REFLACX, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays
This dataset addresses the need for scalable supervision in medical imaging for radiologists and AI researchers, though it is incremental as it builds on existing methods for data collection.
The authors tackled the problem of limited datasets for localizing abnormalities in chest x-rays by creating REFLACX, a dataset with 3,032 sets of eye-tracking data and report transcriptions for 2,616 chest x-rays, collected from five radiologists to provide implicit localization data.
Deep learning has shown recent success in classifying anomalies in chest x-rays, but datasets are still small compared to natural image datasets. Supervision of abnormality localization has been shown to improve trained models, partially compensating for dataset sizes. However, explicitly labeling these anomalies requires an expert and is very time-consuming. We propose a potentially scalable method for collecting implicit localization data using an eye tracker to capture gaze locations and a microphone to capture a dictation of a report, imitating the setup of a reading room. The resulting REFLACX (Reports and Eye-Tracking Data for Localization of Abnormalities in Chest X-rays) dataset was labeled across five radiologists and contains 3,032 synchronized sets of eye-tracking data and timestamped report transcriptions for 2,616 chest x-rays from the MIMIC-CXR dataset. We also provide auxiliary annotations, including bounding boxes around lungs and heart and validation labels consisting of ellipses localizing abnormalities and image-level labels. Furthermore, a small subset of the data contains readings from all radiologists, allowing for the calculation of inter-rater scores.