The EMory BrEast imaging Dataset (EMBED): A Racially Diverse, Granular Dataset of 3.4 Million Screening and Diagnostic Mammographic Images

Authors

Jiwoong J. Jeong, Arizona State University
Brianna L. Vey, Emory University
Ananth Bhimireddy, Emory University
Thomas Kim, Georgia Institute of Technology
Thiago Santos, Emory University
Ramon Correa, Arizona State University
Raman Dutt, Emory University
Marina Mosunjac, Emory University
Gabriela Oprea-Ilies, Emory University
Geoffrey Smith, Emory University
Minjae Woo, Kennesaw State University
Christopher R. McAdams, Emory University
Mary S. Newell, Emory University
Imon Banerjee, Arizona State University
Judy Gichoya, Emory University
Hari Trivedi, Emory University

Department

School of Data Science and Analytics

Document Type

Article

Publication Date

1-1-2023

Abstract

The EMory BrEast imaging Dataset (EMBED) contains two-dimensional and digital breast tomosynthesis screening and diagnostic mammograms with lesion-level annotations and pathologic information in racially diverse patients.

Journal Title

Radiology: Artificial Intelligence

Journal ISSN

2638-6100

Volume

5

Issue

1

Digital Object Identifier (DOI)

10.1148/ryai.220047