Maurício Henriques Serpa

The paper examines the relationship between white matter microstructure, measured by fractional anisotropy, and transition to psychosis in individuals at clinical high risk, finding directionally consistent but small associations.

The paper examines longitudinal white matter changes in early psychosis using diffusion tensor imaging and finds no significant group differences or associations with symptom progression, but links antipsychotic medication dose to lower fractional anisotropy.

The paper develops deep learning models to assess the quality of subcortical brain shape models from MRI, reducing human rater time by 46-70%.

This work uses machine learning to automate quality control of 3D brain shape models, reducing human workload by 30-70% across multiple datasets and diseases.