A new model for early diagnosis of alzheimer's disease based on BAT-SVM classifier

Abstract

Magnetic Resonance Images (MRI) of the Brain is a significant tool to diagnosis Alzheimer's disease due to its ability to measure regional changes in the brain that reflect disease progression to detect early stages of the disease. In this paper, we propose a new model that adopts Bat for parameter optimization problem of Support vector machine (SVM) to diagnose Alzheimer’s disease via MRI biomedical image. The proposed model uses MRI for biomedical image classification to diagnose three classes; normal controls (NC), mild cognitive impairment (MCI) and Alzheimer’s disease (AD). The proposed model based on segmentation for the most involved areas in the disease hippocampus, the features of MRI brain images are extracted to build feature vector of the brain, then extracting the most significant features in neuroimaging to reduce the high dimensional space of MRI images to lower dimensional subspace, and submitted to machine learning classification technique. Moreover, the model is applied on different datasets to validate the efficiency which show that the new Bat-SVM model can yield promising acceptable level of accuracy reached to 95.36 % using maximum number of bats equal to 50 and number of generation equal to 10.

Segmentation and classification techniques used to detect early stroke diagnosis using brain magnetic resonance imaging: a review

“…Challenges with clustering data of varying sizes and densities [44] Discriminant Method has an efficient method for feature extraction and dimension reduction [45] Assigns exact values to outcomes of various actions [45] It is restricted to one output attribute [45] SVM Analysis Model SVM Method is a best classifier for categorising two or more categories [46] Provides better accuracy compare to other classifier easily handle complex nonlinear data points and easily handle complex nonlinear data points [47] It is expensive [47] k-NN Analysis Model k-NN Method is a nonparametric learning set of a classification algorithm that categorises objects based on the closest pixel [48] It is easy to implement [48] Sensitive to noise and requires large storage space [48] Decision Tree Analysis Model Decision tree Method minimizes the ambiguity of complicated decisions [49] It handles both numerical and categorical data [49] It is an unstable classifier, for example performance of classifier is depend upon the type of dataset [49] The clustering technique is commonly used during the segmentation process. K-means is computationally faster than fuzzy c-means [50].…”

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

“…Also, a developed algorithm called "Support Vector Machine Leave-One-Out Recursive Feature Elimination and Cross-Validation" (SVM-RFE-LOO) for early detection of AD was proposed 15 . Moreover, several researchers also used SVM concerning the detection of AD [16][17][18][19][20][21][22][23][24] . For instance 25 , used Artificial Neural Network (ANN) with MRI images to perform prediction for the transition from mild cognitive impairment (MCI) to AD with an accuracy of 89.5%.…”

Alzheimer’s detection through neuro imaging and subsequent fusion for clinical diagnosis

“…An average of the three white and black pixel counts calculated are used to classify the brain scan under different stages of the disease as aforementioned. Taie and Ghonaim [7] described a new model for the early diagnosis of AD based on bat-support vector machine (SVM) classifier. Firstly, features of MRI brain images to build feature vector of brain are obtained.…”