Rick van Veen, Neha Rajendra Bari Tamboli, Sofie Lövdal, Sanne K Meles, Remco J Renken, Gert-Jan de Vries, Dario Arnaldi, Silvia Morbelli, Pedro Clavero, José A Obeso, Maria C Rodriguez Oroz, Klaus L Leenders, Thomas Villmann, Michael Biehl
In machine learning, data often comes from different sources, but combining them can introduce extraneous variation that affects both generalization and interpretability. For example, we investigate the classification of neurodegenerative diseases using FDG-PET data collected from multiple neuroimaging centers. However, data collected at different centers introduces unwanted variation due to differences in scanners, scanning protocols, and processing methods. To address this issue, we propose a two-step approach to limit the influence of center-dependent variation on the classification of healthy controls and early vs...
March 2024: Artificial Intelligence in Medicine