Global Optimization of Deformable Surface Meshes Based on Genetic Algorithms

Deformable models are by their formulation able to solve surface extraction problem from noisy volumetric image data encountered commonly in medical image analysis. However, this ability is shadowed by the fact that the minimization problem formulated is difficult to solve globally. Constrained global solutions are needed, if the amount of noise is substantial. This paper presents a new optimization strategy for deformable surface meshes based on real coded genetic algorithms. Real coded genetic algorithms are favored over binary coded ones because they can more efficiently be adapted to the particular problem domain. The experiments with synthetic images are performed. These demonstrate that the applied deformable model is able extract a surface from a noisy volumetric image. Also superiority of the proposed approach compared to a greedy minimization with multiple initializations is demonstrated.