Emory Knee Radiograph (MRKR) Dataset

TL;DR

The Emory Knee Radiograph (MRKR) dataset is a large, diverse collection of knee images with detailed clinical data, aimed at advancing research in osteoarthritis and improving model development for minority populations.

Contribution

This paper introduces the MRKR dataset, a comprehensive and demographically diverse knee radiograph dataset with rich clinical and imaging metadata, filling gaps in existing resources.

Findings

Provides over 500,000 knee radiographs from diverse populations

Includes detailed clinical information like pain scores and diagnostic codes

Enhances research potential for osteoarthritis and minority health disparities

Abstract

The Emory Knee Radiograph (MRKR) dataset is a large, demographically diverse collection of 503,261 knee radiographs from 83,011 patients, 40% of which are African American. This dataset provides imaging data in DICOM format along with detailed clinical information, including patient-reported pain scores, diagnostic codes, and procedural codes, which are not commonly available in similar datasets. The MRKR dataset also features imaging metadata such as image laterality, view type, and presence of hardware, enhancing its value for research and model development. MRKR addresses significant gaps in existing datasets by offering a more representative sample for studying osteoarthritis and related outcomes, particularly among minority populations, thereby providing a valuable resource for clinicians and researchers.