Intermodality 3D medical image registration with global search
Lawrence H. Staib, Xianzhang Lei · 2002
Describes a new registration method for three-dimensional medical images. It is important clinically to bring images from different modalities into alignment so that equivalent points can be identified. Often, functional images (showing metabolism or blood flow) are registered to structural images in order to more accurately interpret and quantify these images. This is especially important in areas of decreased function. This registration method determines the optimal transformation between the images using a match metric based on the distance transform of a structure visible in both modalities. The globally optimal transform is determined using a genetic optimization method and a hybrid technique using both genetic and gradient optimization. This provides a feasible way of determining the global solution making this method robust to local minima and insensitive to initial positioning.>