Skip to content Skip to navigation

Shared Datasets

CheXpert is a dataset consisting of 224,316 chest radiographs of 65,240 patients who underwent a radiographic examination from Stanford University Medical Center between October 2002 and July 2017, in both inpatient and outpatient centers. Included are their associated radiology reports.
EchoNet-Dynamic is a dataset of over 10k echocardiogram, or cardiac ultrasound, videos from unique patients at Stanford University Medical Center. Each apical-4-chamber video is accompanied by an estimated ejection fraction, end-systolic volume, end-diastolic volume, and tracings of the left ventricle performed by an advanced cardiac sonographer and reviewed by an imaging cardiologist.
In this retrospective, HIPAA-compliant, IRB-approved study, we collected data from 182 patients who underwent a radiographic examination at the Stanford University Medical Center between 2003 and 2014. The dataset consists of images of the foot, knee, ankle, or hip associated with each patient.
The MRNet dataset consists of 1,370 knee MRI exams performed at Stanford University Medical Center. The dataset contains 1,104 (80.6%) abnormal exams, with 319 (23.3%) ACL tears and 508 (37.1%) meniscal tears; labels were obtained through manual extraction from clinical reports.
MURA (musculoskeletal radiographs) is a large dataset of bone X-rays from the Stanford University Medical Center.
From the RSNA AI Challenge 2017, a dataset of bone age x-ray's from Stanford University, the University of Colorado and the University of California - Los Angeles.
From the RSNA AI Challenge 2018, a dataset labeled chest x-rays from the the National Institutes of Health (NIH).
Four research institutions provided large volumes of de-identified CT studies that were assembled to create the RSNA AI 2019 challenge dataset: Stanford University, Thomas Jefferson University, Unity Health Toronto and Universidade Federal de São Paulo (UNIFESP), The American Society of Neuroradiology (ASNR) organized a cadre of more than 60 volunteers to label over 25,000 exams for the challenge dataset.