Euler Elastica Regularized Logistic Regression for Whole-Brain Decoding of fMRI Data

2018 ◽  
Vol 65 (7) ◽  
pp. 1639-1653 ◽  
Author(s):  
Chuncheng Zhang ◽  
Li Yao ◽  
Sutao Song ◽  
Xiaotong Wen ◽  
Xiaojie Zhao ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Fmri Data ◽  
Whole Brain ◽  
Brain Decoding ◽  
Euler Elastica

scholarly journals Sparse logistic regression for whole-brain classification of fMRI data

NeuroImage ◽  
2010 ◽  
Vol 51 (2) ◽  
pp. 752-764 ◽  
Author(s):  
Srikanth Ryali ◽  
Kaustubh Supekar ◽  
Daniel A. Abrams ◽  
Vinod Menon
Keyword(s):  
Logistic Regression ◽  
Fmri Data ◽  
Whole Brain ◽  
Sparse Logistic Regression

scholarly journals Emotional contagion of pain across different social cues shares common and process-specific neural representations

2020 ◽  
Author(s):  
Feng Zhou ◽  
Jialin Li ◽  
Weihua Zhao ◽  
Lei Xu ◽  
Xiaoxiao Zheng ◽  
...  
Keyword(s):  
Anterior Cingulate Cortex ◽  
Emotional Contagion ◽  
Social Cues ◽  
Thermal Stimulation ◽  
Anterior Cingulate ◽  
Fmri Data ◽  
Whole Brain ◽  
Neural Representations ◽  
Experienced Pain ◽  
Multivariate Pattern

AbstractInsular and anterior cingulate cortex activation across vicarious pain induction procedures suggests that they are core pain empathy nodes. However, pain empathic responses encompass emotional contagion as well as unspecific arousal and overlapping functional activations are not sufficient to determine shared and process-specific neural representations. We employed multivariate pattern analyses to fMRI data acquired during physical and affective vicarious pain induction and found spatially and functionally similar cross-modality (physical versus affective) whole-brain vicarious pain-predictive patterns. Further analyses consistently identified shared neural representations in the bilateral mid-insula. Mid-insula vicarious pain patterns were not sensitive to capture non-painful arousing negative stimuli but predicted self-experienced pain during thermal stimulation, suggesting process-specific representation of emotional contagion for pain. Finally, a domain-general vicarious pain pattern which predicted vicarious as well as self-experienced pain was developed. Our findings demonstrate a generalizable neural expression of vicarious pain and suggest that the mid-insula encodes emotional contagion for pain.

scholarly journals Sparse DCM for whole-brain effective connectivity from resting-state fMRI data

NeuroImage ◽  
2020 ◽  
Vol 208 ◽  
pp. 116367 ◽  
Author(s):  
Giulia Prando ◽  
Mattia Zorzi ◽  
Alessandra Bertoldo ◽  
Maurizio Corbetta ◽  
Marco Zorzi ◽  
...  
Keyword(s):  
Resting State ◽  
Effective Connectivity ◽  
Resting State Fmri ◽  
Fmri Data ◽  
Whole Brain

scholarly journals A Multichannel 2D Convolutional Neural Network Model for Task-Evoked fMRI Data Classification

2019 ◽  
Vol 2019 ◽  
pp. 1-9
Author(s):  
Jinlong Hu ◽  
Yuezhen Kuang ◽  
Bin Liao ◽  
Lijie Cao ◽  
Shoubin Dong ◽  
...  
Keyword(s):  
Neural Networks ◽  
Brain Imaging ◽  
Motor Task ◽  
Data Classification ◽  
Fmri Data ◽  
Imaging Data ◽  
Whole Brain ◽  
Human Connectome Project ◽  
Brain Imaging Data ◽  
3D Cnn

Deep learning models have been successfully applied to the analysis of various functional MRI data. Convolutional neural networks (CNN), a class of deep neural networks, have been found to excel at extracting local meaningful features based on their shared-weights architecture and space invariance characteristics. In this study, we propose M2D CNN, a novel multichannel 2D CNN model, to classify 3D fMRI data. The model uses sliced 2D fMRI data as input and integrates multichannel information learned from 2D CNN networks. We experimentally compared the proposed M2D CNN against several widely used models including SVM, 1D CNN, 2D CNN, 3D CNN, and 3D separable CNN with respect to their performance in classifying task-based fMRI data. We tested M2D CNN against six models as benchmarks to classify a large number of time-series whole-brain imaging data based on a motor task in the Human Connectome Project (HCP). The results of our experiments demonstrate the following: (i) convolution operations in the CNN models are advantageous for high-dimensional whole-brain imaging data classification, as all CNN models outperform SVM; (ii) 3D CNN models achieve higher accuracy than 2D CNN and 1D CNN model, but 3D CNN models are computationally costly as any extra dimension is added in the input; (iii) the M2D CNN model proposed in this study achieves the highest accuracy and alleviates data overfitting given its smaller number of parameters as compared with 3D CNN.

