Improving Quality Control Of MRI Images Using Synthetic Motion Data
This provides a more robust and resource-efficient solution for automating MRI quality control, potentially benefiting diverse research settings, though it is incremental as it builds on existing transfer learning and synthetic data methods.
The paper tackles the challenge of MRI quality control by pretraining a model on synthetically generated motion artifacts and using transfer learning, which improves accuracy in identifying poor-quality scans and reduces training time and resource requirements.
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.