南方医科大学学报

南方医科大学学报 ›› 2020, Vol. 40 ›› Issue (04): 531-537.doi: 10.12122/j.issn.1673-4254.2020.04.13

• • 上一篇    下一篇

基于耦合的卷积-图卷积神经网络的阿尔茨海默病的磁共振诊断方法

李青峰，邢潇丹，冯前进   

  • 出版日期:2020-04-30 发布日期:2020-04-20
  • 基金资助:

Coupled convolutional and graph network-based diagnosis of Alzheimer’s disease using MRI

  

  • Online:2020-04-30 Published:2020-04-20

HTML

PDF

1156

摘要： 目的 针对已有方法未利用大脑拓扑信息的问题，提出基于耦合的卷积-图卷积神经网络的疾病诊断模型，以实现对阿尔茨海默病及其前驱症状的精确诊断，为临床提供可靠的辅助诊断信息。方法 根据ADNI数据库提供的信息，将MMSE评分在20~26分、同时CDR评分为0.5或1的被试的疾病标签标记为AD组；将MMSE评分在24~30分且CDR评分为0、无抑郁症状、无认知障碍、无焦虑症状的被试疾病标签标记为NC组。本文提出一种耦合的卷积-图卷积神经网络（CCGCN）模型，以组间比较获取的疾病相关区域作为输入，利用卷积神经网络，从大脑磁共振图像的不同区域提取疾病相关的特征，再使用图卷积网络，结合提取到的特征，对区域间拓扑结构进行建模，并在图卷积网络中嵌入图池化操作，从而自适应地学习大脑拓扑结构与疾病诊断任务之间的内在联系。利用ADNI数据集，获得CCGCN模型对阿尔茨海默病及其前驱症状的疾病诊断准确率、灵敏度和特异度，并进行模型结构的消融实验。结果 该模型在阿尔茨海默病的诊断任务上取得了92.5%的准确率、88.1%的灵敏度和96.0%的特异度，诊断精度优于目前最先进的方法；同时在区分进行型轻度认知障碍患者和稳定型轻度认知障碍患者的任务上取得了79.8%的准确率、55.3%的灵敏度和83.7%的特异度；消融实验的结果显示了CCGCN模型各组成成分的有效性。结论 基于耦合的卷积-图卷积神经网络的疾病诊断模型利用了原始图像的结构和拓扑信息，相比现有方法可以提供更加精确的阿尔茨海默病诊断结果，有望将其应用于临床的辅助诊断中。

Abstract: Objective To propose a coupled convolutional and graph convolutional network (CCGCN) model for diagnosis of Alzheimer’s disease (AD) and its prodromal stage. Methods The disease-related brain regions generated by group-wise comparison were used as the input. The convolutional neural networks (CNNs) were used to extract disease-related features from different locations on brain magnetic resonance (MR) images. The generated features via the graph convolutional network (GCN) were processed, and graph pooling was performed to analyze the inherent relationship between the brain topology and the diagnosis task adaptively. Through ADNI dataset, we acquired the accuracy, sensitivity and specificity of the diagnosis tasks for AD and its prodromal stages, followed by an ablation study on the model structure. Results The CCGCN model outperformed the current state-of-the-art methods and showed a classification accuracy of 92.5% for AD with a sensitivity of 88.1% and a specificity of 96.0%. Conclusion Based on the structural and topological features of the brain MR images, the proposed CCGCN model shows excellent performance in AD diagnosis and is expected to provide important assistance to physicians in disease diagnosis.