Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa; iThemba Laboratory for Accelerator Based Science, National Research Foundation, P. O. Box 722Somerset, West, South Africa
Matjelo, N.J., Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa; Nicolls, F., Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa; Muller, N., iThemba Laboratory for Accelerator Based Science, National Research Foundation, P. O. Box 722Somerset, West, South Africa
This paper presents an evaluation of an optimal control-based deformable image registration model and compares it to four well-known variational-based models, namely, elastic, fluid, diffusion and curvature models. Using similarity and deformation quality measures as performance indices, Non-dominated Sorting Genetic Algorithm (NSGA-II) is applied to approximate Pareto Fronts for each model to facilitate proper evaluation. The Pareto Fronts are also visualized using Level diagrams. © Springer International Publishing Switzerland 2015.