Our project aims to develop different methods for the analysis of behavior in mice (in this case, exploration of an object) to determine which is the best approach to this kind of study. We were able to implement and compare three increasingly complex methods to determine exploration time: manual labeling; motion tracking and data analysis using a custom algorithm; training a Machine Learning classifier on our labeled data.
Schizophrenia (SZ) involves significant alterations in perception, thoughts, mood, and behavior. This project aims to develop an AI model using machine learning for complementary SZ diagnosis, utilizing prefrontal cortex connectomics and tractography techniques. It focuses on creating scripts for data separation, comparing classification models, and analyzing the connectome of healthy individuals and those with SZ. Early detection and accurate diagnosis through machine learning will enable targeted interventions, improving outcomes for individuals with SZ.
This project uses functional magnetic resonance imaging data to study the connectivity of children with Attention Deficit Hyperactivity Disorder (ADHD).A set of children diagnosed with ADHD were given a series of memory tasks while undergoing MRI scans. In this project, data from one of these tasks was used to calculate connectivity matrices for 65 subjects from that data set and a machine learning model was trained. The data was downloaded from Openneuro website.
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.
The goal of this project is to make a classification of the needs and desires states from studies fMRI data
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.
Can a model predict the genetic profile of an individual based on brain regions volumes? There is growing evidence suggesting that genetic variations formally associated to neurodevelopmental disorders have significant effects on brain structures. In this project, the performance of three classifiers will be compared when predicting the genetic status of individuals from brain region volumes in a highly imbalanced dataset (UK BioBank cohort).
Does functional connectivity between brain regions differ in male and female? If yes then fMRI data can be used to distinguish sex on the basis of the difference in functional connectivity. I applied supervised Machine Learning algorithms on the fMRI data to classify sex.
Machine learning models are often used to analyze fMRI data, whether it be a simple classification or regression problem or something more complex. While the focus of a study is often centered on the model architecture, data preprocessing also plays a vital role in a model’s success. This project will explore the effect that various preprocessing options may have on the prediction performance of a machine learning model for age prediction using resting state fMRI.