Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study
This work addresses the challenge of effectively using human-generated data like eye gaze in medical imaging AI, but it is incremental as it confirms prior findings.
The study investigated whether integrating eye-gaze data into deep learning architectures improves abnormality detection in chest X-rays, finding that it did not lead to superior predictive performance.
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.