Study generates synthetic fNIRS data and applies machine learning for improved neuroimaging.
problem Scarcity of high-quality fNIRS neuroimaging datasets.
method Synthetic data generation using Monte Carlo simulations and machine learning.
result Improved accuracy and efficiency of fNIRS tomography.
Study reveals XAI methods fail in neuroimaging, suggesting domain-specific adaptation.
problem Systematic failures of XAI methods in neuroimaging applications.
method Systematic comparison of XAI methods on 45,000 structural brain MRIs using a novel validation framework.
result Two widely used XAI methods (GradCAM and Layer-wise Relevance Propagation) fail to accurately explain neuroimaging data.
Advances in Python and data standards boost reproducibility in neuroimaging.
problem Lack of reproducibility in scientific research.
method Open data sharing resources, data standards, open-source Python, and software engineering advances.
result Reproducibility in neuroimaging has improved with new tools and practices.
Deep learning improves AD diagnosis and prognosis from neuroimaging data.
problem Early detection and accurate classification of Alzheimer's disease.
method Deep learning models applied to neuroimaging data for AD diagnosis and prognosis.
result Deep learning models can achieve high accuracy in AD diagnosis and prognosis.
Deep learning aids in autism diagnosis and rehabilitation using neuroimaging data.
problem Challenges in automated detection and rehabilitation of ASD using neuroimaging data.
method Deep learning techniques applied to neuroimaging data for ASD diagnosis and rehabilitation.
result Deep learning improves accuracy in ASD diagnosis and rehabilitation.
NEURO-DRAM improves neuroimaging classification accuracy.
problem Improper use of traditional computer vision models in neuroimaging.
method 3D recurrent visual attention model trained with reinforcement learning.
result NEURO-DRAM achieves state-of-the-art accuracy in Alzheimer's disease prediction.
InVA models image outcomes from multiple modalities, outperforming standard VAEs.
problem Understanding relationships across multiple imaging modalities in neuroimaging.
method Integrative Variational Autoencoder (InVA) framework for image-on-image regression.
result InVA accurately predicts PET scans from structural MRI, outperforming conventional models.
BPt is a Python library for ML with neuroimaging data.
problem Analyzing large neuroimaging datasets using machine learning.
method Unified framework of ML tools for tabulated and neuroimaging data.
result Unified ML tools for neuroimaging and tabulated data.
fastHDMI improves neuroimaging variable selection in high-dimensional data.
problem Efficient variable screening in high-dimensional neuroimaging datasets.
method Three mutual information estimation methods implemented in fastHDMI.
result FFTKDE-based method superior for continuous nonlinear outcomes.
Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g. multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate…
HBR improves normative modeling of neuroimaging data across multiple sites.
problem Dealing with nuisance variation in neuroimaging data across different sites.
method Hierarchical Bayesian regression (HBR) for multi-site normative modeling.
result HBR provides more accurate normative ranges compared to existing methods.
Neuroimaging research has predominantly drawn conclusions based on classical statistics, including null-hypothesis testing, t-tests, and ANOVA. Throughout recent years, statistical learning methods enjoy increasing popularity, including cross-validation, pattern classification, and sparsity-inducing regression. These t…
Nowadays, a lot of scientific efforts are concentrated on the diagnosis of Alzheimer's Disease (AD) applying deep learning methods to neuroimaging data. Even for 2017, there were published more than a hundred papers dedicated to AD diagnosis, whereas only a few works considered a problem of mild cognitive impairments (…
DeepFDR uses deep learning for better FDR control in neuroimaging data.
problem Spatial dependence among voxel-based tests in neuroimaging data.
method DeepFDR leverages unsupervised deep learning-based image segmentation.
result DeepFDR outperforms existing methods in FDR control and computational efficiency.
New method quantifies biases in neuroimaging datasets.
problem Pooling neuroimaging datasets can introduce biases.
method Causal inference to quantify confounding factors.
result Simple pooling often leads to biased training data.
