Alzheimer Classifications Combining Machine Learning and Signal Processing
- 30 October 2025
- journal article
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 15 (1) , 18-29
Abstract
Manual detection of presence of Alzheimer even determination of its intensity from Magnetic Resonance Imaging (MRI) image is an easy task when a patient is heavily affected by the disease. The situation becomes cumbersome for a physician when a very mild affected image comes under consideration. For cases involving subtle differences in images, Machine Learning (ML) and Deep Learning (DL) classification are considered the best solutions. In this paper, Alzheimer-affected images of four categories —mild impairment, moderate impairment, very mild impairment, and no impairment — are taken from a benchmark open database. The image set is converted to a numerical feature vector using Speeded-Up Robust Features (SURF), Features from Accelerated Segment Test (FAST), Harris–Stephen’s, and minimum eigenvalue. The feature vector is then applied to several ML algorithms: Fuzzy Inference System (FIS), Multiple Linear Regression (MLR), Fuzzy C-Means (FCM), Naïve Bayes and linear Support Vector Machine (SVM) to check their eligibility in classifying these four types of medical images. The accuracy of detection from any individual method ranges from 56 percent to 68 percent. However, applying the maximum voting scheme to all the MLs yields an accuracy of 75 percent. The long feature vector is also extracted from the discrete wavelet transform (DWT), and classification is done from its coherence, but the accuracy is found to be very poor. Next, the image dataset is applied to the Bag of Features (BoF) algorithm using 500 visual words, yielding a moderate result with an accuracy of 84.28 percent. Finally, two deep learning models are applied: PyTorch Convolutional Neural Network (CNN) and Keras Visual Geometry Group (VGG) 19. These models are tested on 20 percent of the trained images, achieving accuracies of 95.7 percent and 97.1 percent, respectively.Keywords
This publication has 15 references indexed in Scilit:
- DeepCurvMRI: Deep Convolutional Curvelet Transform-Based MRI Approach for Early Detection of Alzheimer’s DiseaseIEEE Access, 2023
- An MRI-based deep learning approach for accurate detection of Alzheimer’s diseaseAlexandria Engineering Journal, 2022
- Automated Detection of Alzheimer’s Disease and Mild Cognitive Impairment Using Whole Brain MRIIEEE Access, 2022
- Resting State fMRI and Improved Deep Learning Algorithm for Earlier Detection of Alzheimer’s DiseaseIEEE Access, 2020
- Optimized One vs One Approach in Multiclass Classification for Early Alzheimer’s Disease and Mild Cognitive Impairment DiagnosisIEEE Access, 2020
- Alzheimer’s Diseases Detection by Using Deep Learning Algorithms: A Mini-ReviewIEEE Access, 2020
- Image Classification Based on Approximate Wavelet Transform and Transfer Learning on Deep Convolutional Neural Networks2020
- Ensembles of Patch-Based Classifiers for Diagnosis of Alzheimer DiseasesIEEE Access, 2019
- Relative Investigation of Machine Learning Algorithms for Performance Analysis on Brain MR ImagesProcedia Computer Science, 2018
- JPEG Compression Detection Based on Edge-Corner Features Using SVM2017