Individual identification based on brain function has gained traction in literature. Investigating individual differences in brain function can provide additional insights into the brain. In this work, we introduce a recurrent neural network-based model for identifying individuals based on only a short segment of resting-state functional magnetic resonance imaging data. In addition, we demonstrate how the global signal and differences in atlases affect individual identifiability. Furthermore, we investigate neural network features that exhibit the uniqueness of each individual. The results indicate that our model is able to identify individuals based on neural features and provides additional information regarding brain dynamics.
Get full access to this article
View all access options for this article.
References
1.
AllenEA, DamarajuE, PlisSM, ErhardtEB, EicheleT, CalhounVD. 2014. Tracking whole-brain connectivity dynamics in the resting state. Cereb Cortex, 24:663–676.
2.
AmodeiD, AnubhaiR, BattenbergE, CaseC, CasperJ, CatanzaroB, et al.2015. Deep speech 2: end-to-end speech recognition in English and Mandarin. arXiv Preprint arXiv:1512.02595.
3.
BurgessGC, KandalaS, NolanD, LaumannTO, PowerJD, AdeyemoB, et al.2016. Evaluation of denoising strategies to address motion-correlated artifacts in resting-state functional magnetic resonance imaging data from the Human Connectome Project. Brain Connect, 6:669–680.
4.
ChenS, LangleyJ, ChenX, HuX. 2016. Spatiotemporal modeling of brain dynamics using resting-state functional magnetic resonance imaging with Gaussian Hidden Markov model. Brain Connect, 6:326–334.
5.
CholletF. Keras. 2015. https://github.com/fchollet/keras Last accessed February10, 2017.
6.
ChungJ, GulcehreC, ChoK, BengioY. 2014. Empirical evaluation of gated recurrent neural networks on sequence modelings. arXiv Preprint arXiv:1412.3555.
7.
FinnES, ShenXL, ScheinostD, RosenbergMD, HuangJ, ChunMM, et al.2015. Functional connectome fingerprinting: identifying individuals using patterns of brain connectivity. Nat Neurosci, 18:1664–1671.
8.
GlasserMF, CoalsonTS, RobinsonEC, HackerCD, HarwellJ, YacoubE, et al.2016. A multi-modal parcellation of human cerebral cortex. Nature, 536:171–178.
9.
GlasserMF, SotiropoulosSN, WilsonJA, CoalsonTS, FischlB, AnderssonJL, et al.2013. The minimal preprocessing pipelines for the Human Connectome Project. Neuroimage, 80:105–124.
10.
GlorotX, BengioY. 2010. Understanding the Difficulty of Training Deep Feedforward Neural Networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Sardinia, Italy. pp. 249–256.
11.
GravesA. 2012. Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks. Guide to OCR for Arabic Scripts. London: Springer. p. 297.
12.
GriffantiL, Salimi-KhorshidiG, BeckmannCF, AuerbachEJ, DouaudG, SextonCE, et al.2014. ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging. Neuroimage, 95:232–247.
13.
GüçlüU, van GervenMA. 2017. Modeling the dynamics of human brain activity with recurrent neural networks. Front Comput Neurosci, 11:7.
14.
KingmaD, BaJ. 2014. Adam: a method for stochastic optimization. arXiv Preprint arXiv:1412.6980.
15.
LeeMH, SmyserCD, ShimonyJS. 2013. Resting-state fMRI: a review of methods and clinical applications. Am J Neuroradiol, 34:1866–1872.
16.
MaatenLvd, HintonG. 2008. Visualizing data using t-SNE. J Mach Learn Res, 9:2579–2605.
17.
MazumdarJ, HarleyRG. 2008. Recurrent neural networks trained with backpropagation through time algorithm to estimate nonlinear load harmonic currents. IEEE Trans Ind Electron, 55:3484–3491.
18.
MazziottaJC, TogaAW, EvansA, FoxP, LancasterJ. 1995. A probabilistic atlas of the human brain—theory and rationale for its development. Neuroimage, 2:89–101.
19.
MikolovT, KarafiatM, BurgetL, CernockyJ, KhudanpurS. 2010. Recurrent Neural Network Based Language Model. 11th Annual Conference of the International Speech Communication Association 2010 (Interspeech 2010). Makuhari, Chiba, Japan. 2010, volume 1–2, p. 1045.
20.
MohrPN, NagelIE. 2010. Variability in brain activity as an individual difference measure in neuroscience?. J Neurosci, 30:7755–7757.
21.
PowerJD, CohenAL, NelsonSM, WigGS, BarnesKA, ChurchJA, et al.2011. Functional network organization of the human brain. Neuron, 72:665–678.
22.
PowerJD, PlittM, LaumannTO, MartinA. 2017. Sources and implications of whole-brain fMRI signals in humans. Neuroimage, 146:609–625.
23.
RobinsonEC, JbabdiS, GlasserMF, AnderssonJ, BurgessGC, HarmsMP, et al.2014. MSM: a new flexible framework for multimodal surface matching. Neuroimage, 100:414–426.
24.
Salimi-KhorshidiG, DouaudG, BeckmannCF, GlasserMF, GriffantiL, SmithSM. 2014. Automatic denoising of functional MRI data: combining independent component analysis and hierarchical fusion of classifiers. Neuroimage, 90:449–468.
25.
SaxeAM, McClellandJL, GanguliS. 2013. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv Preprint arXiv:1312.6120.
26.
SiegelJS, MitraA, LaumannTO, SeitzmanBA, RaichleM, CorbettaM, SnyderAZ. 2016. Data quality influences observed links between functional connectivity and behavior. Cereb Cortex, 27:4492–4502.
27.
SrivastavaN, HintonG, KrizhevskyA, SutskeverI, SalakhutdinovR. 2014. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res, 15:1929–1958.
28.
TalairachJ, TournouxP. 1988. Co-Planar Stereotaxic Atlas of the Human Brain: 3-Dimensional Proportional System: An Approach to Cerebral Imaging. Stuttgart, Germany: Thieme Medical Publishers.
29.
Van EssenDC, SmithSM, BarchDM, BehrensTE, YacoubE, UgurbilK, WU-Minn HCP Consortium. 2013. The WU-Minn human connectome project: an overview. Neuroimage, 80:62–79.
30.
YeoBT, KrienenFM, SepulcreJ, SabuncuMR, LashkariD, HollinsheadM, et al.2011. The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J Neurophysiol, 106:1125–1165.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
