Efficacy of MRI data harmonization in the age of machine learning. A multicenter study across 36 datasets

Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicenter data is necessary to reduce the confounding effect associated with non-biological sources of variability in the data. However, when applied to the entire dataset before machine learning, the harmonization leads to data leakage, because information outside the training set may affect model building, and potentially falsely overestimate performance. We propose a …

age cs.lg data datasets eess.iv machine machine learning machine learning techniques mri multiple pooling power promote q-bio.qm reduce statistical study