An Efficient Computer System for Alzheimer Diseases Classification Using Fast Finite Shearlet Transform Domain and Support Vector Machine Classifier

Abstract

Alzheimer’s disease (AD) is the most common cause of neurodegenerative dementia in the elderly population. Several researchers have developed numerous methods for AD stage classification based on machine learning and deep learning over the last few decades. In this field, the main challenge is to design an algorithm that enables the acquisition of a good classification with better performance to achieve a certain diagnosis. Furthermore, capturing the brain atrophy information spatially distributed in magnetic resonance imaging (MRI) to distinguish between Alzheimer’s disease stages is a challenging task. In this work, we proposed a method for AD disease stage classification to classify four categories: three phases of AD compared to non-demented cases using the Fast Finite Shearlet Transform (FFST), the gray level co-occurrence matrix (GLCM), and the SVM algorithm classifier. Our proposed method is established on a set of 400 MRI images and investigates the impact of the diverse directions of the FFST on the classification results. The proposed algorithm obtained good performance compared to the state of the art and shows that the use of the shearlet domain improve the classification accuracy which led to better detection.