Samah Khawaled1 and Moti Freiman2
1Applied Mathematics, Technion, Haifa, Israel, 2Biomedical Engineering, Technion, Haifa, Israel
1Applied Mathematics, Technion, Haifa, Israel, 2Biomedical Engineering, Technion, Haifa, Israel
Bayesian deep learning models enable safer utilization in MRI, improve generalization and assess the uncertainty of the predictions. We propose a non-parametric Bayesian method to estimate the uncertainty in MRI registration and assess its correlation with the out-of-distribution data.
Fig. 1: Block diagram of
the proposed Bayesian registration system. μ and σ are the mean and standard deviation of the deformation.
Table 1: Registration evaluation results. The added noise
levels are denoted by σ and α, respectively. The mean and std, calculated over
the test set, are presented for three different anatomical structures (from top
to bottom: R inferior frontal gyrus, L precentral gyrus, L lateral
orbitofrontal gyrus).
