Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, New York.
Center for Advanced Imaging Innovation and Research (CAI2R), New York University School of Medicine, New York, New York.
Magn Reson Med. 2019 Jan;81(1):116-128. doi: 10.1002/mrm.27355. Epub 2018 May 17.
Although 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 2 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 led to substantial decreases in reconstruction image quality, whereas image contrast was less relevant. Trainings from heterogeneous training data generalized well toward the 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.
尽管深度学习在磁共振图像重建方面显示出了巨大的潜力，但关于这种方法成功的一个悬而未决的问题是，在训练数据和测试数据之间存在偏差的情况下的稳健性。本研究的目的是评估图像对比度、信噪比和图像内容对学习图像重建的泛化能力的影响，并展示迁移学习的潜力。
使用具有不同信噪比、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，从欠采样数据中训练重建。在训练过程中未使用的 10 个来自 2 种不同脉冲序列的体内膝关节 MRI 采集上评估训练后的重建性能。通过使用少量体内 MR 训练数据对来自合成数据的基线训练进行微调，评估迁移学习。
训练和测试之间的 SNR 差异导致重建图像质量的大幅下降，而图像对比度则不太相关。来自异构训练数据的训练可以很好地推广到具有各种采集参数的测试数据。来自非磁共振图像数据的合成训练数据显示出残留的混叠伪影，通过迁移学习启发的微调可以去除这些伪影。
本研究深入了解了在训练和测试之间采集设置存在偏差的情况下学习图像重建的泛化能力。它还为仅使用少量训练案例对特定目标应用进行微调的迁移学习潜力提供了展望。
