movement behaviors to reduce personal bias for a more robust result.

Abstract

Early diagnosis of Alzheimer's Disease (AD) is very important for following medical treatments, and eye movements under special visual stimuli may serve as a potential non-invasive biomarker for detecting cognitive abnormalities of AD patients. In this paper, we propose an Depth-induced saliency comparison network (DISCN) for eye movement analysis, which may be used for diagnosis the Alzheimers disease. In DISCN, a salient attention module fuses normal eye movements with RGB and depth maps of visual stimuli using hierarchical salient attention (SAA) to evaluate comprehensive saliency maps, which contain information from both visual stimuli and normal eye movement behaviors. In addition, we introduce serial attention module (SEA) to emphasis the most abnormal eye movement behaviors to reduce personal bias for a more robust result. According to our experiments, the DISCN achieves consistent validity in classifying the eye movements between the AD patients and normal controls.
Paper Structure (26 sections, 12 equations, 9 figures, 5 tables)

This paper contains 26 sections, 12 equations, 9 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. AD diagnosing methods based on eye movements
  4. Serial attention neural networks
  5. Method
  6. Notations and preliminaries
  7. Depth-included salient attention module for preliminary saliency map evaluation of visual stimuli
  8. Salient attention module for integrating visual stimuli with human visual attention
  9. Saliency-aware serial attention module for feature fusion
  10. Experiments
  11. Participants
  12. Eye movements collection
  13. Stereo visual stimuli designs
  14. Noninvasive eye tracker
  15. Heatmaps of visual attention
  16. ...and 11 more sections

Figures (9)

  • Figure 1: The overall process of the proposed approach for diagnosing AD with visual salience evaluation and deep learning.
  • Figure 2: The overall structure of proposed DISCN with two parts: an integration module for fusing heatmaps and RGB-D visual stimuli, and a serial attention module for combining temporal visual saliency features.
  • Figure 6: The stereo image stimuli of diverse styles presented to the subjects.
  • Figure 7: The process of eye movements collection and heatmaps generation.
  • Figure 8: Several heatmaps that contain human visual attention information and the corresponding visual stimuli.
  • ...and 4 more figures