School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China; Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China.
School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China.
Comput Biol Med. 2023 Oct;165:107395. doi: 10.1016/j.compbiomed.2023.107395. Epub 2023 Sep 1.
Recently, deep learning models have achieved superior performance for mapping functional brain networks from functional magnetic resonance imaging (fMRI) data compared with traditional methods. However, due to the lack of sufficient data and the high dimensionality of brain volume, deep learning models of fMRI tend to suffer from overfitting. In addition, existing methods rarely studied fMRI data augmentation and its application. To address these issues, we developed a VAE-GAN framework that combined a VAE (variational auto-encoder) with a GAN (generative adversarial net) for functional brain network identification and fMRI augmentation. As a generative model, the VAE-GAN models the distribution of fMRI so that it enables the extraction of more generalized features, and thus relieve the overfitting issue. The VAE-GAN is easier to train on fMRI than a standard GAN since it uses latent variables from VAE to generate fake data rather than relying on random noise that is used in a GAN, and it can generate higher quality of fake data than VAE since the discriminator can promote the training of the generator. In other words, the VAE-GAN inherits the advantages of VAE and GAN and avoids their limitations in modeling of fMRI data. Extensive experiments on task fMRI datasets from HCP have proved the effectiveness and superiority of the proposed VAE-GAN framework for identifying both temporal features and functional brain networks compared with existing models, and the quality of fake data is higher than those from VAE and GAN. The results on resting state fMRI of Attention Deficit Hyperactivity Disorder (ADHD)-200 dataset further demonstrated that the fake data generated by the VAE-GAN can help improve the performance of brain network modeling and ADHD classification.
最近，与传统方法相比，深度学习模型在从功能磁共振成像（fMRI）数据中映射功能脑网络方面取得了优异的性能。然而，由于缺乏足够的数据和大脑体积的高维度，fMRI 的深度学习模型往往容易出现过拟合。此外，现有的方法很少研究 fMRI 数据增强及其应用。为了解决这些问题，我们开发了一种 VAE-GAN 框架，该框架结合了 VAE（变分自编码器）和 GAN（生成对抗网络），用于功能脑网络识别和 fMRI 增强。作为生成模型，VAE-GAN 对 fMRI 进行建模，以便能够提取更具概括性的特征，从而缓解过拟合问题。与标准 GAN 相比，VAE-GAN 更容易在 fMRI 上进行训练，因为它使用 VAE 的潜在变量来生成虚假数据，而不是依赖于 GAN 中使用的随机噪声，并且它可以生成比 VAE 更高质量的虚假数据，因为鉴别器可以促进生成器的训练。换句话说，VAE-GAN 继承了 VAE 和 GAN 的优点，并避免了它们在 fMRI 数据建模方面的局限性。在 HCP 的任务 fMRI 数据集上的广泛实验证明了与现有模型相比，所提出的 VAE-GAN 框架在识别时间特征和功能脑网络方面的有效性和优越性，并且虚假数据的质量高于 VAE 和 GAN 的数据。在 ADHD-200 数据集的静息态 fMRI 上的结果进一步表明，VAE-GAN 生成的虚假数据可以帮助提高脑网络建模和 ADHD 分类的性能。
