TY - JOUR AU - Demirhan, Ayşe PY - 2016/12/26 Y2 - 2024/03/28 TI - Classification of Structural MRI for Detecting Alzheimer’s Disease JF - International Journal of Intelligent Systems and Applications in Engineering JA - Int J Intell Syst Appl Eng VL - IS - SE - Research Article DO - 10.18201/ijisae.2016Special Issue-146973 UR - https://ijisae.org/index.php/IJISAE/article/view/959 SP - 195-198 AB - <span>Alzheimer’s Disease (AD) is a pathological form of dementia that degenerates brain structures. AD affects millions of elderly people over the world and the number of people with AD doubles every year. Detecting AD years before the effects of disease using structural magnetic resonance imaging (MRI) of the brain is possible. Neuroimaging features that are extracted from the structural brain MRI can be used to predict AD by revealing disease related patterns. Machine learning techniques can detect AD and predict conversions from mild cognitive impairment (MCI) to AD automatically and successfully by using these neuroimaging features. In this study common structural brain measures such as volumes and thickness of anatomical structures that are obtained from The Open Access Series of Imaging Studies (OASIS) and made publicly available by https://www.nmr.mgh.harvard.edu/lab/mripredict are analysed. State-of-the-art machine learning techniques, namely support vector machines (SVM), k-nearest neighbour (kNN) algorithm and backpropagation neural network (BP-NN) are employed to discriminate AD and mild AD from healthy controls. Training hyperparameters of the classifiers are tuned using classification accuracy which is obtained with 5-fold cross validation. Prediction performance of the techniques are compared using accuracy, sensitivity and specificity. Results of the system revealed that AD can be distinguished from the healthy controls successfully using multivariate morphological features and machine learning tools. According to the performed experiments SVM is the most successful classifier for detecting AD with classification accuracies up to 82%.</span> ER -