Detecting Asymmetries in Hippocampal Shape and Receptor Distribution using Statistical Appearance Models and Linear Discriminant Analysis

Neurological studies are often concerned with identifying abnormalities in brain structure affecting asymmetry between left and right hemispheres. This paper presents techniques which allow measurement and characterisation of differences between neuroanatomic structures due to variation in both shape and receptor distribution. This provides a potentially powerful tool for identifying subtle pathological asymmetries. We propose a combination of appearance modelling and linear discriminant analysis and present preliminary results of the technique applied to 2D hippocampal autoradiographs. We also describe experiments testing the relative performance of variants of our method to test assumptions about the nature of the analysis and the nature of the data.