Application requiredXRAY

LERA: Lower Extremity Radiographs

Name: LERA: Lower Extremity Radiographs
License: Access requires registration and acceptance of the Stanford University School of Medicine LERA Research Use Agreement. Use is permitted without charge only for personal, non-commercial research. Redistribution, commercial use and creation of derivative works are prohibited.

LERA is a lower-extremity radiography dataset containing foot, ankle, knee and hip images with patient-level binary labels indicating whether the examination was normal or abnormal.

Licence and access

Access requires registration and acceptance of the Stanford University School of Medicine LERA Research Use Agreement. Use is permitted without charge only for personal, non-commercial research. Redistribution, commercial use and creation of derivative works are prohibited.

application requiredcommercial use restrictedredistribution restricted

Visit official source ↗last verified 2026-09-03

Access status: Access requires an application, data-use agreement, registration workflow or institutional approval.

Coverage

kneehipotherclassificationin vivo

subjects

182

images

1,297

formats

CSV

origin

not verified

Citation

Varma M, Lu M, Gardner R, et al. Automated abnormality detection in lower extremity radiographs using deep learning. Nature Machine Intelligence. 2019;1:578-583. DOI: 10.1038/s42256-019-0126-0. Dataset DOI: 10.71718/aqrb-et67.

Notes

The dataset contains 1,297 radiographs from 182 patients. The current Redivis interface lists 1,298 files, consistent with 1,297 image files and one CSV label file. Foot and ankle are not supported by the current anatomy enum, so they are represented as other. The exact image file format could not be verified from the public pages and is therefore not included in format.

This record is a pointer. Licence and access terms are recorded as they stood on the verification date above; what binds you is the dataset's own licence text. Confirm at the source before use.