Structural connectome validation using pairwise classification

In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.

[1]  M. Chun,et al.  Functional connectome fingerprinting: Identifying individuals based on patterns of brain connectivity , 2015, Nature Neuroscience.

[2]  Max A. Viergever,et al.  Recursive calibration of the fiber response function for spherical deconvolution of diffusion MRI data , 2014, NeuroImage.

[3]  Xi-Nian Zuo,et al.  Reliable intrinsic connectivity networks: Test–retest evaluation using ICA and dual regression approach , 2010, NeuroImage.

[4]  Barnabás Póczos,et al.  Quantifying Differences and Similarities in Whole-Brain White Matter Architecture Using Local Connectome Fingerprints , 2016, bioRxiv.

[5]  Bruce Fischl,et al.  FreeSurfer , 2012, NeuroImage.

[6]  Vince D. Calhoun,et al.  Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls , 2017, NeuroImage.

[7]  Danielle S. Bassett,et al.  Conserved and variable architecture of human white matter connectivity , 2011, NeuroImage.

[8]  Chris Rorden,et al.  Reproducibility of the Structural Brain Connectome Derived from Diffusion Tensor Imaging , 2015, PloS one.

[9]  Martijn P. van den Heuvel,et al.  The parcellation-based connectome: Limitations and extensions , 2013, NeuroImage.

[10]  Anders M. Dale,et al.  An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest , 2006, NeuroImage.

[11]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[12]  Yong He,et al.  Test-retest reliability of white matter structural brain networks: a multiband diffusion MRI study , 2015, Front. Hum. Neurosci..

[13]  Chad J. Donahue,et al.  Using Diffusion Tractography to Predict Cortical Connection Strength and Distance: A Quantitative Comparison with Tracers in the Monkey , 2016, The Journal of Neuroscience.

[14]  Renaud Lopes,et al.  Intra-subject reliability of the high-resolution whole-brain structural connectome , 2014, NeuroImage.

[15]  Cassandra D. Leonardo,et al.  Comparison of nine tractography algorithms for detecting abnormal structural brain networks in Alzheimer’s disease , 2015, Front. Aging Neurosci..

[16]  P. Thiran,et al.  Mapping Human Whole-Brain Structural Networks with Diffusion MRI , 2007, PloS one.

[17]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[18]  Maxime Descoteaux,et al.  Dipy, a library for the analysis of diffusion MRI data , 2014, Front. Neuroinform..

[19]  P. Vargha,et al.  A critical discussion of intraclass correlation coefficients. , 1997, Statistics in medicine.

[20]  Timothy P. L. Roberts,et al.  Test-Retest Reliability of Computational Network Measurements Derived from the Structural Connectome of the Human Brain , 2013, Brain Connect..

[21]  Maxime Descoteaux,et al.  Non Local Spatial and Angular Matching : Enabling higher spatial resolution diffusion MRI datasets through adaptive denoising , 2016, Medical Image Anal..