Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo
This addresses the challenge of providing calibrated uncertainty estimates in medical image registration, which is important for clinical applications, though it appears incremental as it builds on existing frameworks.
The paper tackled the problem of probabilistic non-rigid registration of 3D medical images with uncertainty quantification, developing a Bayesian model that improved calibration of uncertainty estimates compared to the state-of-the-art VoxelMorph model.
We develop a new Bayesian model for non-rigid registration of three-dimensional medical images, with a focus on uncertainty quantification. Probabilistic registration of large images with calibrated uncertainty estimates is difficult for both computational and modelling reasons. To address the computational issues, we explore connections between the Markov chain Monte Carlo by backpropagation and the variational inference by backpropagation frameworks, in order to efficiently draw samples from the posterior distribution of transformation parameters. To address the modelling issues, we formulate a Bayesian model for image registration that overcomes the existing barriers when using a dense, high-dimensional, and diffeomorphic transformation parametrisation. This results in improved calibration of uncertainty estimates. We compare the model in terms of both image registration accuracy and uncertainty quantification to VoxelMorph, a state-of-the-art image registration model based on deep learning.