To aim of this project was to provide a full neuroimaging workflow from preprocessing of raw data to visualisation of results, to explore longitudinal analysis between two treatments in this dataset and to visualise resting-state networks linked to the default mode network and attention. In my github repository you will find scripts and documentation about the the BIDS to NiFTY conversion, fMRI prep as well as resting-state visualisation of a single participant. There is also a powerpoint presentation slide to guide you through the work.
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.
Sex differences in the language network is a long lasting and unresolved debate in the neuroscience field. Clinical studies have shown that pathologies or developmental conditions affecting language functions can differently affect individuals based on their sex. Although the language network is bilaterally organized, the left hemisphere is dominant for language in most individuals. However, this lateralisation tends to vary between sexes.In the present project, we address the research question on whether young adults present differences in the pattern of rs-fMRI functional connectivity within the language network based on their sex. To address this issue, we propose to determine whether we can classify healthy young adults, men and women, based on their rs-fMRI functional connectivity profiles within the language network.
My project consists of exploring the predictive normative modelling (PCN) toolkit via their numerous tutorials. It contains a markdown file for future new users of this package. It also includes steps on how to format your own data to use this toolkit. Finally, some cloud computing user guides will be touched upon.
Painful experience involves a distributed pattern of brain activity. With hypnosis, it's possible to increase or decrease pain. This project aims to decode fMRI pain-evoked brain activity and identify pattern of activity that are associated with specific hypnotic conditions
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.
What can our brain tells us about our facial expression in response to painful stimulus ? This projects aims to compare different regression algorithms to see if it is possible to predict facial expression of pain from fMRI data in healthy adults.
Generating a BIDS compatible dataset and interactive graphs from the Projet Courtois NeuroMod's hearing test data
In a longitudinal study, the amount of data and figures to manage and create quickly becomes too massive to be manually handled. The goal of this project is to create tools to take an auditory test database and automatically format it into a BIDS compatible dataset and generate interactive graphs.
Experimenting with Occlusion methods to visualize the features learned by a CNN from audio or visual inputs
This project has for goal to explore, understand and learn how to create comprehensive visualizations of the features learned by a convolution neural network, whether the model is specialized in auditory or visual input.