So Jae-Hong, Madusanka Nuwan, Choi Heung-Kook, Choi Boo-Kyeong, Park Hyeon-Gyun
Department of Digital Anti-Aging Healthcare, u-AHRC, Inje University, Gimhae, Gyeongsangnam, Korea.
Department of Computer Engineering, u-AHRC, Inje University, Gimhae, Gyeongsangnam, Korea.
Curr Med Imaging Rev. 2019;15(7):689-698. doi: 10.2174/1573405615666190404163233.
We propose a classification method for Alzheimer's disease (AD) based on the texture of the hippocampus, which is the organ that is most affected by the onset of AD.
We obtained magnetic resonance images (MRIs) of Alzheimer's patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. This dataset consists of image data for AD, mild cognitive impairment (MCI), and normal controls (NCs), classified according to the cognitive condition. In this study, the research methods included image processing, texture analyses, and deep learning. Firstly, images were acquired for texture analyses, which were then re-spaced, registered, and cropped with Gabor filters applied to the resulting image data. In the texture analyses, we applied the 3-dimensional (3D) gray-level co-occurrence (GLCM) method to evaluate the textural features of the image, and used Fisher's coefficient to select the appropriate features for classification. In the last stage, we implemented a deep learning multi-layer perceptron (MLP) model, which we divided into three types, namely, AD-MCI, AD-NC, and MCI-NC.
We used this model to assess the accuracy of the proposed method. The classification accuracy of the proposed deep learning model was confirmed in the cases of AD-MCI (72.5%), ADNC (85%), and MCI-NC (75%). We also evaluated the results obtained using a confusion matrix, support vector machine (SVM), and K-nearest neighbor (KNN) classifier and analyzed the results to objectively verify our model. We obtained the highest accuracy of 85% in the AD-NC.
The proposed model was at least 6-19% more accurate than the SVM and KNN classifiers, respectively. Hence, this study confirms the validity and superiority of the proposed method, which can be used as a diagnostic tool for early Alzheimer's diagnosis.
我们提出了一种基于海马体纹理的阿尔茨海默病（AD）分类方法，海马体是受AD发病影响最大的器官。
我们从阿尔茨海默病神经影像倡议（ADNI）数据集中获取了AD患者的磁共振图像（MRI）。该数据集包含根据认知状况分类的AD、轻度认知障碍（MCI）和正常对照（NC）的图像数据。在本研究中，研究方法包括图像处理、纹理分析和深度学习。首先，采集图像进行纹理分析，然后对其进行重新采样、配准和裁剪，并将Gabor滤波器应用于所得图像数据。在纹理分析中，我们应用三维（3D）灰度共生矩阵（GLCM）方法来评估图像的纹理特征，并使用Fisher系数选择合适的特征进行分类。在最后阶段，我们实现了一个深度学习多层感知器（MLP）模型，我们将其分为三种类型，即AD-MCI、AD-NC和MCI-NC。
我们使用该模型评估所提出方法的准确性。所提出的深度学习模型在AD-MCI（72.5%）、AD-NC（85%）和MCI-NC（75%）的病例中分类准确率得到了证实。我们还使用混淆矩阵、支持向量机（SVM）和K近邻（KNN）分类器对所得结果进行了评估，并对结果进行了分析以客观验证我们的模型。我们在AD-NC中获得了85%的最高准确率。
所提出的模型分别比SVM和KNN分类器至少准确6%-19%。因此，本研究证实了所提出方法的有效性和优越性，该方法可作为早期阿尔茨海默病诊断的诊断工具。
