Built independently by an author, for readers. Read the story and support ChapterPal

keyword

deformable template

A deformable template is a flexible prototype model or reference image used in computer vision and medical image analysis that can undergo continuous spatial transformations to align with target shapes or patterns. Rather than requiring strict geometric invariance, this approach applies parameterized or smooth non-rigid coordinate mappings to a baseline representation to accommodate natural structural variability across different instances. The alignment is typically achieved through an optimization process that balances the degree of visual or structural similarity to the target data against the regularization cost of the deformation, ensuring that the resulting transformation remains smooth, realistic, and structurally consistent.

1 item

Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms

Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms

MIRZA FAISAL BEG, MICHAEL I. MILLER, ALAIN TROUVÉ, LAURENT YOUNES

OrganizationsENS Paris-SaclayJohns Hopkins UniversitySimon Fraser University

Why you should read this

Develops the algorithmic and mathematical foundation for large deformation diffeomorphic metric mapping by deriving Euler-Lagrange equations and implementing a semi-Lagrangian particle flow method to compute shortest-path geodesic transformations between anatomical images.

This paper examine the Euler-Lagrange equations for the solution of the large deformation diffeomorphic metric mapping problem studied in Dupuis et al. (1998) and Trouvé (1995) in which two images I0, I1 are given and connected via the diffeomorphic change of coordinates I0 ∘ φ−1 = I1 where φ = ϕ1 is the end point at t = 1 of curve ϕt, t ∈ [0, 1] satisfying ϕ̇t = vt(ϕt), t ∈ [0, 1] with ϕ0 = id. The variational problem takes the form argmin v:ϕ̇t=vt(ϕt) ( ∫0^1 ‖vt‖_V^2 dt + ‖I0 ∘ ϕ_1^−1 − I1‖_L^2^2 ), where ‖vt‖_V is an appropriate Sobolev norm on the velocity field vt(·), and the second term enforces matching of the images with ‖·‖_L^2 representing the squared-error norm. In this paper we derive the Euler-Lagrange equations characterizing the minimizing vector fields vt, t ∈ [0, 1] assuming sufficient smoothness of the norm to guarantee existence of solutions in the space of diffeomorphisms. We describe the implementation of the Euler equations using semi-Lagrangian method of computing particle flows and show the solutions for various examples. We also compute the metric distance on several anatomical configurations as measured by ∫0^1 ‖vt‖_V dt on the geodesic shortest paths.

Added

2026-09-18