Diffusion Tensor Imaging retrieval for Alzheimer's disease diagnosis

Abstract

Content-Based Visual Information Retrieval (CBVIR) methods applieds to Magnetic Resonance Imaging (MRI) are penetrating the universe of IT tools for clinical decision support. A clinician can take profit from retrieving subjects' scans with similar patterns. The CBVIR approach has been used since recently for Alzheimer's disease (AD) diagnosis. The most explored imaging modality in this context is the structural MRI. The Diffusion Tensor Imaging (DTI) is a relatively recent technique and CBVIR approaches have not yet been developed on it. The combination of several MRI modalities improves the performances of CBVIR methods, but first of all it is necessary to explore the ability of DTI modality to give a correct answer alone. The present work is amongst the earliest attempts to use visual features as in a generic CBVIR, on this modality for AD research. The proposed approach is based on the comparison of visual features extracted from the hippocampal area. We use the Circular Harmonic Functions (CHFs) to describe the content of the Diffusion Tensor-derived map: Mean Diffusivity (MD). This study was first accomplished with a subset of participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and then with the DTI scans of a French epidemiological study: “Bordeaux-3City”. The obtained results are encouraging and open interesting perspectives.