Manfredo Atzori

This study benchmarks predictive models for long-term stroke outcomes using a global consortium, revealing mechanistic diversity and key predictors across motor, cognitive, and emotional domains.

The paper compares spatial and temporal muscle synergies in upper-limb movements, finding that temporal synergies require fewer components and show higher inter-subject similarity.

stainlib provides a Python library for augmenting and normalizing H&E histopathology images to improve model robustness across clinical settings.

This paper develops a deep learning retrieval system for digital histopathology images and literature to improve pathologists' workflow and decision support.