This study aims to explore the diagnosis in patients with Alzheimer's disease (AD) based on magnetic resonance (MR) images, and to compare the differences of bilateral hippocampus in classification and recognition. MR images were obtained from 25 AD patients and 25 normal controls (NC) respectively. Three-dimensional texture features were extracted from bilateral hippocampus of each subject. The texture features that existed significant differences between AD and NC were used as the features in a classification procedure. Back propagation (BP) neural network model was built to classify AD patients from healthy controls. The classification accuracy of three methods, which were principal components analysis, linear discriminant analysis and non-linear discriminant analysis, was obtained and compared. The correlations between bilateral hippocampal texture parameters and Mini-Mental State Examination (MMSE) scores were calculated. The classification accuracy of nonlinear discriminant analysis with a neural network model was the highest, and the classification accuracy of right hippocampus was higher than that of the left. The bilateral hippocampal texture features were correlated to MMSE scores, and the relative of right hippocampus was higher than that of the left. The neural network model with three-dimensional texture features could recognize AD patients and NC, and right hippocampus might be more helpful to AD diagnosis.
In this paper, a new method for the classification of Alzheimer’s disease (AD) using multi-feature combination of structural magnetic resonance imaging is proposed. Firstly, hippocampal segmentation and cortical thickness and volume measurement were performed using FreeSurfer software. Then, histogram, gradient, length of gray level co-occurrence matrix and run-length matrix were used to extract the three-dimensional (3D) texture features of the hippocampus, and the parameters with significant differences between AD, MCI and NC groups were selected for correlation study with MMSE score. Finally, AD, MCI and NC are classified and identified by the extreme learning machine. The results show that texture features can provide better classification results than volume features on both left and right sides. The feature parameters with complementary texture, volume and cortical thickness had higher classification recognition rate, and the classification accuracy of the right side (100%) was higher than that of the left side (91.667%). The results showed that 3D texture analysis could reflect the pathological changes of hippocampal structures of AD and MCI patients, and combined with multi-feature analysis, it could better reflect the essential differences between AD and MCI cognitive impairment, which was more conducive to clinical differential diagnosis.