Automatic Classification of Alzheimer's Disease using brain MRI data and deep Convolutional Neural Networks

TL;DR

This study evaluates deep learning architectures for classifying Alzheimer's disease using brain MRI data, demonstrating that image preprocessing and segmentation improve classification accuracy, with ResNet achieving up to 93.50%.

Contribution

It investigates the impact of image segmentation on deep learning classification of brain MRI for Alzheimer's detection, which is less explored in prior research.

Findings

Processed images improved classification accuracy.

ResNet achieved highest accuracy of 93.50%.

Segmentation positively influenced model performance.

Abstract

Alzheimer's disease (AD) is one of the most common public health issues the world is facing today. This disease has a high prevalence primarily in the elderly accompanying memory loss and cognitive decline. AD detection is a challenging task which many authors have developed numerous computerized automatic diagnosis systems utilizing neuroimaging and other clinical data. MRI scans provide high-intensity visible features, making these scans the most widely used brain imaging technique. In recent years deep learning has achieved leading success in medical image analysis. But a relatively little investigation has been done to apply deep learning techniques for the brain MRI classification. This paper explores the construction of several deep learning architectures evaluated on brain MRI images and segmented images. The idea behind segmented images investigates the influence of image segmentation step on deep learning classification. The image processing presented a pipeline consisting of pre-processing to enhance the MRI scans and post-processing consisting of a segmentation method for segmenting the brain tissues. The results show that the processed images achieved a better accuracy in the binary classification of AD vs. CN (Cognitively Normal) across four different architectures. ResNet architecture resulted in the highest prediction accuracy amongst the other architectures (90.83% for the original brain images and 93.50% for the processed images).