Bayesian optimization for fitting 3D morphable models of brain structures

Localize target areas in deep brain stimulation is a difficult task, due to the shape variability that brain structures exhibit between patients. The main problem in this process is that the fitting procedure is carried out by a registration method that lacks of accuracy. In this paper we proposed a novel method for 3D brain structure fitting based on Bayesian optimization. We use a morphable model in order to capture the shape variability in a given set of brain structures. Then from the trained model, we perform a Bayesian optimization task with the aim to find the best shape parameters that deform the trained model, and fits accurately to a given brain structure. The experimental results show that by using an optimization framework based on Bayesian optimization, the model performs an accurate fitting over cortical brain structures (thalamus, amygdala and ventricle) in comparison with common fitting methods, such as iterative closest point.