Disease classification with hippocampal shape invariants

We present an Alzheimer's detection study based on a global shape description of hippocampal surface models. With global descriptors forming our bag of features, Support Vector Machine classification of 49 Alzheimer (AD) and 63 elderly control subjects yielded 75.5% sensitivity and 87.3% specificity with 82.1% correct overall in a leave-one-out test. We show that our description contributes new information to simpler shape measures. Armed with a rigid shape registration tool, we also present a way to visualize variation in global shape description as a local displacement map, thus clarifying the descriptors' anatomical meaning.