Medical Image Retrieval for Alzheimer’s Disease Using Data from Multiple Time Points

Abstract

This paper presents medical image retrieval for Alzheimer’s disease based on information extracted from multiple time points. The aim is to analyze the retrieval performance directed by the information combination of different time points and from each time point separately. For each subject, Magnetic Resonance Images (MRI) of four consecutive time points are obtained from ADNI database. Measurements of cortical and subcortical brain structures, including volumes and cortical thickness of the brain regions are used as features. The feature selection is performed aiming to select the most relevant features and reduce redundant and possibly noisy data.

The evaluation is based on ten scenarios defined for separate time points and for a combination of multiple time points. According to the obtained results, it can be concluded that the retrieval performance gets better while using the time point that is more temporally distant from the baseline, regarding the scenarios in which separate information at any time point is used. When using a combination of multiple time points, the retrieval performance is improved only in the case when more than two time points are available and the selected features from the last two points are used. Feature selection algorithm leads to better results in all cases, while significantly reduces the feature vector dimensionality. The selected features are known as significant markers for Alzheimer’s Disease.