Brain Midline Approximation to Improve Symmetry Analysis of Brain CT Scans

Analysis of the symmetry of the brain hemispheres at the level of individual structures and dominant tissue features has been the subject of research for many years in the context of improving the effectiveness of imaging methods for the diagnosis of brain tumor, stroke, and Alzheimer's disease, among others. One useful approach is to reliably determine the midline of the brain, which allows comparative analysis of the hemispheres and uncovers information on symmetry/asymmetry in the relevant planes of, for example, CT scans. Therefore, an effective method that is robust to various geometric deformations, artifacts, varying noise characteristics, and natural anatomical variability is sought. This paper presents a novel method of estimating the midline of the brain. It is based on a comprehensive analysis of brain volume in two main steps. First, the images are reoriented. Using the matched ellipse, a head mask model is determined, the parameters of which are used to estimate the shape of the skull. Based on this, a precisely localized center line of the brain is created using 2D cross-correlation calculated on the edge images of successive scans. The algorithm developed has been validated, and the results obtained are competitive with the best reported achievements. The main advantages of the described method are high resistance to head tilt, simplicity of implementation, and high efficiency. The method can be used in a wide range of applications to support medical imaging diagnostics. The results obtained showed a 92.9% success rate and a mean error equal to 1.2 mm.