Alzheimer’s Disease Classification in Brain MRI using Modified kNN Algorithm

Alzheimer’s Disease (AD) is a neuro degenerative disease that is usually observed in elderly people which ultimately leads to the death of the patient. As no proper treatment exists for this chronic disease, early detection and treatment may reduce the effects of AD. In this paper, a method of detection and classification of AD from Brain MR images using various image processing techniques, feature extraction techniques and machine learning classifiers is proposed. A classification algorithm is modelled from the traditional k-Nearest Neighbour classification algorithm to increase the accuracy of classification and performance of the proposed method. The experiments are carried out with the MR images collected from OASIS database it is observed that the classification accuracy of the proposed model is 93.18% with good specificity and sensitivity.