2026-05-05T10:27:13Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/643372025-03-26T19:10:03Zcom_10324_1191com_10324_931com_10324_894col_10324_1379

00925njm 22002777a 4500 dc Menchon Lara, Rosa María author Royuela del Val, Javier author Simmross Wattenberg, Federico Jesús author Casaseca de la Higuera, Juan Pablo author Martín Fernández, Marcos Antonio author Alberola López, Carlos author 2021 Background and Objective:This paper proposes a new and highly efficient implementation of 3D+t groupwise registration based on the free-form deformation paradigm. Methods:Deformation is posed as a cascade of 1D convolutions, achieving great reduction in execution time for evaluation of transformations and gradients. Results:The proposed method has been applied to 4D cardiac MRI and 4D thoracic CT monomodal datasets. Results show an average runtime reduction above 90%, both in CPU and GPU executions, compared with the classical tensor product formulation. Conclusions:Our implementation, although fully developed for the metric sum of squared differences, can be extended to other metrics and its adaptation to multiresolution strategies is straightforward. Therefore, it can be extremely useful to speed up image registration procedures in different applications where high dimensional data are involved. Computer Methods and Programs in Biomedicine, March 2021, vol. 200 0169-2607 https://uvadoc.uva.es/handle/10324/64337 10.1016/j.cmpb.2020.105812 Fast 4D elastic group-wise image registration. Convolutional interpolation revisited