Being able to collect rich morphological information of brain, structural magnetic resonance imaging (MRI) is popularly applied to computer-aided diagnosis of Alzheimer’s disease (AD). Conventional methods for AD diagnosis are labor-intensive and typically depend on a substantial amount of hand-crafted features. In this paper, we propose a novel framework of convolutional neural network that aims at identifying AD or normal control, and mild cognitive impairment or normal control. The centerpiece of our method are pseudo-3D block and expanded global context block which are integrated into residual block of backbone in a cascaded manner. To be specific, we transfer pseudo-3D block in the video feature representation to extract structural MRI features. Besides, we extend the 2D global context block to the 3D model which can effectively combine the features and capture the latent associations, while simulate the global context in each dimension of structural MRI results. With the preprocessed structural MRI used as the input of the overall network, our method is capable of constructing a latent representation with multiple residual blocks to promote the classification accuracy. Intrinsically, our method reduces the complexity of conventional 3D convolutional network model applied to AD diagnosis and improves the classification accuracy over the baseline. Furthermore, our network can fully take advantage of the deep 3D convolutional neural network for automatic feature extraction and representation, and thus avoids the limitation of low processing efficiency caused by the preprocessing procedure in which a specific area needs to be annotated in advance. Experimental results on Alzheimer’s Disease Neuroimaging Initiative database indicate that our proposed method reports accuracy of 89.29% on the AD/NC and 87.57% on the mild cognitive impairment/NC, whilst our approach achieves the 0.5% improvement of accuracy compared with the backbone.

结构磁共振成像（MRI）能够收集丰富的大脑形态信息，广泛应用于阿尔茨海默病（AD）的计算机辅助诊断。AD 诊断的传统方法是劳动密集型的，并且通常依赖于大量手工制作的特征。在本文中，我们提出了一种新的卷积神经网络框架，旨在识别 AD 或正常控制，以及轻度认知障碍或正常控制。我们方法的核心是伪 3D 块和扩展的全局上下文块，它们以级联方式集成到主干的残差块中。具体而言，我们在视频特征表示中传输伪 3D 块以提取结构 MRI 特征。除了，我们将 2D 全局上下文块扩展到 3D 模型，该模型可以有效地结合特征并捕获潜在关联，同时在结构 MRI 结果的每个维度中模拟全局上下文。将预处理的结构 MRI 作为整个网络的输入，我们的方法能够构建具有多个残差块的潜在表示，以提高分类精度。从本质上讲，我们的方法降低了应用于 AD 诊断的传统 3D 卷积网络模型的复杂性，并提高了基线的分类精度。此外，我们的网络可以充分利用深度 3D 卷积神经网络进行自动特征提取和表示，从而避免了预处理过程中需要预先标注特定区域而导致处理效率低下的限制。阿尔茨海默病神经影像学倡议数据库的实验结果表明，我们提出的方法报告的准确率为 89.29％的AD / NC和87.57 ％的轻度认知障碍/ NC，而我们的方法实现了0.5 ％精度的提高与主干相比较。