A hybrid approach links fMRI data to deep features for visual category decoding.
problem Lack of practical fMRI decoder with CNN structure due to limited brain data.
method Kernel Canonical Correlation Analysis linking fMRI and deep learnt representations.
result Effective in distinguishing semantic visual categories using only brain imaging data.
DynDepNet learns dynamic brain graphs from fMRI data for better prediction performance.
problem Static brain graphs from fMRI data lead to poor GNN performance.
method Dynamic Graph Structure Learning for time-varying brain connectivity.
result DynDepNet achieves state-of-the-art sex classification accuracy on real-world fMRI data.
Researchers compare brain connectomes using geodesic distance on manifold for twin pairs.
problem Assessing functional similarity in brain networks between monozygotic and dizygotic twins.
method Using fMRI data, the researchers compared functional networks between mono- and dizygotic twin pairs by measuring similarity with geodesic distance on graph Laplacians.
result Functional networks are more similar in monozygotic twins compared to dizygotic twins, and similarity is higher for task-relevant networks.
Study adapts β-TCVAE for fMRI to recover nonlinear brain components.
problem Capturing nonlinear brain dynamics in fMRI data.
method Adapted β-TCVAE framework for fMRI data. result Recovery of meaningful nonlinear spatial components in fMRI data.
Deep CNNs identify age-related patterns in fetal brain activity.
problem Understanding age effects in fetal brain development.
method Supervised 3D Convolutional Neural Networks applied to fetal fMRI data.
result Deep CNNs can distinguish age groups in fetal brain activity.
Adaptive smoothing in fMRI improves brain activity analysis.
problem Optimizing spatial smoothing in fMRI data processing pipelines.
method Integrating adaptive spatial smoothing as a neural network layer.
result Adaptive smoothing enhances brain activity analysis accuracy.
Brain networks has attracted the interests of many neuroscientists. From functional MRI (fMRI) data, statistical tools have been developed to recover brain networks. However, the dimensionality of whole-brain fMRI, usually in hundreds of thousands, challenges the applicability of these methods. We develop a hierarchica…
ST-GCN improves rs-fMRI prediction accuracy by modeling spatio-temporal graph connectivity.
problem Existing rs-fMRI methods neglect functional connectivity or temporal dynamics.
method Spatio-temporal graph convolutional network (ST-GCN) trained on BOLD time series.
result ST-GCN predicts gender and age more accurately than common methods.
Proposes a new similarity learning framework for brain networks.
problem Learning similarity metrics for neuroimages, especially fMRI and DTI.
method End-to-end similarity learning framework using Higher-order Siamese GCN.
result Achieves significant AUC gains over existing methods.
A new method clusters subjects based on brain networks without vectorizing fMRI data.
problem Distortion of clustering results when simplifying fMRI data structure.
method Wishart mixture models for multiple-view clustering of brain networks.
result Identifies multiple underlying pairs of associations between subject clusters and brain sub-networks.
This study shows how EEG can be used to generate fMRI data.
problem Mapping fMRI from EEG signals.
method Deep learning approaches (Autoencoders, GANs, Pairwise Learning).
result Feasibility of EEG to fMRI brain image mappings.
Proposes a method to cluster fMRI data and estimate brain connectivity networks.
problem Clustering fMRI data to identify patient groups based on brain connectivity.
method Random covariance clustering model (RCCM) to cluster subjects and estimate individual and shared FC networks.
result RCCM outperforms other methods in clustering and FC network estimation, demonstrated through simulations and real data.
Graph embedding improves fMRI classification and reveals brain region differences in ASD.
problem Difficult to embed informative brain fMRI representations due to high dimensionality and low SNR.
method Modelled fMRI as a graph, used GNN to learn from graph data, incorporated mutual information loss (Infomax).
result Infomax graph embedding improves classification performance and reveals separable nodal representations of ASD and HC groups.
Framework identifies brain connectivity alterations for MDD patients using limited rs-fMRI data.
problem Difficult to analyze brain connectivity alterations from limited rs-fMRI data.
method Proposed a multitask Gaussian Bayesian network (MTGBN) framework to learn individual disease-induced alterations.
result Framework efficiently learns Bayesian network structures from limited data, showing improved performance.
Understanding the functional architecture of the brain in terms of networks is becoming increasingly common. In most fMRI applications functional networks are assumed to be stationary, resulting in a single network estimated for the entire time course. However recent results suggest that the connectivity between brain …
DeepLight uses LSTM to decode fMRI data, improving cognitive state analysis.
problem Challenges in analyzing neuroimaging data due to high dimensionality, low sample size, and complex dependency structure.
method Introduces DeepLight framework using LSTM-based DL models to process fMRI data sequences, adapts LRP for interpretability.
result DeepLight outperforms conventional fMRI analysis methods in decoding cognitive states and identifying brain regions.
