Discrimination between Alzheimer's disease and control group in MR-images based on texture analysis using Artificial Neural Network

In this study, we have proposed a novel method investigates MR-Images for normal and abnormal brains which effected by Alzheimer's Disease (AD) to extract 336 number of different features based on texture analysis. Before applying this algorithm, we have to use a registration method because of variety in size of normal and abnormal images. Consequently, the output of Texture Analysis System (TAS) is a vector containing 336 elements that are features extracted from texture. This vector is considered as the input of the Artificial Neural Network (ANN) which is feed-forward one. The features extracted from the Gray-level Co-occurrence Matrix (GLCM) have been interpreted and compared with normal brains to make the final decision. Decision making is the role of feed-forward ANN. Before using ANN, we have applied Principle Component Analysis (PCA) to eliminate any redundancies in features i.e. input vector. The results show a powerful diagnosis of AD with 95 percent proper response. Dataset includes 75 MR-images: 50 images show normal brains and rest of them is affected by AD. We used 60 percent of every group for training and 40 percent were considered as a "test data".