Department of Instrument Science and Engineering, School of EIEE, Shanghai Jiao Tong University, Shanghai, 200240, China.
MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China.
Brain Imaging Behav. 2021 Oct;15(5):2330-2339. doi: 10.1007/s11682-020-00427-y. Epub 2021 Jan 4.
Hippocampal atrophy is often considered as one of the important biomarkers for early diagnosis of Alzheimer's disease (AD), which is an irreversible neurodegenerative disorder. Traditional methods for hippocampus analysis usually computed the shape and volume features from structural Magnetic Resonance Image (sMRI) for the computer-aided diagnosis of AD as well as its prodromal stage, i.e., mild cognitive impairment (MCI). Motivated by the success of deep learning, this paper proposes a deep learning method with the multi-channel cascaded convolutional neural networks (CNNs) to gradually learn the combined hierarchical representations of hippocampal shapes and asymmetries from the binary hippocampal masks for AD classification. First, image segmentation is performed to generate the bilateral hippocampus binary masks for each subject and the mask difference is obtained by subtracting them. Second, multi-channel 3D CNNs are individually constructed on the hippocampus masks and mask differences to extract features of hippocampal shapes and asymmetries for classification. Third, a 2D CNN is cascaded on the 3D CNNs to learn high-level correlation features. Finally, the features learned by multi-channel and cascaded CNNs are combined with a fully connected layer followed by a softmax classifier for disease classification. The proposed method can gradually learn the combined hierarchical features of hippocampal shapes and asymmetries to enhance the classification. Our method is verified on the baseline sMRIs from 807 subjects including 194 AD patients, 397 MCI (164 progressive MCI (pMCI) + 233 stable MCI (sMCI)), and 216 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results demonstrate that the proposed method achieves an AUC (Area Under the ROC Curve) of 88.4%, 74.6% and 71.9% for AD vs. NC, MCI vs. NC and pMCI vs. sMCI classifications, respectively. It proves the promising classification performance and also shows that both hippocampal shape and asymmetry are helpful for AD diagnosis.
海马体萎缩通常被认为是阿尔茨海默病（AD）早期诊断的重要生物标志物之一，AD 是一种不可逆转的神经退行性疾病。传统的海马体分析方法通常从结构磁共振成像（sMRI）中计算形状和体积特征，用于 AD 及其前驱阶段，即轻度认知障碍（MCI）的计算机辅助诊断。受深度学习成功的启发，本文提出了一种基于多通道级联卷积神经网络（CNNs）的深度学习方法，用于从二进制海马体掩模中逐步学习 AD 分类的海马体形状和不对称性的组合分层表示。首先，执行图像分割以生成每个受试者的双侧海马体二进制掩模，并通过相减获得掩模差异。其次，在海马体掩模和掩模差异上分别构建多通道 3D CNN 以提取海马体形状和不对称性的特征进行分类。第三，在 3D CNN 上级联 2D CNN 以学习高级相关特征。最后，将多通道和级联 CNN 学习到的特征与全连接层结合，再加上 softmax 分类器用于疾病分类。所提出的方法可以逐步学习海马体形状和不对称性的组合分层特征，以增强分类。我们的方法在来自阿尔茨海默病神经影像学倡议（ADNI）数据集的 807 名受试者的基线 sMRI 上进行了验证，包括 194 名 AD 患者、397 名 MCI（164 名进展性 MCI（pMCI）+233 名稳定 MCI（sMCI））和 216 名正常对照（NC）。实验结果表明，所提出的方法在 AD 与 NC、MCI 与 NC 和 pMCI 与 sMCI 分类中的 AUC（ROC 曲线下面积）分别为 88.4%、74.6%和 71.9%。这证明了该方法具有有前景的分类性能，也表明海马体形状和不对称性都有助于 AD 诊断。
