# Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach Source: [Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:50:35.784Z Authors: Xiao Yang, Roland Kwitt, Martin Styner, Marc Niethammer Published: 2017-03-31T14:13:55.000Z ## Abstract This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during the testing time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. We show experimental results for uni-modal atlas-to-image as well as uni- / multi- modal image-to-image registrations. These experiments demonstrate that our method accurately predicts registrations obtained by numerical optimization, is very fast, achieves state-of-the-art registration results on four standard validation datasets, and can jointly learn an image similarity measure. Quicksilver is freely available as an open-source software. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Registration on LPBA40 (test)](): Image Registration; LPBA40 (test); FLIRT Error: 0.102. - [Image Registration on IBSR18 (test)](): Image Registration; IBSR18 (test); FLIRT Error: 0.118. - [Image Registration on CUMC12 (test)](): Image Registration; CUMC12 (test); FLIRT Error: 0.12. - [Image Registration on MGH10 (test)](): Image Registration; MGH10 (test); FLIRT: 0.091. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()