A robust normalization method for fMRI data for brain decoding

2016 ◽  
Author(s):  
Ozan Yildiz ◽  
Fethiye Irmak Dogan ◽  
Ilke Oztekin ◽  
Eda Mizrak ◽  
Fatos T. Yarman Vural
Keyword(s):  
Normalization Method ◽  
Fmri Data ◽  
Brain Decoding

scholarly journals A DEEP LEARNING APPROACH TO ESTIMATING INITIAL CONDITIONS OF BRAIN NETWORK MODELS IN REFERENCE TO MEASURED FMRI DATA

2021 ◽  
Author(s):  
Amrit Kashyap ◽  
Sergey Plis ◽  
Michael Schirner ◽  
Petra Ritter ◽  
Shella Keilholz
Keyword(s):  
Deep Learning ◽  
Initial Conditions ◽  
Brain Activity ◽  
Network Models ◽  
Brain Network ◽  
Measured Data ◽  
Fmri Data ◽  
Short Term ◽  
Whole Brain ◽  
Neural Processes

Brain Network Models (BNMs) are a family of dynamical systems that simulate whole brain activity using neural mass models to represent local activity in different brain regions that influence each other via a global structural network. Research has been interested in using these network models to explain measured whole brain activity measured via resting state functional magnetic resonance imaging (rs-fMRI). Properties computed over longer periods of simulated and measured data such as average functional connectivity (FC), have shown to be comparable with similar properties estimated from measured rs-fMRI data. While this shows that these network models have similar properties over the dynamical landscape, it is unclear how well simulated trajectories compare with empirical trajectories on a timepoint-by-timepoint basis. Previous studies have shown that BNMs are able to produce relevant features at shorter timescales, but analysis of short-term trajectories or transient dynamics as defined by synchronized predictions from BNM made at the same timescale as the collected data has not yet been conducted. Relevant neural processes exist in the time frame of measurements and are often used in task fMRI studies to understand neural responses to behavioral cues. Therefore, it is important to investigate how much of these dynamics are captured by our current brain simulations. To test the nature of BNMs short term trajectories against observed data, we utilize a deep learning technique known as Neural ODE that based on an observed sequence of fMRI measurements, estimates the initial conditions such that the BNMs simulation is synchronized to produce the closest trajectory relative to the observed data. We test to see if the parameterization of a specific well studied BNM, the Firing Rate Model, calculated by maximizing its accuracy in reproducing observed short term trajectories matches with the parameterized model that produces the best average long-term metrics. Our results show that such an agreement between parameterization using long and short simulation analysis exists if also considering other factors such as the sensitivity in accuracy with relative to changes in structural connectivity. Therefore, we conclude that there is evidence that by solving for initial conditions, BNMs can be simulated in a meaningful way when comparing against measured data trajectories, although future studies are necessary to establish how BNM activity relate to behavioral variables or to faster neural processes during this time period.

scholarly journals Brain network constraints and recurrent neural networks reproduce unique trajectories and state transitions seen over the span of minutes in resting-state fMRI

2020 ◽  
Vol 4 (2) ◽  
pp. 448-466
Author(s):  
Amrit Kashyap ◽  
Shella Keilholz
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Resting State ◽  
Large Scale ◽  
Brain Network ◽  
Generative Models ◽  
Network Activity ◽  
Fmri Data ◽  
State Transitions ◽  
Whole Brain

Large-scale patterns of spontaneous whole-brain activity seen in resting-state functional magnetic resonance imaging (rs-fMRI) are in part believed to arise from neural populations interacting through the structural network (Honey, Kötter, Breakspear, & Sporns, 2007 ). Generative models that simulate this network activity, called brain network models (BNM), are able to reproduce global averaged properties of empirical rs-fMRI activity such as functional connectivity (FC) but perform poorly in reproducing unique trajectories and state transitions that are observed over the span of minutes in whole-brain data (Cabral, Kringelbach, & Deco, 2017 ; Kashyap & Keilholz, 2019 ). The manuscript demonstrates that by using recurrent neural networks, it can fit the BNM in a novel way to the rs-fMRI data and predict large amounts of variance between subsequent measures of rs-fMRI data. Simulated data also contain unique repeating trajectories observed in rs-fMRI, called quasiperiodic patterns (QPP), that span 20 s and complex state transitions observed using k-means analysis on windowed FC matrices (Allen et al., 2012 ; Majeed et al., 2011 ). Our approach is able to estimate the manifold of rs-fMRI dynamics by training on generating subsequent time points, and it can simulate complex resting-state trajectories better than the traditional generative approaches.

Sign in / Sign up

Export Citation Format

Share Document