555 Hits in 5.0 sec

Multivariate decoding of brain images using ordinal regression

O.M. Doyle, J. Ashburner, F.O. Zelaya, S.C.R. Williams, M.A. Mehta, A.F. Marquand
2013 NeuroImage  
Here, we propose a novel, alternative multivariate approach that overcomes these limitationswhole brain probabilistic ordinal regression using a Gaussian process framework.  ...  Considering the modulation of ketamine with lamotrigine, we found that ordinal regression significantly outperformed multi-class classification and metric regression in terms of accuracy and mean absolute  ...  support of our translational imaging research programme.  ... 
doi:10.1016/j.neuroimage.2013.05.036 pmid:23684876 pmcid:PMC4068378 fatcat:7auhjqwblnbtjcpcugzqwocfvq

Sparse Ordinal Logistic Regression and Its Application to Brain Decoding

Emi Satake, Kei Majima, Shuntaro C. Aoki, Yukiyasu Kamitani
2018 Frontiers in Neuroinformatics  
Visual image reconstruction from human brain activity using a combination of multiscale local image decoders.  ...  Regression and Its Application to Brain Decoding.  ... 
doi:10.3389/fninf.2018.00051 pmid:30158864 fatcat:uvyoax6wzvcljb42y4tgnktopi

Sparse ordinal logistic regression and its application to brain decoding [article]

Emi Satake, Kei Majima, Shuntaro Aoki, Yukiyasu Kamitani
2017 bioRxiv   pre-print
To date, there is no established method of predicting ordinal variables in brain decoding.  ...  Brain decoding with multivariate classification and regression has provided a powerful framework for characterizing information encoded in population neural activity.  ...  1 Introduction 29 Application of multivariate classification and regression models to functional magnetic resonance 30 imaging (fMRI) signals has allowed the extraction of information encoded in population  ... 
doi:10.1101/238758 fatcat:grqflkixrvew5e4ndlim4ecpfm

Does Hemispheric Asymmetry Reduction in Older Adults (HAROLD) in motor cortex reflect compensation?

Ethan Knights, Alexa Morcom, Richard N. Henson
2021 Journal of Neuroscience  
behavioural and multivariate Bayes (MVB) decoding approaches.  ...  ageing is to provide a mechanistic explanation of how brain-behaviour relationships change with age.  ...  Analysis of the categorical outcomes for the between-region MVB model comparison (Figure 4B ) used ordinal regression.  ... 
doi:10.1523/jneurosci.1111-21.2021 pmid:34580164 pmcid:PMC8580140 fatcat:g36ksjndrfeozjzp2wytjzjxdi

Reactivating ordinal position information from auditory sequence memory in human brains [article]

Ying Fan, Huan Luo
2022 bioRxiv   pre-print
Here participants performed an auditory sequence WM task with their brain activities recorded using electroencephalography (EEG).  ...  Although content representations have been widely studied in working memory (WM), little is known about how ordinal position information of an auditory sequence is retained in the human brain as well as  ...  Their brain activities were recorded using electroencephalogram (EEG) and a multivariate decoding approach was employed to decode the ordinal position information.  ... 
doi:10.1101/2022.04.04.487064 fatcat:54ejnnthwjedbpt4biquxpdfgq

Decoding the categorization of visual motion with magnetoencephalography [article]

Yousra Bekhti, Alexandre Gramfort, Nicolas Zilber, Virginie van Wassenhove
2017 bioRxiv   pre-print
Brain decoding has primarily been used in cognitive neurosciences to predict differences between pairs of stimuli (e.g. faces vs. houses), but how distinct brain/perceptual states can be decoded following  ...  Two brain states were decoded as a function of the degree of visual motion coherence.  ...  The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  ... 
doi:10.1101/103044 fatcat:2gix4b3c3jgttbhw3mdjj7cqxq

Does Hemispheric Asymmetry Reduction in Older Adults (HAROLD) in motor cortex reflect compensation? [article]

Ethan Knights, Alexa Morcom, Richard N Henson, Cam-CAN
2021 bioRxiv   pre-print
behavioural and multivariate Bayes (MVB) decoding approaches.  ...  Older adults tend to display greater brain activation in the non-dominant hemisphere during even basic sensorimotor responses.  ...  Analysis of the categorical outcomes for the between-region MVB model comparison (Figure4B) used ordinal regression.  ... 
doi:10.1101/2021.06.02.446015 fatcat:2vxvlyuu2vdsfgwzc73durxuli

Neural representation of three-dimensional acoustic space in the human temporal lobe

Xiaolu Zhang, Qingtian Zhang, Xiaolin Hu, Bo Zhang
2015 Frontiers in Human Neuroscience  
Sound localization is an important function of the human brain, but the underlying cortical mechanisms remain unclear.  ...  By employing a machine learning algorithm, we successfully decoded sound location from the blood oxygenation level-dependent signals in the temporal lobe.  ...  This work was supported in part by the National Basic Research Program (973 Program) of China (Grant Nos. 2012CB316301), the National Natural Science Foundation of China (Grant No. 61273023), and the Tsinghua  ... 
doi:10.3389/fnhum.2015.00203 pmid:25932011 pmcid:PMC4399328 fatcat:sof3wzz64rbfpp5nj526lcajra

