用预训练模型先验提升隐式神经表示，加速MRI成像质量更优
PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRI
- 融合预训练模型先验知识与实例优化，增强隐式神经表征
- 在高速成像下显著减少结构丢失和伪影，重建质量超越现有方法
- 适合需要高保真快速MRI重建的研究者与临床应用
加速磁共振成像（MRI）可缩短扫描时间，但常导致图像质量下降。尽管隐式神经表示（INRs）在重建中展现潜力，但在高加速因子下因先验约束弱，易出现结构损失和混叠伪影。为此，我们提出PrIINeR，一种将预训练深度学习模型先验知识融入INR框架的重建方法。通过结合群体级知识与实例级优化，并施加双重数据一致性，PrIINeR使重建结果同时符合采集的k-space数据和先验信息。在NYU fastMRI数据集上的评估表明，该方法不仅优于当前最先进的基于INR的方法，还超越多个学习型前沿方法，在结构保持和保真度上显著提升，有效消除混叠伪影。PrIINeR弥合了深度学习与INR技术的差距，为高质量、加速MRI重建提供了更可靠的解决方案。代码已公开于https://github.com/multimodallearning/PrIINeR。
原文摘要 · Abstract (English)
Accelerating Magnetic Resonance Imaging (MRI) reduces scan time but often degrades image quality. While Implicit Neural Representations (INRs) show promise for MRI reconstruction, they struggle at high acceleration factors due to weak prior constraints, leading to structural loss and aliasing artefacts. To address this, we propose PrIINeR, an INR-based MRI reconstruction method that integrates prior knowledge from pre-trained deep learning models into the INR framework. By combining population-level knowledge with instance-based optimization and enforcing dual data consistency, PrIINeR aligns both with the acquired k-space data and the prior-informed reconstruction. Evaluated on the NYU fastMRI dataset, our method not only outperforms state-of-the-art INR-based approaches but also improves upon several learning-based state-of-the-art methods, significantly improving structural preservation and fidelity while effectively removing aliasing artefacts.PrIINeR bridges deep learning and INR-based techniques, offering a more reliable solution for high-quality, accelerated MRI reconstruction. The code is publicly available on https://github.com/multimodallearning/PrIINeR.
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。