AutoEncoder-based feature ranking for Alzheimer Disease classification using PET image

Abstract

This paper presents a method of ranking the effectiveness of brain region of interest (ROI) in order to separate Normal Control (NC) from Alzheimer’s disease (AD) brains Positron Emission Tomography (PET) images based on AutoEncoder (AE) networks. Firstly, PET brains are mapped into ROIs using an anatomical atlas. Then, multiple AE models are trained and fine-tuned with softmax. After that, the connection weights learned from AEs are used to rank ROIs according to the total contribution of ROIs to the networks. We proposed a 2-phase feature ranking method which is able to significantly improve the ranking results. Lastly, the top-ranked ROIs are then input into a support vector machine (SVM) classifier. In experiments on ADNI dataset, the proposed method significantly improves the accuracy of the classifier when compared to other popular feature ranking methods such as: Fisher score, T-score, Conditional Mutual Information Maximization (CMIM), and Lasso. Our result shows that simple single-hidden-layer AE models can be used effectively to perform the feature ranking task. The proposed method could be easily applied to any image dataset where a feature selection is needed.