Resources

This dataset was a collected using an eye tracking system while a radiologist interpreted and read 1,083 public CXR images. The dataset contains the following aligned modalities: image, transcribed report text, dictation audio and eye gaze data.

RadQA is an electronic health record question answering dataset containing clinical questions that can be answered using the Findings and Impressions sections of radiology reports

RadGraph is a dataset of entities and relations in full-text chest X-ray radiology reports, which are obtained using a novel information extraction (IE) schema to capture clinically relevant information in a radiology report.

The MS-CXR-T is a multimodal benchmark that enhances the MIMIC-CXR v2 dataset by including expert-verified annotations. Its goal is to evaluate biomedical visual-language processing models in terms of temporal semantics extracted from image and text.

Chest radiographs in DICOM format with associated free-text reports.

CXR-PRO is an adaptation of the MIMIC-CXR dataset (consisting of chest radiographs and their associated free-text radiology reports) with references to non-existent priors removed.

Chest x-rays in JPG format with structured labels derived from the associated radiology report.

CXLSeg dataset: Chest X-ray with Lung Segmentation, a comparatively large dataset of segmented Chest X-ray radiographs based on the MIMIC-CXR dataset. This contains segmentation results of 243,324 frontal view images and corresponding masks.

Deidentified free-text clinical notes for patients in the MIMIC-IV Clinical Database.

This dataset contains 3032 cases of eye-tracking data collected while five radiologists dictated reports for frontal chest x-rays, synchronized timestamped dictation transcription, and manual labels for validation of localization of abnormalities.