Symmetry recognition using Mid-sagittal Plane extraction and tilt correction in 3D head images

We propose a new method to automatically extract the Mid-sagittal Plane and re-alignment of 3D head image within the scanner coordinate system by tilt correction. We express the problem of Mid-sagittal Plane extraction as a registration problem and compute a degree of similarity between the image and its reflection with respect to a plane. The best plane is then obtained by maximizing the similarity measure. This optimization is performed using the Genetic Algorithm and Powell method. The search for the best plane is implemented in a multi-resolution paradigm so as to decrease computational time. Spatial rigid transform and Tri-linear interpolation then are performed to rotate the 3D head images to achieve tilt correction. The proposed algorithm is successfully tested on 3D PET and CT head images.