Brain Age Prediction Using a Brain Multi-atlas-based Ensemble Deep Regression Method

This ME thesis investigates brain age prediction from resting-state functional MRI using a multi-atlas ensemble deep regression framework based on graph convolutional networks. The study compares population-based and individual-based graph representations, evaluates multiple brain atlases, and explores ensemble strategies for combining predictions. Using Human Connectome Project data, the work examines how functional connectivity and graph-based deep learning can be leveraged for accurate brain age estimation.