Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation

By John Ashburner, Karl J. Friston. NeuroImage, 2011

519 citations recorded by the source corpus.

This paper presents a nonlinear image registration algorithm based on the setting of Large Deformation Diffeomorphic Metric Mapping (LDDMM), but with a more efficient optimisation scheme — both in terms of memory required and the number of iterations required to reach convergence. Rather than perform a variational optimisation on a series of velocity fields, the algorithm is formulated to use a geodesic shooting procedure, so that only an initial velocity is estimated. A Gauss–Newton optimisation strategy is used to achieve faster convergence. The algorithm was evaluated using freely available manually labelled datasets, and found to compare favourably with other inter-subject registration algorithms evaluated using the same data.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/74b24b4ebb7473828c0181c284137688e5b09e1e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Brain templates and atlases (2012, methodology): “…and, by association, functional variability across a population, using elegant closed-form mathematical models for shape analysis (Ashburner, 2007, Ashburner and Friston, 2005, 2009, 2011, Ashburner and Klöppel, 2010; Auzias et al., 2011; Beg et al., 2005; Christensen et al., 1997; Chung et al.,…”
Lead-DBS v2: Towards a comprehensive pipeline for deep brain stimulation imaging (2018, unknown): “SPM DARTEL & SHOOT These two methods were originally designed to perform group-wise registrations (e.g. in context of a typical fMRI group study; Ashburner, 2007; Ashburner and Friston, 2011).”
Deformable Medical Image Registration: A Survey (2013, methodology): “The Gauss-Newton optimizer has been used in [81, 236, 245].”
CAT: a computational anatomy toolbox for the analysis of structural MRI data (2024, methodology): “CAT uses a sophisticated shooting a ppr oac h [ 24 ], together with an av er a ge template created from the IXI dataset [ 32 ].”
PRoNTo: Pattern Recognition for Neuroimaging Toolbox (2013, methodology): “Registration involved estimating initial velocities, from which the deformations were computed by a geodesic shooting procedure (Ashburner and Friston, 2011).”
Quicksilver: Fast Predictive Image Registration – a Deep Learning Approach (2017, methodology): “For example, Ashburner and Friston [6] use a Gauss–Newton method to accelerate convergence for LDDMM and Zhang et al. [7] propose a ﬁnite-dimensional approximation of LDDMM, achieving a roughly 25 speed-up over a standard LDDMM optimization-based solution.”
CAT – A Computational Anatomy Toolbox for the Analysis of Structural MRI Data (2023, unknown): “● Spatial Registration: DARTEL (Ashburner, 2007) or Geodesic Shooting (Ashburner and Friston, 2011) are used to register the individual tissue segments to standardized templates in the ICBM 2009c Nonlinear Asymmetric space ( MNI152NLin2009cAsym ; https://www.bic.mni.mcgill.ca/ServicesAtlases/ICBM152”