Automatic Correction of the 3D Orientation of the Brain Imagery

Classification of human brain pathologies can be guided by the estimation of the departure of 3D internal structures from the normal bilateral symmetry. However symmetry based analysis can´t be precisely carried out when the 3D brain orientation is misaligned, a common occurrence in clinical practice. In this paper, a technique to automatically identify the symmetry plane and correct the 3D orientation of volumetric brain images in a cost effective way is developed. The algorithm seeks the best sampling strategies to realign 3D volumetric representation of the brain within scanner coordinate system. The inertia matrix is computed on the sampled brain, and the principle axes are derived from the eigenvectors of the inertia matrix. The technique is demonstrated on MR and CT brain images and the detected symmetry plane that is orthogonal to the principle vectors is provided. A spatial affine transform is applied to rotate the 3D brain images and align them within the coordinate system of the scanner. The corrected brain volume is re-sliced such that each planar image represents the brain at the same axial level.