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.
Proposes a new method for analyzing fMRI data using gradient-based RSA and Searchlight.
problem Time-consuming and stability issues in classical RSA techniques for large-scale fMRI data.
method Gradient-based Representational Similarity Analysis (GRSA) with Searchlight.
result SSL-GRSA achieves superior performance compared to other RSA algorithms on multi-subject datasets.
Study confirms sparse coding in whole brain using MRI data.
problem Sparse coding in the whole brain's neural activities.
method Applied various matrix factorization methods to fMRI data.
result Sparse coding hypothesis in information representation in the whole human brain is confirmed.
New method creates personalized brain atlases from large datasets.
problem Limited generalizability and spatial specificity of traditional probabilistic atlases.
method Data-driven clustering of regions using point distribution models.
result Personalized probabilistic atlases adapt quickly to new subjects.
Automated brain CT image retrieval from traumatic brain injury cohorts using deep neural networks.
problem Manual image retrieval of whole brain CT scans from large clinical cohorts is time-consuming and resource-intensive.
method Proposes a deep convolutional neural network (dMIR) for automated classification of 2D montage images.
result Achieved high accuracy (f1=1.0) for validation and testing data sets.
Bayesian methods struggle with large-scale brain connectivity estimation.
problem Estimating reliable whole-brain connectivity from limited data.
method Comparison of three Bayesian estimation methods for multivariate Ornstein-Uhlenbeck model.
result Bayesian method scales poorly with network size and requires more samples for similar accuracy.
Deep transfer learning improves fMRI decoding from small datasets.
problem Small sample size and high dimensionality of fMRI datasets.
method Transfer learning using a pre-trained deep learning model on a large dataset.
result A pre-trained DL model outperforms a model trained from scratch on a new dataset.
There is a growing interest in joint multi-subject fMRI analysis. The challenge of such analysis comes from inherent anatomical and functional variability across subjects. One approach to resolving this is a shared response factor model. This assumes a shared and time synchronized stimulus across subjects. Such a model…
BrainTorrent uses peer-to-peer FL for medical image segmentation without a central server.
problem Lack of sufficient annotated data for personalized medical models.
method Peer-to-peer federated learning framework without a central server.
result BrainTorrent outperforms traditional server-based FL and achieves similar performance to pooled data training.
New method aligns brain data across individuals for better brain decoding.
problem Inter-individual variability in brain response patterns limits decoder generalization.
method SpectralOT method that embeds cortical geometry into Laplace-Beltrami eigenmodes.
result SpectralOT strikes balance between aligning functional features and preserving anatomical structure.
New method segments brain tumors and organs-at-risk for radiation therapy.
problem Automating segmentation of brain tumors and organs-at-risk in radiation therapy planning.
method Combines contrast-adaptive generative model and spatial regularization model.
result Tumor segmentation accuracy comparable to state-of-the-art methods.
Finding the most effective way to aggregate multi-subject fMRI data is a long-standing and challenging problem. It is of increasing interest in contemporary fMRI studies of human cognition due to the scarcity of data per subject and the variability of brain anatomy and functional response across subjects. Recent work o…
We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a deep artificial neural network that assigns each voxel in an MR image of the brain to its corresponding anatomical region. The inputs of the network capture infor…
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…
Researchers create a simulator to infer worm brain states from calcium imaging data.
problem Impute C. elegans membrane potentials from calcium imaging data.
method Developed a stochastic whole-brain simulator and used SMC method for imputation.
result First to infer worm brain states from partial calcium imaging observations.
New method aligns brain surfaces based on functional signatures.
problem Inter-individual variability in neuroimaging data.
method Fused Unbalanced Gromov-Wasserstein (FUGW) based on Optimal Transport.
result FUGW significantly increases between-subject correlation of activity.
Variables in many massive high-dimensional data sets are structured, arising for example from measurements on a regular grid as in imaging and time series or from spatial-temporal measurements as in climate studies. Classical multivariate techniques ignore these structural relationships often resulting in poor performa…
Bayesian network structure learning algorithms with limited data are being used in domains such as systems biology and neuroscience to gain insight into the underlying processes that produce observed data. Learning reliable networks from limited data is difficult, therefore transfer learning can improve the robustness …
Bayesian DNN speeds up brain MRI segmentation.
problem Efficiently predicting brain MRI segmentations.
method Bayesian deep neural network with spike-and-slab dropout.
result Bayesian DNN outperforms existing methods in segmentation accuracy.