Study extracts brain networks in multiple time-resolutions using deep learning.
problem Analyzing connectivity patterns among brain regions for cognitive tasks.
method Wavelet decomposition, short time windows, Stacked De-noising Auto-Encoder (SDAE), hierarchical clustering.
result Each cluster represents a cognitive task with high performance metrics.
Unsupervised neural models predict brain activity better than supervised methods.
problem Understanding how the brain represents visual information without direct supervision.
method Built upon PredNet, used RSA to compare PredNet representations to fMRI and MEG data.
result Unsupervised models trained to predict video frames outperform supervised image classification models in predicting brain activity.
New method clusters brain networks via nonlinear dependencies.
problem Capturing non-linear nodal dependencies in brain networks.
method Kernel ARMA modeling and Grassmannian mapping.
result Effective clustering framework for various brain network problems.
Functional connectivity refers to the temporal statistical relationship between spatially distinct brain regions and is usually inferred from the time series coherence/correlation in brain activity between regions of interest. In human functional brain networks, the network structure is often inferred from functional m…
BrainCast predicts whole-brain fMRI time series from short scans.
problem Short scans reduce fMRI data quality and statistical power.
method Spatio-temporal forecasting framework for fMRI time series.
result BrainCast improves fMRI time series quality and prediction.
Fine-grained atlases improve fMRI analysis of brain activity.
problem Large fMRI datasets require scalable brain network summaries.
method Trained on millions of fMRI volumes, DiFuMo dictionaries of 64-1024 networks.
result Fine-grained atlases enhance classic fMRI analysis pipelines.
Novel method extracts hierarchical brain connectivity patterns from fMRI.
problem Functional hierarchical organization of the human brain.
method Sparse Connectivity Patterns (SCPs) with hierarchy of sparse overlapping patterns, deep factorization of correlation matrices.
result Reproducible multi-scale hierarchical SCPs more stable than single-scale patterns.
DBGDGM models dynamic brain graphs for better understanding brain function.
problem Previous brain graph models ignore temporal dynamics, limiting their usefulness.
method DBGDGM clusters brain regions into evolving communities and learns dynamic node embeddings.
result DBGDGM outperforms baselines in graph generation, dynamic link prediction, and graph classification.
Survey of deep learning methods for fMRI natural image reconstruction.
problem Reconstructing natural images from fMRI brain activity.
method Survey of deep learning approaches, including architectural design, datasets, and evaluation metrics.
result Performance evaluation across standardized metrics.
Sparse ELM classifier predicts brain ages from adolescent multimodal brain data.
problem Predicting brain ages from adolescent multimodal brain data with high accuracy.
method Sparse ELM classifier using residual errors for feature pruning.
result RES-ELM classifier outperforms conventional and sparse Bayesian learning ELM.
Develops GIN for fMRI sex classification, explaining results.
problem Difficulty in explaining GNN classification results in neuroscientific terms.
method Develops Graph Isomorphism Network (GIN) for fMRI data, leveraging CNN saliency maps.
result GIN enables visualization of brain regions important for sex classification.
PR-GNN identifies salient brain regions for ASD biomarkers.
problem Identifying brain regions associated with neurological disorders.
method Pooling Regularized Graph Neural Network (PR-GNN) with novel salient region selection.
result PR-GNN outperforms baseline methods in ASD classification accuracy.
New method reconstructs images from fMRI data using unlabeled data.
problem Challenges in acquiring labeled data for fMRI-to-image reconstruction.
method Self-supervised training with Encoder-Decoder and Decoder-Encoder networks.
result Reconstruction network adapts to new unlabeled test data.
Graph Neural Network identifies ASD biomarkers from fMRI data.
problem Finding biomarkers for Autism Spectrum Disorder (ASD).
method Graph Neural Network (GNN) for analyzing task-fMRI brain networks, 2-stage pipeline to interpret feature importance.
result GNN achieves high accuracy in identifying ASD biomarkers and reveals their association with social behaviors.
Paper introduces a framework for diagnosing Alzheimer's disease using higher-order topological features from fMRI.
problem Diagnosing Alzheimer's disease using brain network topology.
method Persistent homology to extract higher-order features (cycles, cavities) from fMRI data.
result Framework significantly outperforms existing methods in AD classification.
