ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports

TL;DR

ReXGradient-160K tackles generalization challenges in radiology AI by providing the largest publicly available multi-institution chest X-ray dataset with paired free-text reports. It aggregates 160,000 studies (273,004 images) from 109,487 patients across 3 U.S. health systems, split into training, validation, and public test sets, plus a private ReXrank test set for evaluation. The authors implement rigorous de-identification, standardized image preprocessing, and a four-section report structure extracted via GPT-4o, with validation to ensure completeness. By open-sourcing on HuggingFace, it enables robust benchmarking and cross-site generalization studies for automated radiology reporting and AI-assisted interpretation.

Abstract

We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. This dataset contains 160,000 chest X-ray studies with paired radiological reports from 109,487 unique patients across 3 U.S. health systems (79 medical sites). This comprehensive dataset includes multiple images per study and detailed radiology reports, making it particularly valuable for the development and evaluation of AI systems for medical imaging and automated report generation models. The dataset is divided into training (140,000 studies), validation (10,000 studies), and public test (10,000 studies) sets, with an additional private test set (10,000 studies) reserved for model evaluation on the ReXrank benchmark. By providing this extensive dataset, we aim to accelerate research in medical imaging AI and advance the state-of-the-art in automated radiological analysis. Our dataset will be open-sourced at https://huggingface.co/datasets/rajpurkarlab/ReXGradient-160K.