Francesca Biondo

This paper uses a semi-supervised autoencoder to create multivariate normative models of brain structure and behaviour in children, showing associations between structural deviations and cognitive/behavioural differences.

This paper improves cerebrovascular brain age predictions by harmonizing arterial spin labeling (ASL) features across multiple cohorts using various methods, showing that ASL-specific harmonization enhances model performance.

The paper characterises and stratifies reinforcement-related behaviours by analysing neural activation patterns in adolescents using a statistical framework.