Identification of Anonymous MRI Research Participants with Face-Recognition Software

With the use of publicly available software, reconstructed facial images from deidentified cranial MRI scans were matched to photographs of individual study participants 83% of the time as the first choice from a panel of photographs. This raises the possibility of identifying anonymous research par...

Full description

Saved in:
Bibliographic Details
Published inThe New England journal of medicine Vol. 381; no. 17; pp. 1684 - 1686
Main Authors Schwarz, Christopher G, Kremers, Walter K, Therneau, Terry M, Sharp, Richard R, Gunter, Jeffrey L, Vemuri, Prashanthi, Arani, Arvin, Spychalla, Anthony J, Kantarci, Kejal, Knopman, David S, Petersen, Ronald C, Jack, Clifford R
Format Journal Article
LanguageEnglish
Published United States Massachusetts Medical Society 24.10.2019
Subjects
Automation
Computer programs
Facial Recognition
Humans
Magnetic Resonance Imaging
Metadata
NMR
Nuclear magnetic resonance
Pattern recognition
Pattern Recognition, Automated
Privacy
Research Subjects
Software
Online AccessGet full text

Cover

More Information
Summary:With the use of publicly available software, reconstructed facial images from deidentified cranial MRI scans were matched to photographs of individual study participants 83% of the time as the first choice from a panel of photographs. This raises the possibility of identifying anonymous research participants.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Correspondence-2
content type line 14
ObjectType-Letter to the Editor-1
ObjectType-Article-2
ObjectType-Correspondence-1
content type line 23
ISSN:0028-4793
1533-4406
1533-4406
DOI:10.1056/NEJMc1908881