1,715 Hits in 5.5 sec

Deep Hypergraph U-Net for Brain Graph Embedding and Classification [article]

Mert Lostar, Islem Rekik
2020 arXiv   pre-print
Graph embedding methods which map data samples (e.g., brain networks) into a low dimensional space have been widely used to explore the relationship between samples for classification or prediction tasks  ...  In this paper, inspired by the nascent field of geometric deep learning, we propose Hypergraph U-Net (HUNet), a novel data embedding framework leveraging the hypergraph structure to learn low-dimensional  ...  To this aim, investigating a population of brain connectomes using graphbased embedding techniques has become popular, given their capacity to model the one-to-one relationship between data samples (i.e  ... 
arXiv:2008.13118v1 fatcat:xkyg5ddmzbg6fktxwqcmqfttoi

Coalescent embedding in the hyperbolic space unsupervisedly discloses the hidden geometry of the brain [article]

Alberto Cacciola, Alessandro Muscoloni, Vaibhav Narula, Alessandro Calamuneri, Salvatore Nigro, Emeran A. Mayer, Jennifer S. Labus, Giuseppe Anastasi, Aldo Quattrone, Angelo Quartarone, Demetrio Milardi, Carlo Vittorio Cannistraci
2017 arXiv   pre-print
The human brain structural connectome represents the perfect benchmark to test algorithms aimed to solve this problem.  ...  Coalescent embedding was recently designed to map a complex network in the hyperbolic space, inferring the node angular coordinates.  ...  The tractographic algorithms (FACT = Fiber assignment by continuous tracking; GQI = Generalized Q-sampling imaging; CSD = Constrained Spherical Deconvolution) used to create the connectomes and their weights  ... 
arXiv:1705.04192v1 fatcat:atctczqgcvhsnn5ljdlvck5dwy

Joint Functional Brain Network Atlas Estimation and Feature Selection for Neurological Disorder Diagnosis With Application to Autism

Islem Mhiri, Islem Rekik
2019 Medical Image Analysis  
Essentially, we first learn the pairwise similarities between connectomes in the population to map them into different subspaces.  ...  Next, we non-linearly diffuse and fuse connectomes living in each subspace, respectively.  ...  SIMLR efficiently learns sample-to-sample similarity measure that best fits the structure of the data by combining multiple kernels.  ... 
doi:10.1016/ pmid:31739282 fatcat:dlwejthh6rfx5hsy3ilhmuis6q

Mapping structure to function and behavior with individual-level connectome embedding [article]

Gidon Levakov, Joshua Faskowitz, Galia Avidan, Olaf Sporns
2021 bioRxiv   pre-print
Our novel approach allows mapping individual differences in the connectome through structure to function and behavior.  ...  Furthermore, age-related differences in this structure-function mapping are preserved and enhanced.  ...  The goal is to remove variability related to the stochasticity in the CE fitting process and the different latent spaces, and preserve variability related to variations in the underlining network topology  ... 
doi:10.1101/2021.01.13.426513 fatcat:a3yryjwlkfezjihbddu3cfbkim

Auto-encoding brain networks with applications to analyzing large-scale brain imaging datasets [article]

Meimei Liu, Zhengwu Zhang, David B. Dunson
2021 arXiv   pre-print
structural connectomes and human traits.  ...  There has been huge interest in studying human brain connectomes inferred from different imaging modalities and exploring their relationship with human traits, such as cognition.  ...  In addition, when the focus is on relating brain structure to human traits or in predicting traits based on brain structure or vice versa, the non-identifiability issue does not present a problem.  ... 
arXiv:1911.02728v3 fatcat:s7blnejq3zdlzchkjhqbrim4gi

BRAINtrinsic: A Virtual Reality-Compatible Tool for Exploring Intrinsic Topologies of the Human Brain Connectome [chapter]

Giorgio Conte, Allen Q. Ye, Angus G. Forbes, Olusola Ajilore, Alex Leow
2015 Lecture Notes in Computer Science  
Thanks to advances in non-invasive technologies such as functional Magnetic Resonance Imaging (fMRI) and Diffusion Tensor Imaging (DTI), highly-detailed maps of brain structure and function can now be  ...  In this paper we present BRAINtrinsic, an innovative web-based 3D visual analytics tool that allows users to intuitively and iteratively interact with connectome data.  ...  meaningful patterns of structure or function may be much easier to appreciate in a topological space.  ... 
doi:10.1007/978-3-319-23344-4_7 fatcat:hlk5sassmbgirm3m3r6v4wf3ma

Optimized Diffusion Imaging for Brain Structural Connectome Analysis [article]

William Consagra, Arun Venkataraman, Zhengwu Zhang
2021 arXiv   pre-print
To more accurately estimate the structural connectome, dense samples in q-space are often acquired, potentially resulting in long scanning times and logistical challenges.  ...  For a new subject to be scanned, the priors are mapped into the subject-specific coordinate and used to help select the best q-space samples.  ...  In Section IV, we show real data examples for several tasks related to dMRI processing and structural connectome analyses. Conclusions and future directions are presented in Section V. II.  ... 
arXiv:2102.12526v2 fatcat:u2kwlmja4javhehgsczy63763u

High-order Connectomic Manifold Learning for Autistic Brain State Identification [chapter]

