Dieter Adrian Häring

The paper introduces a scalable Bayesian factor analysis framework for handling mixed and incomplete data, demonstrating its effectiveness on MS datasets.

BARTharm improves MRI data harmonization by using image quality metrics and Bayesian non-parametric models, outperforming ComBat in removing scanner-induced bias while preserving biological signals.

The paper develops a convolutional neural network to automate MRI defacing quality control, reducing manual checks and improving efficiency.