Abstrait

Classification of alzheimer's disease subjects from MRI using fuzzy neural network with feature extraction using discrete wavelet transform

Geetha C, Pugazhenthi D

Alzheimer's Disease (AD) is a kind of dementia which is tricky to diagnose in accordance with clinical observations. Detection of Alzheimer’s diseases over brain Magnetic Resonance Imaging (MRI) data is main concern in the neurosciences. Traditional assessment of functional image scans typically relies on manual reorientation, visual reading and semi quantitative investigation of certain sections of the brain. Here, proposed Fuzzy Neural Network (FNN) scheme for the purpose of automated multiclass diagnosis of Dementia, in accordance with classification of MRI of human brain. During the initial stage of the work pre-processing is done to get rid of noises. The pre-processing and enhancement scheme includes two steps; initially the removal of film artifacts, for instance, labels and X-ray marks are eliminated from the MRI by means of tracking algorithm. Then, the elimination of high frequency elements by means of Ant Colony based Optimization (ACO) scheme. 2D histogram signal is obtained from preprocessed MR images of brain and subsequently further feature extraction is done through Discrete Wavelet Transform (DWT). This makes use of first few DWT coefficients as features and utilized for the purpose of classification by means of FNN. The features consequently derived are employed for the purpose of training a Fuzzy Neural Network (FNN) to classify features into three classes like Alzheimer’s, Mild Alzheimer's and Huntington's disease. The experimental result shows that the proposed method classification accuracy performance is better than other classification approaches.