Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Development

TL;DR

This paper presents a comprehensive Chest X-Ray dataset combining images, reports, audio, and eye-tracking data to enhance AI research in explainability, multimodal learning, and disease localization.

Contribution

The creation of a multimodal CXR dataset with eye-tracking, report dictation, and aligned images, enabling new research in explainable AI and multimodal analysis.

Findings

Eye gaze data improves disease localization accuracy.

Deep learning models benefit from multimodal inputs.

Potential for advancing explainable radiology AI.

Abstract

We developed a rich dataset of Chest X-Ray (CXR) images to assist investigators in artificial intelligence. The data were collected using an eye tracking system while a radiologist reviewed and reported on 1,083 CXR images. The dataset contains the following aligned data: CXR image, transcribed radiology report text, radiologist's dictation audio and eye gaze coordinates data. We hope this dataset can contribute to various areas of research particularly towards explainable and multimodal deep learning / machine learning methods. Furthermore, investigators in disease classification and localization, automated radiology report generation, and human-machine interaction can benefit from these data. We report deep learning experiments that utilize the attention maps produced by eye gaze dataset to show the potential utility of this data.