Complex relationships between structural changes using brain MR imaging in early diagnosis of Alzheimer´s Disease

This proposal helps to identify topics regions on brain MRI that can be associated with presence or

Accurate diagnosis of Alzheimer´s disease (AD) from structural Magnetic Resonance (MRI) images is difficult due to the complex alteration of patterns in brain anatomy that could indicate the presence or absence of the pathology. Currently, an effective approach that allows to interpret the disease in terms of global and local changes is not available in the clinical practice. We propose an approach for classification of brain MR images, based on finding pathology-related patterns through the identification of regional structural changes. This approach combines a probabilistic Latent Semantic Analysis technique, which allows to identify image regions through latent topics inferred from the brain MRI, with a bottom-up Graph-Based Visual Saliency model, which calculates maps of relevant information per region, obtaining a master saliency map of each brain MRI. The proposed approach includes a one-to-one comparison of the saliency maps which feeds a Support Vector Machine (SVM) classifier, to group test subjects into normal or probable AD subjects.