Extract low-dimensional dynamics from multiple neural recordings.
problem Current methods can't handle dynamics across multiple neural recordings.
method Subspace-identification approach with moment-matching objective and scalable stochastic gradient descent.
result Can identify dynamics and predict correlations even with missing data and small overlap.
fMRI analysis classifies autobiographical memory valence across individuals.
problem Classifying valence of autobiographical memories across different participants.
method Feature selection (ReliefF) combined with boosting methods applied to voxel space data.
result Classification accuracy of 62% in cross-participant setting, significantly higher than previous results.
MarmoNet automates analysis of marmoset brain axonal projections.
problem Automatically detect and segment axonal tracer signals in noisy, cluttered images.
method Uses machine learning, specifically CNNs and image registration, to process and map axonal projections.
result Automated pipeline extracts and maps axonal projections robustly.
New model improves detection of brain disorder variations.
problem Modeling brain disorder heterogeneity in neuroimaging data.
method Tensor-variate Gaussian process in a Bayesian mixed-effects model with Kronecker algebra and low-rank approximation.
result Improved detection sensitivity compared to mass-univariate and classifier approaches.
PS-VAE extracts multi-parameter MRI biomarkers with uncertainty quantification.
problem Uncertainty in inverse problems limits clinical acceptance of quantitative MRI methods.
method Physics-Structured Variational Autoencoder (PS-VAE) integrating physics simulator and self-supervised learning.
result PS-VAE provides full covariance of inter-parameter correlations and accelerates multi-parametric MRI quantification.
Computed tomography (CT) equivalent information is needed for attenuation correction in PET imaging and for dose planning in radiotherapy. Prior work has shown that Gaussian mixture models can be used to generate a substitute CT (s-CT) image from a specific set of MRI modalities. This work introduces a more flexible cl…
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.
Inverse inference, or "brain reading", is a recent paradigm for analyzing functional magnetic resonance imaging (fMRI) data, based on pattern recognition and statistical learning. By predicting some cognitive variables related to brain activation maps, this approach aims at decoding brain activity. Inverse inference ta…
3D ConvNets improved with Project & Excite for medical imaging segmentation.
problem Improving segmentation performance in 3D medical imaging.
method Proposed Project & Excite (PE) modules for 3D F-CNNs, extending 2D recalibration methods.
result Project & Excite modules boost segmentation performance up to 0.3 in Dice Score.
Stochastic encoding improves gender classification of brain networks from UK Biobank data.
problem Complexity and bias in interpreting deep learning models of brain connectivity.
method Stochastic encoding in ensemble of CNNs, multivariate balancing algorithm.
result AUROC of 0.8459, with resting-state data more accurate than task data.
The paper analyzes deep neural networks using information theory to improve classification accuracy.
problem Improving classification accuracy in deep neural networks.
method Modeling the output of convolutional filters as a random variable conditioned on class and network structure, computing conditional entropy as a compact code.
result The conditional entropy feature analysis leads to higher classification accuracy than the original CNN.
New approach models brain dynamics using coupled van der Pol oscillators and LSTM.
problem Capturing nonlinear dynamics in brain calcium imaging data.
method Proposes a new approach combining van der Pol oscillators and LSTM for modeling brain activity.
result Shows improved accuracy and interpretability compared to LSTM and hybrid VDP-LSTM approach.
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.
Substantial evidence indicates that major psychiatric disorders are associated with distributed neural dysconnectivity, leading to strong interest in using neuroimaging methods to accurately predict disorder status. In this work, we are specifically interested in a multivariate approach that uses features derived from …
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.
New method uses SPHARM coefficients to classify AD, MCI, and controls.
problem Discriminating between AD, MCI, and normal aging.
method Spherical harmonics (SPHARM) coefficients for hippocampal shape modeling, SVM classification, feature selection.
result High accuracy in classifying AD vs controls (94%) and MCI vs controls (83%).
Combined ML and JVC-SENSE enable high-resolution imaging with fewer shots and less distortion.
problem Severe distortion artifacts and blurring in high-resolution imaging due to shot-to-shot variations in msEPI.
method Employed deep learning to obtain an interim image with minimal artifacts, which was then used in a Joint Virtual Coil Sensitivity Encoding (JVC-SENSE) reconstruction.
result Enabled navigator-free, highly accelerated multishot EPI with fewer shots and improved geometric fidelity.
Proposes LSTM algorithm for robust Alzheimer's disease progression modeling with missing data.
problem Challenges in modeling disease progression using incomplete longitudinal data.
method Utilizes Long Short-Term Memory (LSTM) networks for Alzheimer's disease progression modeling with a generalized training rule for handling missing data.
result Achieves significantly lower mean absolute error (MAE) than alternatives with p < 0.05.