Filters








51 Hits in 2.4 sec

Probabilistic tractography using Lasso bootstrap

Chuyang Ye, Jerry L. Prince
2017 Medical Image Analysis  
In this work, we propose a probabilistic tractography algorithm named Lasso bootstrap tractography (LBT) for the models that incorporate sparsity.  ...  Bootstrap provides a nonparametric approach to the estimation of FO uncertainties and residual bootstrap has been used for developing probabilistic tractography.  ...  Up to this point, however, probabilistic tractography based on bootstrapping the Lasso model has not been explored.  ... 
doi:10.1016/j.media.2016.08.013 pmid:27662597 pmcid:PMC5099091 fatcat:45ry6mxipfa2fkejnqopchfigy

INDIVIDUAL CLASSIFICATION OF ALZHEIMER'S DISEASE WITH DIFFUSION MAGNETIC RESONANCE IMAGING

Tijn M. Schouten, Marisa Koini, Frank de Vos, Stephan Seiler, Mark de Rooij, Anita Lechner, Reinhold Schmidt, Martijn van den Heuvel, Jeroen van der Grond, Serge A.R.B. Rombouts
2017 Alzheimer's & Dementia  
Third, we determined structural connectivity between Harvard Oxford atlas regions with probabilistic tractography, as well as graph measures based on these structural connectivity graphs.  ...  All measures combined with a sparse group lasso resulted in an AUC of 0.896. Overall, fractional anisotropy clustered into ICA components was the best performing measure.  ...  Boxplot of the sparse group lasso classification models from 10-fold times 10 repeated cross validation. The bars indicate the spread of the sum of the absolute beta values.  ... 
doi:10.1016/j.jalz.2017.06.2419 fatcat:4owo2ixbtrgmnfhverbcpwhyti

Bayesian Estimation of Conditional Independence Graphs Improves Functional Connectivity Estimates

Max Hinne, Ronald J. Janssen, Tom Heskes, Marcel A.J. van Gerven, Danielle S Bassett
2015 PLoS Computational Biology  
Finally, we demonstrate how our approach can be extended in several ways, for instance to achieve data fusion by informing the conditional independence graph with data from probabilistic tractography.  ...  In this paper, we propose a probabilistic generative model that allows us to estimate functional connectivity in terms of both partial correlations and a graph representing conditional independencies.  ...  Here, we use an existing model of structural connectivity based on probabilistic tractography [39, 40] , defined as follows.  ... 
doi:10.1371/journal.pcbi.1004534 pmid:26540089 pmcid:PMC4634993 fatcat:ywhz2keycnednl5xnd5sc33dny

NODDI and Tensor-Based Microstructural Indices as Predictors of Functional Connectivity

Fani Deligianni, David W. Carmichael, Gary H. Zhang, Chris A. Clark, Jonathan D. Clayden, Daniele Marinazzo
2016 PLoS ONE  
Here we exploit a statistical framework based on sparse Canonical Correlation Analysis (sCCA) and randomised Lasso to identify structural connections that are highly correlated with resting-state functional  ...  Subsequently, we ran probabilistic tractography, implemented in Trac-toR, for each dataset.  ...  These studies demonstrated that probabilistic tractography algorithms favour the shortest, simplest and straightest paths.  ... 
doi:10.1371/journal.pone.0153404 pmid:27078862 pmcid:PMC4831788 fatcat:vdfossnk2zgadmxxckpi4ecsie

The Severity of Sensorimotor Tracts Degeneration May Predict Motor Performance in Chronic Stroke Patients, While Brain Structural Network Dysfunction May Not

