Gabriele Amorosino

This study benchmarks deep learning models for white matter tract segmentation across diverse datasets, finding that CNN-based models perform best within their training domain but degrade under domain shifts, and introduces an ensemble method to mitigate this issue.

This study tracks brain development and learning in first graders, finding that white matter changes predict math learning but not reading.

The paper aligns white matter tracts with canonical functional brain networks using an atlas and meta-analytic decoding, revealing structural-functional organization.

The paper shows that structural connectivity in the human visual cortex preserves retinotopic organization, revealing a retinotopic wiring principle and systematic perceptual asymmetries in early visual cortex connectivity.

This paper evaluates transfer learning for adapting a deep learning model trained on healthy data to segment white matter bundles in glioma patients, finding performance drops due to domain shift and partial success of transfer learning.

This study investigates whether transfer learning can improve segmentation of white matter bundles in glioma patients by addressing domain shift between healthy and patient data.

This work evaluates how white matter registration methods affect tractogram alignment using homologous fiber structures as a benchmark.

This study uses TMS and tractography to show that the SFG and IFG have opposite roles in predictive/reactive strategies, mediated by the FAT.