Okito Yamashita

This paper introduces hTSMNet, a method for zero-shot EEG decoding across datasets and paradigms using geometry-conditioned hyperalignment and Riemannian SPD manifold learning.

This study introduces a block-structured Bayesian model for MEG source estimation that integrates functional brain areas and inter-areal relationships, improving accuracy in localizing neural activity.

The paper develops a method to profile resting-state fMRI connectivity variations to improve the reliability and generalizability of psychiatric disorder biomarkers across multiple centers.

This paper introduces a functionally-structured Bayesian model to improve MEG source estimation accuracy and reduce information spreading.

This study compares unsupervised feature selection with supervised methods to identify robust resting-state functional connectivity patterns associated with psychiatric disorders.

This paper identifies a thalamo-somatomotor functional connectivity biomarker that stratifies MDD patients into subtypes with distinct antidepressant treatment responses, demonstrating generalizability across independent datasets.

The paper evaluates rs-fMRI analysis pipelines for MDD biomarkers using multi-site datasets, finding optimal combinations of parcellation, connectivity estimation, harmonization, and machine learning methods.

This study uses a CNN-RNN deep learning model to classify mouse behavioral states from cortex-wide calcium imaging data, identifying key somatosensory regions involved in behavior classification.

This study develops a generalizable neuromarker for ASD across multiple sites and developmental stages, showing significant performance in adults, children, and adolescents.

The paper uses VR-based real-time imaging to study cortical functional connectivity dynamics during behavioral transitions in a mouse model of autism, finding altered FC patterns in motor areas associated with motor clumsiness.

This study uses dynamic mode decomposition to predict individual behavioral differences from resting-state fMRI data, finding that low-frequency dynamic modes are most effective.

The paper identifies common brain networks between major depressive disorder and depression symptoms that generalize across independent imaging sites.

This paper outlines a multi-site MRI study aiming to establish harmonized imaging biomarkers for brain disorders across the lifespan using standardized protocols and data from healthy and patient subjects.

The paper develops a harmonization method for resting-state fMRI data across sites by separating site differences into sampling and measurement biases, reducing measurement bias by 29% and improving signal-to-noise ratios by 40%.