High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks.
High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks.
复制标题
DOI：
10.1109/embc44109.2020.9176241
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Akcakaya M
中科院分区：
文献类型：
--
作者：
Hossein Hosseini SA;Yaman B;Moeller S;Akcakaya M
长扫描持续时间仍然是高分辨率磁共振成像的一个挑战。深度学习通过提供直接从数据学习的数据驱动的正则化方法，已经成为加速MRI重建的一种强有力的手段。这些数据驱动的先验通常在测试阶段的未来数据中保持不变，一旦它们在培训中被学习。在这项研究中，我们建议使用迁移学习方法来微调这些规则化的新对象使用自我监督的方法。虽然所提出的方法可以折衷深度学习MRI方法的极快的重建时间，但我们在膝关节MRI上的结果表明，这种自适应可以显著减少重建图像中的残留伪影。此外，建议的方法有可能降低推广到罕见病理情况的风险，而这可能是训练数据中无法获得的。
Long scan duration remains a challenge for high-resolution MRI. Deep learning has emerged as a powerful means for accelerated MRI reconstruction by providing data-driven regularizers that are directly learned from data. These data-driven priors typically remain unchanged for future data in the testing phase once they are learned during training. In this study, we propose to use a transfer learning approach to fine-tune these regularizers for new subjects using a self-supervision approach. While the proposed approach can compromise the extremely fast reconstruction time of deep learning MRI methods, our results on knee MRI indicate that such adaptation can substantially reduce the remaining artifacts in reconstructed images. In addition, the proposed approach has the potential to reduce the risks of generalization to rare pathological conditions, which may be unavailable in the training data.