IEEE/ACM Trans Comput Biol Bioinform. 2018 Mar-Apr;15(2):624-632. doi: 10.1109/TCBB.2016.2635144. Epub 2016 Dec 2.
Regions of interest (ROIs) based classification has been widely investigated for analysis of brain magnetic resonance imaging (MRI) images to assist the diagnosis of Alzheimer's disease (AD) including its early warning and developing stages, e.g., mild cognitive impairment (MCI) including MCI converted to AD (MCIc) and MCI not converted to AD (MCInc). Since an ROI representation of brain structures is obtained either by pre-definition or by adaptive parcellation, the corresponding ROI in different brains can be measured. However, due to noise and small sample size of MRI images, representations generated from single or multiple ROIs may not be sufficient to reveal the underlying anatomical differences between the groups of disease-affected patients and health controls (HC). In this paper, we employ a whole brain hierarchical network (WBHN) to represent each subject. The whole brain of each subject is divided into 90, 54, 14, and 1 regions based on Automated Anatomical Labeling (AAL) atlas. The connectivity between each pair of regions is computed in terms of Pearson's correlation coefficient and used as classification feature. Then, to reduce the dimensionality of features, we select the features with higher scores. Finally, we use multiple kernel boosting (MKBoost) algorithm to perform the classification. Our proposed method is evaluated on MRI images of 710 subjects (200 AD, 120 MCIc, 160 MCInc, and 230 HC) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our proposed method achieves an accuracy of 94.65 percent and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.954 for AD/HC classification, an accuracy of 89.63 percent and an AUC of 0.907 for AD/MCI classification, an accuracy of 85.79 percent and an AUC of 0.826 for MCI/HC classification, and an accuracy of 72.08 percent and an AUC of 0.716 for MCIc/MCInc classification, respectively. Our results demonstrate that our proposed method is efficient and promising for clinical applications for the diagnosis of AD via MRI images.
基于感兴趣区域（ROI）的分类已被广泛研究，用于分析脑磁共振成像（MRI）图像，以辅助阿尔茨海默病（AD）的诊断，包括其早期预警和发展阶段，例如轻度认知障碍（MCI），包括转化为 AD 的 MCI（MCIc）和未转化为 AD 的 MCI（MCInc）。由于 ROI 对脑结构的表示是通过预定义或自适应分割获得的，因此可以测量不同大脑中的相应 ROI。然而，由于 MRI 图像的噪声和小样本量，来自单个或多个 ROI 的表示可能不足以揭示疾病患者组和健康对照组（HC）之间的潜在解剖差异。在本文中，我们采用全脑层次网络（WBHN）来表示每个主体。基于自动解剖标记（AAL）图谱，将每个主体的整个大脑分为 90、54、14 和 1 个区域。计算每对区域之间的连接，以 Pearson 相关系数表示，并用作分类特征。然后，为了降低特征的维数，我们选择得分较高的特征。最后，我们使用多核提升（MKBoost）算法进行分类。我们的方法在来自阿尔茨海默病神经影像倡议（ADNI）数据库的 710 名受试者（200 名 AD、120 名 MCIc、160 名 MCInc 和 230 名 HC）的 MRI 图像上进行了评估。实验结果表明，我们的方法在 AD/HC 分类中达到了 94.65%的准确率和 0.954 的接收器操作特征（ROC）曲线下面积（AUC），在 AD/MCI 分类中达到了 89.63%的准确率和 0.907 的 AUC，在 MCI/HC 分类中达到了 85.79%的准确率和 0.826 的 AUC，在 MCIc/MCInc 分类中达到了 72.08%的准确率和 0.716 的 AUC。我们的结果表明，我们的方法对于通过 MRI 图像诊断 AD 的临床应用是高效且有前景的。
