Alzheimer Disease MRI Preprocessed Images: A Machine Intelligent Based Approach for Classification and Analysis

Abstract

Purpose: Alzheimer’s disease (AD) is considered as one of the most dangerous diseases in the present scenario. It is a brain disorder disease which leads to the destruction of the thinking skills and memory of human beings. It is very much essential for the early classification of AD magnetic resonance imaging (MRI) preprocessed images (ADMPIs) into several categories such as Mild_Demented (MID), Moderate_Demented (MOD), Non_Demented (ND), Very_Mild_Demented (VMD), etc. so that preventive measures can be taken at the earliest.

Approach: In this work, a machine intelligent (MI) based approach is proposed for the classification of ADMPIs into the MID, MOD, ND and VMD types. This approach is focused on machine learning (ML) based methods such as Logistic Regression (LRG), Support Vector Machine (SVMN), Random Forest (RFS), Neural Network (NNT), Decision Tree (DTR), AdaBoost (ADB), Naïve Bayes (NBY), K-Nearest Neighbor (KNNH) and Stochastic Gradient Descent (SGDC) to carry out such classification.

Result: The ML based methods have been implemented using Python based Orange 3.26.0. In this work, 1564 ADMPIs having 500, 64, 500 and 500 numbers of each type such as MID, MOD, ND and VMD respectively are taken from the Kaggle source. The performance of all the methods is assessed using the performance parameters such as classification accuracy (CA), F1, Precision (PR) and Recall (RC). From the results, it is found that the NNT method is capable of providing better classification results in terms of CA, F1, PR and RC as compared to other ML based methods such as SVMN, RFS, NNT, DTR, ADB, NBY, KNNH and SGD.   

Originality: In this work, a MI based approach is proposed to carry out the classification of ADMPIs into several types such as MID, MOD, ND and VMD types. The NNT method performs better in terms of CA, F1, PR and RC as compared to LRG, SVMN, RFS, DTR, ADB, NBY, KNNH and SGDC methods.  

Paper Type: Conceptual Research.