Traditional voxel-level multiple testing procedures in neuroimaging, mostly p-value based, often ignore the spatial correlations among neighboring voxels and thus suffer from substantial loss of power. We extend the local-significance-index based procedure originally developed for the hidden Markov chain models, whic…
Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding- than in decoding models. In this paper, we a…
Motivated by applications in neuroimaging analysis, we propose a new regression model, Sparse TensOr REsponse regression (STORE), with a tensor response and a vector predictor. STORE embeds two key sparse structures: element-wise sparsity and low-rankness. It can handle both a non-symmetric and a symmetric tensor respo…
Deep normative modeling of clinical neuroimaging data improves diagnostic performance.
problem Modeling variation of neuroimaging measures across individuals for psychiatric disorders.
method Proposes a deep normative modeling framework based on neural processes (NPs) for spatially structured mixed-effect modeling of neuroimaging data.
result Substantial improvements in novelty detection performance for certain diagnostic problems.
Integrative analysis of patient health records and neuroimages using MemGCN.
problem Combining EHR and neuroimaging data for disease understanding.
method Memory-Based Graph Convolution Network (MemGCN) framework.
result Superior classification performance in Parkinson's Disease cases versus controls.
fcHMRF-LIS controls FDR in neuroimaging data, improving power and scalability.
problem Complex spatial dependencies and high variability in FDR control methods for neuroimaging data.
method fcHMRF-LIS integrates LIS-based testing with fcHMRF to model spatial structures efficiently.
result fcHMRF-LIS achieves accurate FDR control, lower FNR, and higher true positives compared to existing methods.
Unified normative modeling for neuroimaging phenotypes using denoising diffusion models.
problem Discarding multivariate dependence in neuroimaging pipelines.
method Denoising diffusion probabilistic models (DDPMs) with FiLM and SAINT backbones.
result Unified multivariate normative modeling with better calibration and dependence preservation.
CNNs adapted for brain images predict age with improved accuracy.
problem Applying CNNs to brain images without considering their 3D structure.
method Two modifications to existing CNN architectures tailored for brain images.
result Achieved a mean absolute error (MAE) of 1.4 years compared to 1.6 years for a baseline.
Novel Bayesian framework for spatio-temporal neuroimaging data.
problem Inference on multi-task sparse hierarchical regression models with complex spatio-temporal dynamics.
method Flexible hierarchical Bayesian framework with Kronecker product covariance structure, majorization-minimization optimization, and Riemannian geometry.
result Improved performance on synthetic and real M/EEG data.
Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexi…
This volume is a collection of contributions from the 5th Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI) at the Neural Information Processing Systems (NIPS 2015) conference. Modern multivariate statistical methods developed in the rapidly growing field of machine learning are being increasingly…
A new model for dynamic covariance recovery in neuroimaging data.
problem Estimating time-varying covariances in high-dimensional neuroimaging data.
method Nonconvex factorization into sparse spatial and smooth temporal components, combined with spectral initialization and gradient descent.
result The proposed method achieves linear convergence and superior performance compared to existing approaches.
This paper describes a new neuroimaging analysis toolbox that allows for the modeling of nonlinear effects at the voxel level, overcoming limitations of methods based on linear models like the GLM. We illustrate its features using a relevant example in which distinct nonlinear trajectories of Alzheimer's disease relate…
Canonical correlation analysis (CCA) is a valuable method for interpreting cross-covariance across related datasets of different dimensionality. There are many potential applications of CCA to neuroimaging data analysis. For instance, CCA can be used for finding functional similarities across fMRI datasets collected fr…
Novel framework predicts brain biomarker trajectories with superior performance.
problem Challenges in estimating longitudinal brain biomarker trajectories due to variability, inconsistencies, and irregular measurements.
method Personalized deep kernel regression with Adaptive Shrinkage Estimation.
result Superior predictive performance compared to state-of-the-art models.
A new framework detects statistical significance of deep learning in neuroimaging studies.
problem Lack of statistical significance testing in deep learning neuroimaging.
method Non-parametric framework using autoencoders and SVM, with random-effects inference and cross-validation.
result CV and RUB methods offer acceptable false positive rates and statistical power, but low generalization ability.
A new framework for brain mapping using statistical agnostic methods.
problem Estimating brain connectivity with limited data and controlling false positives.
method Statistical Agnostic Mapping (SAM) based on concentration inequalities.
result Relieves instability and provides less conservative p-value correction.
