MRI quality control (QC) is challenging due to unbalanced and limited datasets, as well as subjective scoring, which hinder the development of reliable automated QC systems. To address these issues, we introduce an approach that pretrains a model on synthetically generated motion artifacts before applying transfer learning for QC classification. This method not only improves the accuracy in identifying poor-quality scans but also reduces training time and resource requirements compared to training from scratch. By leveraging synthetic data, we provide a more robust and resource-efficient solution for QC automation in MRI, paving the way for broader adoption in diverse research settings.
@article{arxiv.2502.00160,
title = {Improving Quality Control Of MRI Images Using Synthetic Motion Data},
author = {Charles Bricout and Kang Ik K. Cho and Michael Harms and Ofer Pasternak and Carrie E. Bearden and Patrick D. McGorry and Rene S. Kahn and John Kane and Barnaby Nelson and Scott W. Woods and Martha E. Shenton and Sylvain Bouix and Samira Ebrahimi Kahou},
journal= {arXiv preprint arXiv:2502.00160},
year = {2025}
}