Eye-Tracking, Mouse Tracking, Stimulus Tracking,and Decision-Making Datasets in Digital Pathology

TL;DR

This paper introduces PathoGaze1.0, a comprehensive behavioral dataset capturing eye-tracking, mouse interactions, and decision data from pathologists diagnosing cancer in gigapixel images, aiming to improve understanding and training.

Contribution

The paper presents a novel, ecologically valid dataset of diagnostic behavior in digital pathology, filling a gap in behavioral data for understanding diagnostic errors and supporting AI training.

Findings

Large dataset with 18.69 hours of data from 19 pathologists

Extensive behavioral data including eye movements and mouse interactions

Dataset available for research and AI development

Abstract

Interpretation of giga-pixel whole-slide images (WSIs) is an important but difficult task for pathologists. Their diagnostic accuracy is estimated to average around 70%. Adding a second pathologist does not substantially improve decision consistency. The field lacks adequate behavioral data to explain diagnostic errors and inconsistencies. To fill in this gap, we present PathoGaze1.0, a comprehensive behavioral dataset capturing the dynamic visual search and decision-making processes of the full diagnostic workflow during cancer diagnosis. The dataset comprises 18.69 hours of eye-tracking, mouse interaction, stimulus tracking, viewport navigation, and diagnostic decision data (EMSVD) collected from 19 pathologists interpreting 397 WSIs. The data collection process emphasizes ecological validity through an application-grounded testbed, called PTAH. In total, we recorded 171,909 fixations, 263,320 saccades, and 1,867,362 mouse interaction events. In addition, such data could also be used to improve the training of both pathologists and AI systems that might support human experts. All experiments were preregistered at https://osf.io/hj9a7, and the complete dataset along with analysis code is available at https://go.osu.edu/pathogaze.