Loukas G. Astrakas, Shasha Li, Sabrina Elbach, A. Aria Tzika
2022 Frontiers in Neurology  
We compared fractional anisotropy (FA) and mean diffusivity (MD) in 60 CST segments using the probabilistic sensorimotor area tract template (SMATT).  ...  Least Absolute Shrinkage and Selection Operator (LASSO) regressions were used to select independent predictors of Fugl-Meyer upper extremity (FM-UE) scores among FA and MD values of SMATT regions.  ...  A 10-fold crossvalidation approach was used to estimate λ and the optimal LASSO model. Bootstrapping with 1,000 times resampling was used to estimate standard errors of the predictor's coefficients.  ... 
doi:10.3389/fneur.2022.813763 pmid:35432180 pmcid:PMC9008887 fatcat:6uthpjysvfhlloht5wg3cklsbu

Network communication models improve the behavioral and functional predictive utility of the human structural connectome

Caio Seguin, Ye Tian, Andrew Zalesky
2020 Network Neuroscience  
Communication matrices were (i) used to perform predictions of five data-driven behavioral dimensions and (ii) correlated to resting-state functional connectivity (FC).  ...  For instance, validation of our results for connectomes mapped using probabilistic tractography and/or larger numbers of streamline seeds would be valuable.  ...  The same train and test sets were used for lasso and NBS regressions.  ... 
doi:10.1162/netn_a_00161 pmid:33195945 pmcid:PMC7655041 fatcat:beqmyezrwfgctcxkvic47zvt64

Network communication models improve the behavioral and functional predictive utility of the human structural connectome [article]

Caio Seguin, Ye Tian, Andrew Zalesky
2020 biorxiv/medrxiv   pre-print
Communication matrices were (i) used to perform predictions of five data-driven behavioral dimensions and (ii) correlated to interregional resting-state functional connectivity (FC).  ...  For instance, validation of our results for connectomes mapped using probabilistic tractography and/or larger numbers of streamline seeds would be valuable.  ...  The same train and test sets were used for lasso and NBS regressions.  ... 
doi:10.1101/2020.04.21.053702 fatcat:ns5tg6l5qjepvbukv4257xgfii

Communication dynamics in the human connectome shape the cortex-wide propagation of direct electrical stimulation [article]

Caio Seguin, Maciej Jedynak, Olivier David, Sina Mansour L, Olaf Sporns, Andrew Zalesky
2022 bioRxiv   pre-print
Here, we use 2.77 million intracranial EEG recordings, acquired following 29,055 single-pulse electrical stimulations in a total of 550 individuals, to study inter-areal communication in the human brain  ...  We used a lasso regression [94] to predict y from X.  ...  Whole-brain white matter tractograms of individual participants were mapped using a probabilistic tractography pipeline (MRtrix3 software [78] , multi-shell multi-tissue constrained spherical deconvolution  ... 
doi:10.1101/2022.07.05.498875 fatcat:dx6qs4w4xnevlezvdyxy7bd5ni

Predictive models of brain connectivity based on transportation on a Riemannian manifold [article]

Fani Deligianni, Jonathan D. Clayden
2018 arXiv   pre-print
Subsequently, we ran probabilistic tractography, implemented in TractoR, for each dataset.  ...  Towards this end, we use randomised Lasso and bootstrapping with replacement that resample the subjects space and provide an estimation of the probability a connection to be selected.  ... 
arXiv:1811.08763v1 fatcat:dmlzd6jl3jc4zgskoq2atz5ire

A Framework for Inter-Subject Prediction of Functional Connectivity From Structural Networks

Fani Deligianni, Gael Varoquaux, Bertrand Thirion, David J. Sharp, Christian Ledig, Robert Leech, Daniel Rueckert
2013 IEEE Transactions on Medical Imaging  
These probabilistic labels were then used as spatial priors in a subsequent refinement step, where a probabilistic intensity model is solved using the Expectation-Maximization (EM) algorithm.  ...  For this purpose, we use the randomized LASSO, a generalization of LASSO with better sparse recovery properties [50] .  ... 
doi:10.1109/tmi.2013.2276916 pmid:23934663 fatcat:26fl7luy6refzfjywvuc3edzvu

