Cristina Granziera

This study uses deep learning and normative modeling to analyze MRI data from MS patients and identify subcortical volume deviations that improve understanding of disease progression.

This paper improves MS lesion segmentation and detection in MRI by using saliency maps to refine prediction scores, achieving higher F1 and PPV scores.

This paper demonstrates a new MRI technique, LoBa-bSSFP, achieving 77-micron isotropic resolution for ex vivo cerebellar imaging using standard 3T equipment.

This paper introduces a robust tractogram filtering method that accounts for motion artefacts in diffusion MRI, validated with simulations and infant data, showing improved structural connectivity and microstructural analyses.

This study evaluates variability in white matter bundle segmentation across 42 groups using the same dataset, finding protocol variability exceeds other sources of inconsistency.

This paper develops a 3T MRI method for high-resolution human whole-brain imaging and applies it to study multiple sclerosis pathology.