IEEE Trans Med Imaging. 2022 Aug;41(8):1925-1937. doi: 10.1109/TMI.2022.3151118. Epub 2022 Aug 1.
Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively.
磁共振成像（MRI）已被证明是诊断阿尔茨海默病（AD）的有效方法。深度学习的最新显著进展极大地促进了基于数据驱动的 CNN 方法的 MRI 分析，该方法使用大规模的纵向 MRI 数据集。然而，由于志愿者的意外退出，大多数现有的 MRI 数据集都是碎片化的。为了解决这个问题，我们提出了一种新颖的时间递归生成对抗网络（TR-GAN）来完成 MRI 数据集的缺失会话。与现有的基于 GAN 的方法不同，这些方法要么无法生成未来的会话，要么只能生成固定长度的会话，TR-GAN 采用递归连接来递归地、平稳地生成具有不同长度的未来会话。具体来说，TR-GAN 采用递归连接来处理不同的输入序列长度，并灵活地生成未来的不同长度的会话。此外，我们还设计了一个多尺度和位置（MSL）模块和一个 SWAP 模块，以鼓励模型更好地关注细节信息，这有助于生成高质量的 MRI 数据。与其他流行的 GAN 架构相比，TR-GAN 在两个数据集的所有评估指标中都取得了最佳性能。在扩展整个 MRI 数据集后，AD 与认知正常（CN）与轻度认知障碍（MCI）和稳定 MCI 与进展性 MCI 分类的平衡准确率分别提高了 3.61%和 4.00%。
