用合成运动伪影数据预训练，提升MRI图像质量控制准确率
Improving Quality Control Of MRI Images Using Synthetic Motion Data
- 先用合成运动伪影数据预训练模型，再微调用于质量分类
- 相比从零训练，准确率更高且节省训练时间和资源
- 适合需要高效自动化MRI质检的研究团队使用
MRI质量控制（QC）因数据集不平衡、样本有限及评分主观性强而面临挑战，制约了可靠自动化系统的开发。为此，我们提出一种方法：先在合成生成的运动伪影数据上预训练模型，再通过迁移学习应用于QC分类任务。该方法不仅提升了识别低质量扫描的准确率，还显著降低了训练时间与资源消耗，相较于从头训练更具优势。通过利用合成数据，我们提供了一种更鲁棒、更高效的MRI QC自动化解决方案，有助于推动其在多样化研究场景中的广泛应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。