Assessment of the generalization of learned image reconstruction and the potential for transfer learning.
Assessment of the generalization of learned image reconstruction and the potential for transfer learning.
复制标题
DOI：
10.1002/mrm.27355
复制
发表时间：
2019-01
影响因子：
3.3
通讯作者：
Sodickson DK
中科院分区：
文献类型：
--
作者：
Knoll F;Hammernik K;Kobler E;Pock T;Recht MP;Sodickson DK
虽然深度学习在MR图像重建方面表现出了很大的潜力，但这种方法的成功还有一个悬而未决的问题，那就是在训练数据和测试数据之间存在偏差的情况下的鲁棒性。本研究的目标是评估图像对比度、SNR和图像内容对学习图像重建泛化的影响，并展示迁移学习的潜力。使用具有不同SNR、采样模式、图像对比度和从公共图像数据库生成的合成数据的数据集，从欠采样数据训练重建。在10次体内患者膝关节MRI采集中评价了训练重建的性能，采集来自训练期间未使用的两个不同脉冲序列。通过使用体内MR训练数据的一个小子集对合成数据的基线训练进行微调来评估迁移学习。训练和测试之间的SNR偏差导致重建图像质量大幅下降，而图像对比度则不太相关。从异构训练数据的训练推广到测试数据与采集参数的范围。来自合成非MR图像数据的训练显示出残留的混叠伪影，其可以通过迁移学习启发的微调来去除。这项研究提出了深入了解学习图像重建的泛化能力，在训练和测试之间的采集设置的偏差。它还为迁移学习的潜力提供了展望，以便仅使用少量的培训案例将培训微调到特定的目标应用程序。
While deep learning has shown great promise for MR image reconstruction, an open question regarding the success of this approach is the robustness in the case of deviations between training and test data. The goal of this study is to assess the influence of image contrast, SNR and image content on the generalization of learned image reconstruction, and to demonstrate the potential for transfer learning. Reconstructions were trained from undersampled data using data sets with varying SNR, sampling pattern, image contrast and synthetic data generated from a public image database. The performance of the trained reconstructions was evaluated on 10 in-vivo patient knee MRI acquisitions from two different pulse sequences that were not used during training. Transfer learning was evaluated by fine-tuning baseline trainings from synthetic data with a small subset of in-vivo MR training data. Deviations in SNR between training and testing lead to substantial decreases in reconstruction image quality, while image contrast was less relevant. Trainings from heterogeneous training data generalized well towards test data with a range of acquisition parameters. Trainings from synthetic non-MR image data showed residual aliasing artifacts, which could be removed by transfer learning inspired fine-tuning. This study presents insights into the generalization ability of learned image reconstruction with respect to deviations in the acquisition settings between training and testing. It also provides an outlook for the potential of transfer learning to fine-tune trainings to a particular target application using only a small number of training cases.
登录
查看更多内容
影响因子：
3.3
作者：
Uecker, Martin;Lai, Peng;Murphy, Mark J.;Virtue, Patrick;Elad, Michael;Pauly, John M.;Vasanawala, Shreyas S.;Lustig, Michael
通讯作者：
Lustig, Michael
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
影响因子：
2.1
作者：
Pock, Thomas;Sabach, Shoham
通讯作者：
Sabach, Shoham
影响因子：
3.8
作者：
Kwon, Kinam;Kim, Dongchan;Park, HyunWook
通讯作者：
Park, HyunWook
影响因子：
10.6
作者：
Wang, Z;Bovik, AC;Simoncelli, EP
通讯作者：
Simoncelli, EP