Rita Lopes Simoes

TL;DR: This work proposes an automatic lesion segmentation method that uses only three-dimensional fluid-attenuation inversion recovery (FLAIR) images and uses a modified context-sensitive Gaussian mixture model to determine voxel class probabilities, followed by correction of FLAIR artifacts.

TL;DR: The method is able not only to perform accurate classification, but also to localize dis-criminative brain regions, which are in accordance with the medical literature, indicating that the method may be suitable for a clinical implementation that can help to diagnose AD at an earlier stage.

TL;DR: This work proposes the use of local statistical texture maps that make no assumptions regarding the location of the affected brain regions and obtained an accuracy of 87% (sensitivity 85%, specificity 95%) with Support Vector Machines, outperforming the 63% achieved by the local gray matter density feature.

TL;DR: This paper presents an unsupervised 3D change detection method based on Change Vector Analysis that is able to detect and discriminate both small changes and ventricle expansions in datasets from Mild Cognitive Impairment patients.

TL;DR: Using an ensemble of local patches over the entire brain, the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer’s disease is proposed.