Research in computer analysis of medical images bears many promises to improve patients'
health. However, a number of systematic challenges are slowing down the progress of the …

Magnetic resonance imaging and computed tomography from multiple batches (eg sites,
scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to …

Abstract Domain generalization (DG) seeks predictors which perform well on unseen test
distributions by leveraging data drawn from multiple related training distributions or …

Computer Vision (CV) has achieved remarkable results, outperforming humans in several
tasks. Nonetheless, it may result in significant discrimination if not handled properly. Indeed …

Removing the bias and variance of multicentre data has always been a challenge in large
scale digital healthcare studies, which requires the ability to integrate clinical features …

Increasingly large MRI neuroimaging datasets are becoming available, including many
highly multi-site multi-scanner datasets. Combining the data from the different scanners is …

Prediction of chronological age from neuroimaging in the healthy population is an important
issue because the deviations from normal brain age may highlight abnormal trajectories …

Modern neuroimaging studies frequently combine data collected from multiple scanners and
experimental conditions. Such data often contain substantial technical variability associated …

Brain imaging research enjoys increasing adoption of supervised machine learning for
single-participant disease classification. Yet, the success of these algorithms likely depends …

Data harmonization is an important method for combining or transforming data. To date
however, articles about data harmonization are field-specific and highly technical, making it …