AUTOMATIC DETECTION OF THE MID-SAGITTAL PLANE IN 3-D BRAIN IMAGES

This article presents a detailed description of an algorithm for the a utomatic detection of the mid-sagittal plane in three-dimensional (3-D ) brain images. The algorithm seeks the plane with respect to which th e image exhibits maximum symmetry. For a given plane, symmetry is meas ured by the cross-correlation between the image sections lying on eith er side, The search for the plane of maximum symmetry is performed by using a multiresolution approach which substantially decreases computa tional time, The choice of the starting plane was found to be an impor tant issue in optimization, A method for selecting the initial plane i s presented, The algorithm has been tested on brain images from variou s imaging modalities in both humans and animals, Results were evaluate d by visual inspection by neuroradiologists and were judged to be cons istently correct.