Multidimensional analysis and detection of informative features in human brain white matter

Adam Richie-Halford, Jason Yeatman, Noah Simon, Ariel Rokem, Roberto Toro
2021 PLoS Computational Biology  
Tractometry uses diffusion-weighted magnetic resonance imaging (dMRI) to quantify tissue properties along the trajectories of these connections.  ...  We developed a method based on the sparse group lasso (SGL) that takes into account tissue properties along all of the bundles and selects informative features by enforcing both global and bundle-level  ...  This manuscript was prepared using a limited access dataset obtained from the Child Mind Institute Biobank, The Healthy Brain Network dataset.  ... 
doi:10.1371/journal.pcbi.1009136 pmid:34181648 fatcat:dllei7jxn5airpjqq4iqobyope

Frontotemporal correlates of impulsivity and machine learning in retired professional athletes with a history of multiple concussions

R. Goswami, P. Dufort, M. C. Tartaglia, R. E. Green, A. Crawley, C. H. Tator, R. Wennberg, D. J. Mikulis, M. Keightley, Karen D. Davis
2015 Brain Structure and Function  
Behavioural changes can emerge after repeated concussion and thus we used MRI to examine the UF and connected gray matter as it relates to impulsivity and aggression in retired professional football players  ...  Using machine learning, we found that UF diffusion imaging differentiates athletes from healthy controls with significant classifiers based on UF mean and radial diffusivity showing 79-84 % sensitivity  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s)  ... 
doi:10.1007/s00429-015-1012-0 pmid:25721800 pmcid:PMC4853456 fatcat:tno5gioxcbbtvl3btrowzfnuja

Early Imaging Based Predictive Modeling of Cognitive Performance Following Therapy for Childhood ALL

Rakib Al-Fahad, Mohammed Yeasin, John O. Glass, Heather M. Conklin, Lisa M. Jacola, Wilburn E. Reddick
2019 IEEE Access  
tractography data, morphometry statistics, tractography measures, behavioral, and demographic variables.  ...  Current state-of-the-art methods mainly use hypothesis-driven statistical testing methods to characterize and model such cognitive events.  ...  of the probabilistic fiber tracing technique [20] .  ... 
doi:10.1109/access.2019.2946240 pmid:32547892 pmcid:PMC7297193 fatcat:gkphqd7s5raxfczna3j6e5e4ji

Structurally-informed Bayesian functional connectivity analysis

Max Hinne, Luca Ambrogioni, Ronald J. Janssen, Tom Heskes, Marcel A.J. van Gerven
2014 NeuroImage  
The model was tested on simulated data as well as resting-state fMRI data and compared with a graphical lasso analysis.  ...  In order to make model estimation feasible it is assumed that the sparseness structure of the precision matrices is given by an estimate of structural connectivity obtained using diffusion imaging data  ...  One approach would be to use bootstrap procedures together with the graphical lasso . Another approach, as demonstrated in this paper, is to use a Bayesian approach.  ... 
doi:10.1016/j.neuroimage.2013.09.075 pmid:24121202 fatcat:moxfjofkdfcqxjrahmy4azqrbi

Multi-Link Analysis: Brain Network Comparison via Sparse Connectivity Analysis [article]

Alessandro Crimi, Luca Giancardo, Fabio Sambataro, Alessandro Gozzi, Vittorio Murino, Diego Sona
2018 bioRxiv   pre-print
Discovery is, however, hindered by the prior knowledge used to make hypotheses. On the other hand, exploratory data analysis is made complex by the high dimensionality of data.  ...  In our experiments, we automatically identified disease-relevant connections in datasets with unsupervised and anatomy driven parcellation approaches using high-dimensional datasets.  ...  26 -we use a multivariate bootstrap-like approach followed by a stability selection step.  ... 
doi:10.1101/277046 fatcat:vvgtewdkzjcihpqdhooztn4thi
« Previous Showing results 1 — 15 out of 51 results