Can we predict music genres based on fMRI connectivity patterns alone? This project explores a single-subject decoding approach using ROI-to-ROI correlation matrices and machine learning classifiers on OpenNeuro dataset ds003720.
This project examines dynamic functional connectivity (dFC) within the Default Mode Network (DMN) in children with ADHD using the ADHD-200 dataset. Key methods of analyses include time-varying correlation, clustering of connectivity states, and group comparisons to understand how brain network dynamics differ in ADHD
We used the ADHD-200 Sample dataset to implement various machine learning classification models, aimed at diagnosing ADHD through resting-state fMRI signals.
This project aimed to create a detailed tutorial on B0 field mapping principles in MRI and demonstrate the estimation methods interactively. Additionally, it explored the importance of B0 field maps in MRI by comparing the connectivity matrix of rs-fMRI with and without using the B0 field map in the processing pipeline.
Can functional connectivity predict sleep deprivation? This project aims to explore neuroimaging data organization to build a workflow from the acquisition of an open dataset to the visualization of brain connectivity. The pipeline will be detailed and carried out for one subject, using resting state fMRI to compare the result between normal sleep and sleep deprivation (less than 3 hours of sleep the previous night).
This project aims to using both fMRI data and the behavioral data during a n-back task to compare the difference between ADHD children and the heathly control ones.
Can functional connectivity data be used as a predictor for neuropsychiatric diagnosis? This project explores the usefulness of connectivity data in predicting ADHD, Bipolar Disorder, and Schizophrenia diagnoses using machine learning classification methods.
Can functional connectivity predict sensory deprivation? This project 1. explores neuroimaging data organization and preprocessing using open science tools and 2. uses a predictive model to classify whether a participant is hearing or not. For better visualization, the most contributing coefficients in the classifier are displayed on the brain.
This project aimed to understand how to pre-process fMRI data using fMRIPrep. Through this learning experience, a tutorial was created.
In this project I employed some of the tools we learned at the Brainhack school to generate interactive figures to display functional connectivity from MEG and fMRI resting state data from the Human Connectome Project.
Copyright (c) 2025, BrainHack School; all rights reserved.
Template by Bootstrapious. Ported to Hugo by DevCows.