Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study

André Luís; Chihcheng Hsieh; Isabel Blanco Nobre; Sandra Costa Sousa; Anderson Maciel; Catarina Moreira; Joaquim Jorge

Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study

Computer Vision and Pattern Recognition 2023-02-07 v1 Artificial Intelligence Human-Computer Interaction

Authors: André Luís , Chihcheng Hsieh , Isabel Blanco Nobre , Sandra Costa Sousa , Anderson Maciel , Catarina Moreira , Joaquim Jorge

View on arXiv ↗ PDF ↗

Abstract

This paper proposes a novel multimodal DL architecture incorporating medical images and eye-tracking data for abnormality detection in chest x-rays. Our results show that applying eye gaze data directly into DL architectures does not show superior predictive performance in abnormality detection chest X-rays. These results support other works in the literature and suggest that human-generated data, such as eye gaze, needs a more thorough investigation before being applied to DL architectures.

Keywords

gaze estimation

Cite

@article{arxiv.2302.02940,
  title  = {Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study},
  author = {André Luís and Chihcheng Hsieh and Isabel Blanco Nobre and Sandra Costa Sousa and Anderson Maciel and Catarina Moreira and Joaquim Jorge},
  journal= {arXiv preprint arXiv:2302.02940},
  year   = {2023}
}

Comments

A version of this paper has been accepted for presentation at the 2nd XR Health workshop - XR Technologies for Healthcare and Wellbeing https://ieeevr.org/2023/contribute/workshoppapers/#XRHealth

Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study

Abstract

Keywords

Cite

Comments

Related papers