Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:2647-2650. doi: 10.1109/EMBC46164.2021.9630103.
To realize precision medicine, it is important to realize the detection of the individual atrophy of Alzheimer's disease (AD) patients. Our objective is to find individual brain regions of interest (ROIs) in AD patients via an unsupervised deep learning network.
This study used structural Magnetic Resonance Imaging (sMRI) scans with the 732 healthy control (HC) subjects and 202 AD patients from the Alzheimer's disease Neuroimaging Initiative (ADNI), and the 105 HC subjects were collected at the Xuanwu Hospital. An unsupervised deep learning network based on Adversarial Autoencoders (AAE) was proposed to delineate the individual atrophy of AD patients. In the proposed model, Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN) were combined to learn the potential distribution and train a generator. In this step, the 530 HCs from ADNI were applied as the training dataset and the 105 HCs from Xuanwu Hospital were applied as an external validation dataset. The structural similarity (SSIM) was used to judge the robustness of the proposed model. Then, ROIs of the 202 AD patients were detected. In order to verify the clinical performance of these ROIs, other 202 HCs were selected from ADNI and a multilayer perceptron (MLP) was used to classify AD versus HC by 5 folder cross-validation. In the comparative experiments, we compared our model with three other previous models.
The SSIM reached 0.86 in both training and external validation datasets. Eventually, the classification accuracy of our model achieved 0.94±0.02. In the meanwhile, the classification accuracies were 0.89±0.01, 0.85±0.04 and 0.91±0.03 for the three previous methods.
Our deep learning model could detect individual atrophy in AD patients. It may be a useful tool for AD diagnosis in clinics.
为了实现精准医学，实现阿尔茨海默病（AD）患者的个体化脑萎缩检测非常重要。我们的目标是通过无监督深度学习网络找到 AD 患者的个体化感兴趣脑区（ROI）。
本研究使用了来自阿尔茨海默病神经影像学倡议（ADNI）的 732 名健康对照（HC）受试者和 202 名 AD 患者的结构磁共振成像（sMRI）扫描，以及宣武医院的 105 名 HC 受试者。我们提出了一种基于对抗自动编码器（AAE）的无监督深度学习网络来描绘 AD 患者的个体化脑萎缩。在该模型中，我们将变分自动编码器（VAE）和生成对抗网络（GAN）相结合，以学习潜在分布并训练生成器。在这一步骤中，我们将 ADNI 的 530 名 HC 作为训练数据集，宣武医院的 105 名 HC 作为外部验证数据集。我们使用结构相似性（SSIM）来判断所提出模型的稳健性。然后，检测了 202 名 AD 患者的 ROI。为了验证这些 ROI 的临床性能，我们从 ADNI 中选择了另外 202 名 HC，并使用多层感知机（MLP）通过 5 折交叉验证对 AD 与 HC 进行分类。在对比实验中，我们将我们的模型与其他三个先前的模型进行了比较。
在训练集和外部验证集上，SSIM 均达到 0.86。最终，我们的模型的分类准确率达到 0.94±0.02。同时，三个先前方法的分类准确率分别为 0.89±0.01、0.85±0.04 和 0.91±0.03。
我们的深度学习模型可以检测 AD 患者的个体化脑萎缩。它可能是临床 AD 诊断的有用工具。