A perceptual-to-conceptual gradient of word coding along the ventral path

Valentina Borghesani, Fabian Pedregosa, Evelyn Eger, Marco Buiatti, Manuela Piazza
2014 2014 International Workshop on Pattern Recognition in Neuroimaging  
By means of a linear decoding model, we have been able to predict the category of the words subjects were seeing while undergoing a functional magnetic resonance images (fMRI) acquisition.  ...  In this paper we show how the combined use of decoding models and of representational similarity analysis (RSA) can enhance our ability to investigate the inter-categorical distinctions as well as the  ...  In this framework, so called decoding models can be used to predict a discrete class label (classification problem) or a continuous target (regression problem) based on the pattern of activation that a  ... 
doi:10.1109/prni.2014.6858512 dblp:conf/prni/BorghesaniPEBP14 fatcat:7ssnuyrox5axtkdwpdrm2bc2ia

Noise correlations in the human brain and their impact on pattern classification

Vikranth R. Bejjanki, Rava Azeredo da Silveira, Jonathan D. Cohen, Nicholas B. Turk-Browne, Nikolaus Kriegeskorte
2017 PLoS Computational Biology  
Multivariate decoding methods, such as multivoxel pattern analysis (MVPA), are highly effective at extracting information from brain imaging data.  ...  Author summary A central challenge in cognitive neuroscience is decoding mental representations from patterns of brain activity.  ...  We expect that our conclusions will apply to multivariate decoding with brain imaging data more generally.  ... 
doi:10.1371/journal.pcbi.1005674 pmid:28841641 pmcid:PMC5589258 fatcat:h7fibbwlrndenfmdf3wksbd5tm

Increased Prefrontal Activity with Aging Reflects Nonspecific Neural Responses Rather than Compensation

Alexa M. Morcom, Richard N.A. Henson
2018 Journal of Neuroscience  
This is a key question in the neuroscience of aging. In this study, we used novel tests of how different brain regions contribute to long-and short-term memory.  ...  Functional brain imaging studies have often shown increased activity in prefrontal brain regions in older adults.  ...  Analysis of outcomes of the between-region MVB model comparison (PVC and PFC combined vs PVC; see Fig. 2 and main text) used ordinal regression with "polr" in MASS.  ... 
doi:10.1523/jneurosci.1701-17.2018 pmid:30037829 pmcid:PMC6096047 fatcat:hy6hnwdbu5cxrk2pqk7ijyn5ce

Longitudinal Self-Supervised Learning [article]

Qingyu Zhao, Zixuan Liu, Ehsan Adeli, Kilian M. Pohl
2021 arXiv   pre-print
Specifically, we propose a new definition of disentanglement by formulating a multivariate mapping between factors (e.g., brain age) associated with an MRI and a latent image representation.  ...  We implement this model, named Longitudinal Self-Supervised Learning (LSSL), via a standard autoencoding structure with a cosine loss to disentangle brain age from the image representation.  ...  The training uses this ordinal information to encourage the change of subjectspecific representations to follow a common developmental direction.  ... 
arXiv:2006.06930v2 fatcat:u7auxga7w5e7zoi6g4gjxrvai4

Increased prefrontal activity with aging reflects nonspecific neural responses rather than compensation [article]

Alexa M. Morcom, Richard N. Henson
2017 bioRxiv   pre-print
Instead, we used a novel model-based multivariate analysis technique, applied to two independent functional magnetic resonance imaging datasets from an adult-lifespan human sample (N=123 and N=115; approximately  ...  These accounts are difficult to distinguish on the basis of average activity levels within brain regions.  ...  of a boost for STM 591 load (in an ordinal regression, t(95) = -2.00, p = .0479).  ... 
doi:10.1101/156935 fatcat:ygz5fi3vpvefpm2nj4fgkv3cl4

Multivariate decoding of cerebral blood flow measures in a clinical model of on-going postsurgical pain

Jonathan O'Muircheartaigh, Andre Marquand, Duncan J. Hodkinson, Kristina Krause, Nadine Khawaja, Tara F. Renton, John P. Huggins, William Vennart, Steven C.R. Williams, Matthew A. Howard
2014 Human Brain Mapping  
4 Pfizer Global Research and Development, Sandwich, United Kingdom r r Abstract: Recent reports of multivariate machine learning (ML) techniques have highlighted their potential use to detect prognostic  ...  using half of the data (equivalent to 15 min scan time).  ...  The T 2 weighted image was skull stripped using a brain extraction tool [FSL-BET] and the resulting brain-only image was coregistered with the average ASL image and used as a mask to exclude extra-cerebral  ... 
doi:10.1002/hbm.22652 pmid:25307488 pmcid:PMC4322468 fatcat:ifd7rx4ymbcz7ahqgkmtlurnje

Learning to synthesise the ageing brain without longitudinal data [article]

Tian Xia, Agisilaos Chartsias, Chengjia Wang, Sotirios A. Tsaftaris
2021 arXiv   pre-print
To answer this question one must devise (and learn from data) a multivariate auto-regressive function which given an image and a desired target age generates an output image.  ...  Our method synthesises images conditioned on two factors: age (a continuous variable), and status of Alzheimer's Disease (AD, an ordinal variable).  ...  To answer this question one must devise (and learn from data) a multivariate auto-regressive function which given an image and a desired target age generates an output image.  ... 
arXiv:1912.02620v5 fatcat:4rprcq6zanfolfz2xmad7hov5q
« Previous Showing results 1 — 15 out of 555 results