Novel algorithm for private analysis of fMRI data.
problem Privacy concerns in collaborative neuroimaging data analysis.
method Differentially private decentralized ICA algorithm using correlated noise.
result Algorithm outperforms existing methods on synthetic and real neuroimaging datasets.
Develops a semi-supervised learning method to generate missing neuroimaging modalities.
problem Lack of paired neuroimaging data for training and inference.
method Semi-Supervised Adversarial CycleGAN (SSA-CGAN) using adversarial and cycle losses.
result Improves reconstruction error and robustness to noise.
New method handles missing data in multimodal brain imaging.
problem Missing data in multimodal brain imaging.
method Full Information Linked ICA (FI-LICA) algorithm.
result FI-LICA outperforms current practices in classification and prediction.
Pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease have been the subject of extensive research in recent years. In this paper, we use deep learning methods, and in particular sparse autoencoders and 3D convolutional neural networks, to build an algorithm that can predict the di…
Method predicts brain regions for neuroimaging phenotypes.
problem Predicting phenotypes from brain networks without static community structure.
method Supervised community detection using block-structured regularization and ADMM optimization.
result The method identifies task-specific brain regions that improve phenotype prediction.
Selective inference improves multi-task neuroimaging analysis.
problem Improving predictive performance and modeling accuracy in neuroimaging studies.
method Proposes a framework for selective inference to jointly identify relevant covariates and conduct valid inference in a sparsity-inducing model.
result Selective inference yields tighter confidence intervals and more accurate signal recovery than single-task methods.
Bayesian method for estimating functional graphical models from neuroimaging data.
problem Estimating dependence structures from functional data in neuroscience.
method Fully Bayesian regularization scheme, including direct Bayesian analog of functional graphical lasso and graphical horseshoe.
result Insight into brain compensation after traumatic brain injury.
Due to the rapid innovation of technology and the desire to find and employ biomarkers for neurodegenerative disease, high-dimensional data classification problems are routinely encountered in neuroimaging studies. To avoid over-fitting and to explore relationships between disease and potential biomarkers, feature lear…
Efficiently analyzes multidimensional functional data using separable basis functions.
problem Curse of dimensionality in traditional functional data analysis.
method Marginal product basis systems for multidimensional data, tensor decomposition, differential operator-based penalties.
result Efficient estimation of multidimensional functional data representations.
A new geometric framework embeds correlation matrices into Euclidean space for scalable brain network analysis.
problem Inefficient and unstable analysis of functional brain networks in high-dimensional contexts.
method Diffeomorphic transformations to embed correlation matrices into Euclidean space, preserving manifold properties.
result Improved computational speed and enhanced accuracy compared to conventional manifold-based approaches.
Most brain disorders are very heterogeneous in terms of their underlying biology and developing analysis methods to model such heterogeneity is a major challenge. A promising approach is to use probabilistic regression methods to estimate normative models of brain function using (f)MRI data then use these to map variat…
Proposes a new method for analyzing multimodal neuroimaging data.
problem Combining interpretability and flexibility in multimodal data analysis.
method Orthogonalized kernel debiased machine learning approach.
result Established consistency and asymptotic normality of the estimated primary parameter.
Machine learning models predict brain age with systematic bias, corrected in this study.
problem Systematic bias in machine learning regression models for brain age prediction.
method General constrained optimization approach to correct bias.
result Our method effectively eliminates the bias from brain age predictions.
Graph Signal Processing (GSP) is a promising framework to analyze multi-dimensional neuroimaging datasets, while taking into account both the spatial and functional dependencies between brain signals. In the present work, we apply dimensionality reduction techniques based on graph representations of the brain to decode…
Deep learning models brain deformations based on atrophy and growth data.
problem Simulating brain deformations due to atrophy and growth.
method Differentiable biomechanical model using deep learning.
result Trained model can rapidly simulate new brain deformations with minimal residuals.
Multiple hypothesis testing is a significant problem in nearly all neuroimaging studies. In order to correct for this phenomena, we require a reliable estimate of the Family-Wise Error Rate (FWER). The well known Bonferroni correction method, while simple to implement, is quite conservative, and can substantially under…