field survey / ecological data

This paper introduces an AI-driven neuromodulation platform that enhances and reorganizes human tongue sensorimotor networks by targeting individual network architecture.

The paper uses fMRI and a deep neural network to assess memory maturation in children aged 3-7, finding that hippocampal development drives memory pattern maturation.

The paper distinguishes pedohebephilic preference from child sexual offending using resting-state functional connectivity and network-based prediction, identifying distinct neural network alterations.

Site-aware population GNN on ABIDE-I: cohort AUC about 0.94 (kept with site-only edges) was not reproduced by a site-prior classifier (0.506); a directed-edge support gain (+0.252) vanished when symmetrised (−0.003).

This paper introduces a method to analyze directional brain network organization using fMRI data, identifying strength and duration signatures of neural influence across species and conditions.

This study compares two computational models of social perception and inference against fMRI data, finding both explain neural activity in social brain regions.

This paper introduces NARS-fMRI, a method that detects millisecond neuronal activity via 23Na signal changes, showing it correlates with BOLD and glutamate transients in rodent somatosensory cortex.

This study introduces MEDIC, a framewise distortion correction method for multi-echo fMRI that improves alignment and reduces motion impact without requiring field maps.

The paper uses fMRI and a Bayesian Switching Dynamic Systems model to analyze brain states during encoding and post-encoding rest in children, showing how dynamic neural states predict episodic memory.

The paper introduces an updated camtrapR package that provides an end-to-end analytical platform for camera trap data, including a graphical interface and Bayesian modeling workflows.

STRiDE improves dynamic brain state estimation by integrating structural and functional connectivity, revealing disruptions in schizophrenia.

NeuroMark-HiFi detects high-spatial-frequency functional brain networks, revealing additional group differences in schizophrenia and healthy controls.

This paper develops an fMRI analysis pipeline to study central chemoreception in humans by comparing breath-hold and free breathing conditions, identifying brainstem and diencephalic regions involved in CO2 responses.

This study uses HD-DOT to decode naturalistic movie content from brain activity with accuracy above chance, demonstrating its potential for non-invasive, real-world applications.

The paper develops a brain age prediction model using multiscale functional connectivity from rsfMRI data of 4,259 individuals, showing that multiscale measures improve prediction and that brain age gaps correlate with cognitive and clinical measures.

This study uses a VAE to map fMRI data into a latent space, enabling the modeling of transient co-activity patterns and their temporal dynamics.

This paper uses a graph neural network to predict task-evoked fMRI responses from structural connectome data, revealing the importance of ipsilateral cortical regions for higher cognitive functions.

The paper introduces the broken_window algorithm to assess the reliability of short-term ecological trends by resampling long-term data and evaluating the likelihood of misleading trajectories.

The paper introduces BLENDS, a method for augmenting 4D fMRI data by generating anatomically realistic images, which improves prediction performance in neuroimaging tasks.

This study shows that phoneme-level decoders trained on elicited inner speech can accurately predict self-generated inner speech, demonstrating zero-shot task transfer.

BrainNET, a machine learning method for fMRI network inference, outperforms correlation and partial correlation in identifying brain network changes in ADHD.

The paper introduces a fuzzy c-mean clustering method to detect nodes in the insular cortex, revealing new functional connectivity patterns beyond existing models.