Age prediction based on brain MRI images using feature learning

Abstract

Magnetic Resonance Imaging (MRI) is a means which is used to form cross-sectional pictures of internal organs using strong magnetic fields, radio waves, and field gradient. Previously some researches tried to predict the age of humans based on face images, DNA, medical images, speech signals, etc. In this paper, a method is proposed to predict the age of humans based on their MRI image. The main challenge here is that the images look very similar and classification would have difficulties because of very small interclass changes. Two feature extraction methods are used, one is based on a single layer Neural Network (NN), and the other is based on the Complex Networks. Finally, Support Vector Machine (SVM) is used for the classification task. The results of experiments on Oasis database show that the proposed method has acceptable performance.