Discovering individual fingerprints in resting-state functional connectivity using deep neural networks

被引:1
作者
Lee, Juhyeon [1 ]
Lee, Jong-Hwan [1 ,2 ,3 ,4 ]
机构
[1] Korea Univ, Dept Brain & Cognit Engn, Seoul, South Korea
[2] Korea Univ, Interdisciplinary Program Precis Publ Hlth, Seoul, South Korea
[3] MIT, McGovern Inst Brain Res, Boston, MA USA
[4] Korea Univ, Dept Brain & Cognit Engn, Anam Ro 145, Seoul 02841, South Korea
关键词
Deep neural networks; Fingerprints; Functional connectivity; Functional magnetic resonance imaging; Human Connectome Project; Individual identification; Transfer Learning; IDENTIFYING INDIVIDUALS; BRAIN NETWORKS; DATA REVEALS; FMRI; CONNECTOME; CORTEX; WINDOW; CLASSIFICATION; PATTERNS;
D O I
10.1002/hbm.26561
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Non-negligible idiosyncrasy due to interindividual differences is an ongoing issue in resting-state functional MRI (rfMRI) analysis. We show that a deep neural network (DNN) can be employed for individual identification by learning important features from the time-varying functional connectivity (FC) of rfMRI in the Human Connectome Project. We employed the trained DNN to identify individuals from an independent dataset acquired at our institution. The results revealed that the DNN could successfully identify 300 individuals with an error rate of 2.9% using 15 s time-window and 870 individuals with an error rate of 6.7%. A trained DNN with nonlinear hidden layers led to the proposal of the "fingerprint of FC" (fpFC) as representative edges of individual FC. The fpFCs for individuals exhibited commonly important and individual-specific edges across time-window lengths (from 5 min to 15 s). Furthermore, the utility of our model for another group of subjects was validated, supporting the feasibility of our technique in the context of transfer learning. In conclusion, our study offers an insight into the discovery of the intrinsic mode of the human brain using whole-brain resting-state FC and DNNs. By using deep neural networks (DNNs), reliable and robust fingerprints of resting-state functional connectivity for individuals were found. The trained DNN showed its efficacy in the identification of individuals from an independent dataset via transfer learning.image
引用
收藏
页数:20
相关论文
共 102 条
[1]   Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning [J].
Abrol, Anees ;
Fu, Zening ;
Salman, Mustafa ;
Silva, Rogers ;
Du, Yuhui ;
Plis, Sergey ;
Calhoun, Vince .
NATURE COMMUNICATIONS, 2021, 12 (01)
[2]   An open resource for transdiagnostic research in pediatric mental health and learning disorders [J].
Alexander, Lindsay M. ;
Escalera, Jasmine ;
Ai, Lei ;
Andreotti, Charissa ;
Febre, Karina ;
Mangone, Alexander ;
Vega-Potler, Natan ;
Langer, Nicolas ;
Alexander, Alexis ;
Kovacs, Meagan ;
Litke, Shannon ;
O'Hagan, Bridget ;
Andersen, Jennifer ;
Bronstein, Batya ;
Bui, Anastasia ;
Bushey, Marijayne ;
Butler, Henry ;
Castagna, Victoria ;
Camacho, Nicolas ;
Chan, Elisha ;
Citera, Danielle ;
Clucas, Jon ;
Cohen, Samantha ;
Dufek, Sarah ;
Eaves, Megan ;
Fradera, Brian ;
Gardner, Judith ;
Grant-Villegas, Natalie ;
Green, Gabriella ;
Gregory, Camille ;
Hart, Emily ;
Harris, Shana ;
Horton, Megan ;
Kahn, Danielle ;
Kabotyanski, Katherine ;
Karmel, Bernard ;
Kelly, Simon P. ;
Kleinman, Kayla ;
Koo, Bonhwang ;
Kramer, Eliza ;
Lennon, Elizabeth ;
Lord, Catherine ;
Mantello, Ginny ;
Margolis, Amy ;
Merikangas, Kathleen R. ;
Milham, Judith ;
Minniti, Giuseppe ;
Neuhaus, Rebecca ;
Levine, Alexandra ;
Osman, Yael .
SCIENTIFIC DATA, 2017, 4
[3]   Tracking Whole-Brain Connectivity Dynamics in the Resting State [J].
Allen, Elena A. ;
Damaraju, Eswar ;
Plis, Sergey M. ;
Erhardt, Erik B. ;
Eichele, Tom ;
Calhoun, Vince D. .
CEREBRAL CORTEX, 2014, 24 (03) :663-676
[4]   The quest for identifiability in human functional connectomes [J].
Amico, Enrico ;
Goni, Joaquin .
SCIENTIFIC REPORTS, 2018, 8
[5]   The Brain's Default Network and Its Adaptive Role in Internal Mentation [J].
Andrews-Hanna, Jessica R. .
NEUROSCIENTIST, 2012, 18 (03) :251-270
[6]  
[Anonymous], 2009, Functional Magnetic Resonance Imaging
[7]   What Size Net Gives Valid Generalization? [J].
Baum, Eric B. ;
Haussler, David .
NEURAL COMPUTATION, 1989, 1 (01) :151-160
[8]   Representation Learning: A Review and New Perspectives [J].
Bengio, Yoshua ;
Courville, Aaron ;
Vincent, Pascal .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1798-1828
[9]   The relationship between spatial configuration and functional connectivity of brain regions [J].
Bijsterbosch, Janine Diane ;
Woolrich, Mark W. ;
Glasser, Matthew F. ;
Robinson, Emma C. ;
Beckmann, Christian F. ;
Van Essen, David C. ;
Harrison, Samuel J. ;
Smith, Stephen M. .
ELIFE, 2018, 7
[10]   FUNCTIONAL CONNECTIVITY IN THE MOTOR CORTEX OF RESTING HUMAN BRAIN USING ECHO-PLANAR MRI [J].
BISWAL, B ;
YETKIN, FZ ;
HAUGHTON, VM ;
HYDE, JS .
MAGNETIC RESONANCE IN MEDICINE, 1995, 34 (04) :537-541