RT info:eu-repo/semantics/article
T1 Efficient convolution-based pairwise elastic image registration on three multimodal similarity metrics
A1 Menchón Lara, Rosa María
A1 Simmross Wattenberg, Federico Jesús
A1 Rodríguez Cayetano, Manuel
A1 Casaseca de la Higuera, Juan Pablo
A1 Martín Fernández, Miguel Angel
A1 Alberola López, Carlos
K1 Multimodal registration
K1 Registro multimodal
K1 Convolution
K1 Convolución
K1 Non-rigid registration
K1 Registro no rígido
K1 3325 Tecnología de las Telecomunicaciones
AB This paper proposes a complete convolutional formulation for 2D multimodal pairwise image registration problems based on free-form deformations. We have reformulated in terms of discrete 1D convolutions the evaluation of spatial transformations, the regularization term, and their gradients for three different multimodal registration metrics, namely, normalized cross correlation, mutual information, and normalized mutual information. A sufficient condition on the metric gradient is provided for further extension to other metrics. The proposed approach has been tested, as a proof of concept, on contrast-enhanced first-pass perfusion cardiac magnetic resonance images. Execution times have been compared with the corresponding execution times of the classical tensor product formulation, both on CPU and GPU. The speed-up achieved by using convolutions instead of tensor products depends on the image size and the number of control points considered, the larger those magnitudes, the greater the execution time reduction. Furthermore, the speed-up will be more significant when gradient operations constitute the major bottleneck in the optimization process.
PB Elsevier
SN 0165-1684
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/55594
UL https://uvadoc.uva.es/handle/10324/55594
LA eng
NO Signal Processing, 2023, vol. 202, 108771
NO Producción Científica
DS UVaDOC
RD 23-nov-2024