A novel method automates quality control of fMRI scans, improving accuracy and generalizability.
problem Lack of automated QC for fMRI scans limits clinical neuroscience research.
method Train machine learning classifiers using runtime log features to predict scan quality.
result Classifiers trained on FLAG-QC features outperform previous methods (AUC=0.79 vs AUC=0.56).
GNNs improve brain activity forecasting in fMRI studies.
problem Understanding neural dynamics in the brain.
method Comparison of GNN architectures for modeling fMRI data.
result GNNs outperform VAR models in robustly scaling to large network studies.
STCA discovers dynamic functional brain networks using spatial-temporal convolution and attention.
problem Lack of dynamic exploration of functional brain networks.
method Spatial-Temporal Convolutional Attention (STCA) model.
result STCA can discover dynamic functional brain networks in a novel way.
Paper detects abnormalities in brain activity patterns using unsupervised learning.
problem Detecting abnormalities in resting-state brain activity patterns.
method Two strategies: autoencoder approach and next frame prediction.
result Both approaches can learn useful representations of rs-fMRI data for abnormality detection.
Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet mathematical constraints such as sparse coding and positivity both provide alternate biologically-plausible frameworks for generating brain networks. Non-negative Matrix Factorization (NMF) would suppress negative BO…
Unified cognitive system from diverse fMRI studies using neural representations.
problem Aggregate heterogeneous brain function data into a universal cognitive system.
method Multi-task learning and multi-scale dimension reduction to learn low-dimensional cognitive representations.
result Achieves best prediction performance on large reference datasets and small datasets.
Enhances brain connectivity graph estimation using additional spatial information.
problem Estimating brain connectivity networks from fMRI data with spatial information.
method Integrates additional spatial information into graph estimation by strengthening tuning parameters.
result Improves reproducibility and provides effective estimations of brain connectivity graphs.
Functional Magnetic Resonance Imaging (fMRI) is a powerful non-invasive tool for localizing and analyzing brain activity. This study focuses on one very important aspect of the functional properties of human brain, specifically the estimation of the level of parallelism when performing complex cognitive tasks. Using fM…
Paper presents a method to diagnose schizophrenia using fMRI dynamics from healthy controls.
problem Early diagnosis of mental disorders like schizophrenia using fMRI.
method Self-supervised pre-training on fMRI dynamics of healthy controls for transfer learning.
result Effective classification of schizophrenia using fMRI dynamics with small datasets.
Paper introduces a new method to identify brain hubs using both structural and functional connectivity.
problem Hub node identification in brain networks using only functional connectivity.
method Graph signal processing framework that models functional activity as graph signals on structural connectivity.
result The proposed GraFHub framework identifies hub nodes more accurately than conventional methods.
Graphs improve brain activity decoding from fMRI data.
problem Decoding brain activity from fMRI data.
method Dimensionality reduction techniques based on graph representations of the brain.
result Mixed graphs using both geometric structure and functional connectivity offer the best performance.
New methods improve brain data analysis from fMRI datasets.
problem Simplified brain models from correlational values are insufficient.
method Deep learning and geometric deep learning techniques.
result Improved predictive spatio-temporal brain data representation.
New method classifies brain networks for distinguishing disorders.
problem Classifying brain networks for various disorders.
method Uses edge weights and network structure via penalties promoting sparsity.
result Effective in distinguishing brain disorders from fMRI data.
A novel topological method analyzes fMRI data over time.
problem Analyzing time-varying fMRI data due to noise and person-to-person variation.
method Encoding each time point as a persistence diagram of topological features.
result Time-varying persistence diagrams can cluster participants and study brain state trajectories.
New method identifies causal brain connections from fMRI data.
problem Identifying causal brain interactions from statistical associations.
method ψ-learning incorporated linear non-Gaussian acyclic model (ψ-LiNGAM). result Identified three types of hub structures and 16 causal flows.
New method combines prior knowledge and brain atlases for fMRI analysis.
problem Matrix factorization formulation of task-related fMRI problem.
method Incorporates prior knowledge from experimental design and brain atlases, uses novel sparsity promoting constraint.
result Efficiently copes with uncertainties and selection of sparsity parameters.
This paper clusters networks with annotated time-series data using kernel-ARMA and Grassmannian geometry.
problem Clustering networks with annotated time-series data, including state, node, and subnetwork clustering.
method Extract features from time-series data using kernel-ARMA, map onto Grassmannian, and cluster using Riemannian geometry.
result The proposed framework outperforms state-of-the-art clustering schemes on brain-network data.