Identification of individual subjects on the basis of their brain anatomical features

We examined whether it is possible to identify individual subjects on the basis of brain anatomical features. For this, we analyzed a dataset comprising 191 subjects who were scanned three times over a period of two years. Based on FreeSurfer routines, we generated three datasets covering 148 anatom...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 8; no. 1; pp. 5611 - 9
Main Authors: Valizadeh, Seyed Abolfazl, Liem, Franziskus, Mérillat, Susan, Hänggi, Jürgen, Jäncke, Lutz
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 04.04.2018
Nature Publishing Group
Subjects:
631/378/116/1925
631/378/2649/2150
631/477/2811
Aged
Brain - anatomy & histology
Brain - diagnostic imaging
Cortex
Datasets
Discriminant analysis
Female
Humanities and Social Sciences
Humans
Identification
Image Processing, Computer-Assisted
Magnetic Resonance Imaging
Male
Middle Aged
multidisciplinary
Science
Science (multidisciplinary)
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We examined whether it is possible to identify individual subjects on the basis of brain anatomical features. For this, we analyzed a dataset comprising 191 subjects who were scanned three times over a period of two years. Based on FreeSurfer routines, we generated three datasets covering 148 anatomical regions (cortical thickness, area, volume). These three datasets were also combined to a dataset containing all of these three measures. In addition, we used a dataset comprising 11 composite anatomical measures for which we used larger brain regions (11LBR). These datasets were subjected to a linear discriminant analysis (LDA) and a weighted K-nearest neighbors approach (WKNN) to identify single subjects. For this, we randomly chose a data subset (training set) with which we calculated the individual identification. The obtained results were applied to the remaining sample (test data). In general, we obtained excellent identification results (reasonably good results were obtained for 11LBR using WKNN). Using different data manipulation techniques (adding white Gaussian noise to the test data and changing sample sizes) still revealed very good identification results, particularly for the LDA technique. Interestingly, using the small 11LBR dataset also revealed very good results indicating that the human brain is highly individual.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-018-23696-6