Sean Deoni

Deep learning super-resolution of paediatric ultra-low-field MRI without paired high-field scans

This study develops a deep learning model to enhance ultra-low-field MRI scans to near high-field resolution without paired high-field data, improving image quality and accessibility.

Latent Representations of Early Brain Development: A Multivariate Normative Model of Brain Structure and Behaviour

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.

Ultra-low-field brain MRI morphometry: test-retest reliability and correspondence to high-field MRI

This study evaluates the reliability and correspondence of ultra-low-field MRI morphometry to high-field MRI, showing high reliability and correspondence across scan resolutions and contrasts.

Ultra-low-field paediatric MRI in low- and middle-income countries: super-resolution using a multi-orientation U-Net

This paper develops a deep learning model to enhance ultra-low-field MRI scans for pediatric neurodevelopmental research, achieving better reconstruction of brain structures than existing methods.

Language exposure and brain myelination in early development

This study examines how early language exposure and socioeconomic status affect brain myelination in infants at 6 and 30 months of age using MRI.

Emergence of Human Amygdala Functional Networks: 3 Months to 5 Years of Age

This study examines the development of amygdala functional networks in infants and young children using resting-state fMRI, finding that key networks are already present at 3 months and evolve with age.