3D Supervoxel based features for early detection of AD: A microscopic view to the brain MRI.

Introduction: Alzheimer's disease (AD) is a chronic form of the neurodegenerative disease marked by atrophy in different brain regions. A region-wise analysis is essential for performing AD detection, as each brain region has different functionalities depending on its location. This work aims to investigate supervoxel based volumetric features in place of traditional voxel-based features from the vital brain regions. Methods: In this work, the whole brain structural magnetic resonance imaging (MRI) is segmented into 116 regions using atlas-based segmentation. Important atrophic regions are used for further analysis based on a region ranking procedure from these segmented regions. The focus of this study is to perform supervoxel based partitioning for attaining features prominent for AD detection. Volumetric features are extracted from supervoxels belonging to the selected regions. An optimal feature set is obtained by using the support vector machine recursive elimination (SVM-RFE) method, and classification is performed using SVM. Results: ADNI dataset is used for experimentation. Results are obtained by iteratively fusing the features extracted from vital brain regions. The highest classification accuracy of 90.11%, the sensitivity of 86.11%, and the specificity of 93.4% are obtained by fusing features extracted from hippocampus and amygdala regions. Discussion: The highest classification accuracy reported in this work for AD detection is obtained by fusing features of the four most important regions, i.e., hippocampus and amygdala, in both left and right hemispheres. These regions are also known to affect the consolidation of memory and decision-making in medical science. Experimental results evaluated on the standard dataset depict that the proposed method performs better than the traditional as well as state-of-the-art methods. [ABSTRACT FROM AUTHOR]