Mayssa Soussia, Islem Rekik
2017 Lecture Notes in Computer Science  
However, 'shape connections' between brain regions were rarely investigated in ASD -e.g., how morphological attributes of a specific brain region (e.g., sulcal depth) change in relation to morphological  ...  For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectomic features, to  ...  For visualization, the same algorithm is used to create an embedding of S in a 2D space.  ... 
doi:10.1007/978-3-319-67159-8_7 fatcat:cjpcvux3l5bjvpg5hqgonjkcvy

Mapping population-based structural connectomes

Zhengwu Zhang, Maxime Descoteaux, Jingwen Zhang, Gabriel Girard, Maxime Chamberland, David Dunson, Anuj Srivastava, Hongtu Zhu
2018 NeuroImage  
We apply the PSC to Human Connectome Project data to illustrate its application in characterizing normal variations and heritability of structural connectomes in healthy subjects.  ...  This article develops a population-based structural connectome (PSC) mapping framework to address these challenges.  ...  Data were provided in part by the Human Connectome Project, WU-Minn Consortium (Principal Investigators: David Van Essen and Kamil Ugurbil; 1U54MH091657).  ... 
doi:10.1016/j.neuroimage.2017.12.064 pmid:29355769 pmcid:PMC5910206 fatcat:zm3436yv7newzbv2pqyq63vwae

Automatic discovery of cell types and microcircuitry from neural connectomics [article]

Eric Jonas, Konrad Kording
2014 arXiv   pre-print
Here we developed a nonparametric Bayesian technique that identifies neuron types and microcircuitry patterns in connectomics data.  ...  It has long been assumed that discovering neuron types and their relation to microcircuitry is crucial to understanding neural function.  ...  Distinct cell types differ in morphology, connectivity, transcriptomics, relation to behavior or stimuli and many other ways.  ... 
arXiv:1407.4137v1 fatcat:65mdgksz6bhwxba5efwf6nshmu

Structural determinants of dynamic fluctuations between segregation and integration on the human connectome [article]

Makoto Fukushima, Olaf Sporns
2020 biorxiv/medrxiv   pre-print
To tackle this problem, we aim to identify specific network features of the connectome (the complete set of structural brain connections) that are responsible for the emergence of dynamic fluctuations  ...  The contributions of network features to the dynamic fluctuations were examined by constructing randomly rewired surrogate connectome data in which network features of interest were selectively preserved  ...  A dvances in measuring techniques of white matter structural connectivity allow obtaining whole-brain network maps, referred to as the connectome 1 .  ... 
doi:10.1101/2020.01.20.912030 fatcat:zsyrynl6zvf43iqsepr43wjc74

Automatic discovery of cell types and microcircuitry from neural connectomics

Eric Jonas, Konrad Kording
2015 eLife  
Here we developed a non-parametric Bayesian technique that identifies neuron types and microcircuitry patterns in connectomics data.  ...  It has long been assumed that discovering neuron types and their relation to microcircuitry is crucial to understanding neural function.  ...  The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication. Additional information  ... 
doi:10.7554/elife.04250 pmid:25928186 pmcid:PMC4415525 fatcat:k6jjbpipzbastdvcicw2iwsi5u

The Case for Optimized Edge-Centric Tractography at Scale

Joseph Y. Moon, Pratik Mukherjee, Ravi K. Madduri, Amy J. Markowitz, Lanya T. Cai, Eva M. Palacios, Geoffrey T. Manley, Peer-Timo Bremer
2022 Frontiers in Neuroinformatics  
The anatomic validity of structural connectomes remains a significant uncertainty in neuroimaging.  ...  This finding even holds true in an entirely different tractography algorithm using MRTrix.  ...  The tractability of structural connectomes to matrix analysis has resulted in a variety of proposed techniques to assess their reliability (Imms et al., 2019) .  ... 
doi:10.3389/fninf.2022.752471 pmid:35651721 pmcid:PMC9148990 fatcat:zz5b6nrkmbhznejokafcsokhge

Learning Weighted Submanifolds with Variational Autoencoders and Riemannian Variational Autoencoders [article]

Nina Miolane, Susan Holmes
2019 arXiv   pre-print
Traditional techniques, like principal component analysis, are ill-adapted to tackle non-Euclidean spaces and may fail to achieve a lower-dimensional representation of the data - thus potentially pointing  ...  In cognitive neuroscience, for instance, brain connectomes base the analysis of coactivation patterns between different brain regions on the analysis of the correlations of their functional Magnetic Resonance  ...  The aforementioned techniques are indeed restricted in that: either (i) they do not leverage any geometric knowledge as to the known manifold to which the data, such as the connectomes, belong; or (ii)  ... 
arXiv:1911.08147v1 fatcat:exlm3gxmrfd6th3euciwtkfpem

BrainSpace: a toolbox for the analysis of macroscale gradients in neuroimaging and connectomics datasets [article]

Reinder Vos de Wael, Oualid Benkarim, Casey Paquola, Sara Lariviere, Jessica Royer, Shahin Tavakol, Ting Xu, Seok-Jun Hong, Sofie Louise Valk, Bratislav Misic, Michael Milham, Daniel S Margulies (+2 others)
2019 biorxiv/medrxiv   pre-print
), and (iii) their visualization (in embedding or cortical space).  ...  More generally, its macroscale perspective on brain organization offers novel possibilities to investigate the complex relationships between brain structure, function, and cognition in a quantified manner  ...  Joint embedding is, thus, a technique to identify correspondence and to map from one space to another, and conceptually related to widely used multivariate associative techniques such as canonical correlation  ... 
doi:10.1101/761460 fatcat:enhppnif6vd3xkhlw3xzwn2oo4
« Previous Showing results 1 — 15 out of 1,715 results