Intensity-based image registration using scatter search.

Objective: We present a novel intensity-based algorithm for medical image registration (IR).

Methods And Materials: The IR problem is formulated as a continuous optimization task, and our work focuses on the development of the optimization component. Our method is designed over an advanced scatter search template, and it uses a combination of restart and dynamic boundary mechanisms integrated within a multi-resolution strategy.

Results: The experimental validation is performed over two datasets of human brain magnetic resonance imaging. The algorithm is evaluated in both a stand-alone registration application and an atlas-based segmentation process targeted to the deep brain structures, considering a total of 16 and 18 scenarios, respectively. Five established IR techniques, both feature- and intensity-based, are considered for comparison purposes, and ground-truth data is used to quantitatively assess the quality of the results. Our approach ranked first in both studies and it is able to outperform all competitors in 12 of 16 registration scenarios and in 14 of 18 registration-based segmentation tasks. A statistical analysis confirms with high confidence (p<0.014) the accuracy and applicability of our method.

Conclusions: With a proper, problem-specific design, scatter search is able to provide a robust, global optimization. The accuracy and reliability of the registration process are superior to those of classic gradient-based techniques.