000003350 001__ 3350 000003350 005__ 20190219081243.0 000003350 037__ $$aINPRO--2009-080 000003350 041__ $$aeng 000003350 100__ $$aHernández, Mónica 000003350 245__ $$aGauss Newton optimization in diffeomorphic registration 000003350 260__ $$c2008-06-13 000003350 300__ $$amult. p 000003350 520__ $$aIn this article, we propose a numerical implementation of Gauss-Newton's method for optimization in diffeomorphic registration in the Large Deformation Diffeomorphi c Metric Mapping framework. The computations of the G\^ateaux derivatives of the o bjective function are performed in the tangent space of the Riemannian manifold of diffeo morphisms. The resulting algorithm has been compared to gradient descent optimization in br ain MRI anatomical images. The experiments have shown similar accuracy for both tech niques at steady-state while Gauss-Newton has resulted to be more robust with a faster rate of convergence. 000003350 540__ $$9info:eu-repo/semantics/openAccess$$aEsta obra está sujeta a una licencia de uso Creative Commons. Se permite la reproducción total o parcial, la distribución, la comunicación pública de la obra y la creación de obras derivadas, siempre que no sea con finalidades comerciales, y sempre que se reconzca la autoria de la obra original.$$uhttps://creativecommons.org/licenses/by-nc/4.0/ 000003350 6531_ $$adiffeomorphic registration 000003350 6531_ $$agauss-newton 000003350 6531_ $$ahilbert spaces 000003350 6531_ $$aoptimization methods 000003350 700__ $$aOlmos Gassó, Salvador 000003350 8560_ $$fmhg@unizar.es 000003350 8564_ $$s217455$$uhttps://zaguan.unizar.es/record/3350/files/INPRO--2009-080.pdf$$zArchivo asociado 000003350 9102_ $$aCiencia de la computación e inteligencia artificial$$bInformática e Ingeniería de Sistemas 000003350 980__ $$aPREPRINT