NANAJan 6, 2017

Langevin equations for landmark image registration with uncertainty

arXiv:1605.0927618 citationsh-index: 31
AI Analysis

For researchers in medical image analysis and shape modeling, this provides a principled way to quantify registration uncertainty, though the approach is incremental.

The paper addresses uncertainty in landmark-based image registration by formulating a Langevin equation to model small random perturbations. It introduces computationally efficient approximations and uses a Bayesian framework to compute posterior distributions and average multiple landmark sets.

Registration of images parameterised by landmarks provides a useful method of describing shape variations by computing the minimum-energy time-dependent deformation field that flows one landmark set to the other. This is sometimes known as the geodesic interpolating spline and can be solved via a Hamiltonian boundary-value problem to give a diffeomorphic registration between images. However, small changes in the positions of the landmarks can produce large changes in the resulting diffeomorphism. We formulate a Langevin equation for looking at small random perturbations of this registration. The Langevin equation and three computationally convenient approximations are introduced and used as prior distributions. A Bayesian framework is then used to compute a posterior distribution for the registration, and also to formulate an average of multiple sets of landmarks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes