Landmark matching via large deformation diffeomorphisms
نویسندگان
چکیده
This paper describes the generation of large deformation diffeomorphisms phi:Omega=[0,1]3<-->Omega for landmark matching generated as solutions to the transport equation dphi(x,t)/dt=nu(phi(x,t),t),epsilon[0,1] and phi(x,0)=x, with the image map defined as phi(.,1) and therefore controlled via the velocity field nu(.,t),epsilon[0,1]. Imagery are assumed characterized via sets of landmarks {xn, yn, n=1, 2, ..., N}. The optimal diffeomorphic match is constructed to minimize a running smoothness cost parallelLnu parallel2 associated with a linear differential operator L on the velocity field generating the diffeomorphism while simultaneously minimizing the matching end point condition of the landmarks. Both inexact and exact landmark matching is studied here. Given noisy landmarks xn matched to yn measured with error covariances Sigman, then the matching problem is solved generating the optimal diffeomorphism phi;(x,1)=integral0(1)nu(phi(x,t),t)dt+x where nu(.)=argmin(nu.)integral1(0) integralOmega parallelLnu(x,t) parallel2dxdt +Sigman=1N[yn-phi(xn,1)] TSigman(-1)[yn-phi(xn,1)]. Conditions for the existence of solutions in the space of diffeomorphisms are established, with a gradient algorithm provided for generating the optimal flow solving the minimum problem. Results on matching two-dimensional (2-D) and three-dimensional (3-D) imagery are presented in the macaque monkey.
منابع مشابه
Large Deformation Registration via n-dimensional Quasi-conformal Maps
We propose a new method to obtain registration between n-dimensional manifolds with very large deformations. Given a set of landmark correspondences, our algorithm produces an optimal diffeomorphism that matches prescribed landmark constraints. The obtained registration is a n-dimensional quasi-conformal map. The basic idea of the model is to minimize an energy functional with a conformality te...
متن کاملExtension to BV functions of the large deformation diffeomorphisms matching approach
The image matching within the framework of large deformations via diffeomorphisms is extended to the space of bounded variation functions. Thanks to a semi-differentiation lemma, which is the central new result of this article, we derive the geodesic equations for a general penalty term and we describe the associated momentum. To cite this article: A. Nom1, A. Nom2, C. R. Acad. Sci. Paris, Ser....
متن کاملA Geometric Framework for Stochastic Shape Analysis
We introduce a stochastic model of diffeomorphisms, whose action on a variety of data types descends to stochastic models of shapes, images and landmarks. The stochasticity is introduced in the vector field which transports the data in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework for shape analysis and image registration. The stochasticity thereby models errors or uncert...
متن کاملRobust Diffeomorphic Mapping via Geodesically Controlled Active Shapes
This paper presents recent advances in the use of diffeomorphic active shapes which incorporate the conservation laws of large deformation diffeomorphic metric mapping. The equations of evolution satisfying the conservation law are geodesics under the diffeomorphism metric and therefore termed geodesically controlled diffeomorphic active shapes (GDAS). Our principal application in this paper is...
متن کاملGenus-One Surface Registration via Teichmüller Extremal Mapping
This paper presents a novel algorithm to obtain landmark-based genus-1 surface registration via a special class of quasi-conformal maps called the Teichmüller maps. Registering shapes with important features is an important process in medical imaging. However, it is challenging to obtain a unique and bijective genus-1surface matching that satisfies the prescribed landmark constraints. In additi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
دوره 9 8 شماره
صفحات -
تاریخ انتشار 2000