부산대학교 도서관

This paper describes a technique for automating the measurement of brain width and angle at the level of the bi-parietal diameter, by processing an axial computed tomography (CT) brain scan image. The development of this algorithm derives from the wish to normalise patient data according to skull size and shape, for the purpose of comparing new patient data with that from past cases. This algorithm uses image processing techniques to find the inner edge of the cavity of the skull. The width and length of the brain are measured as inner dimensions of this bone periphery. The main challenges facing this work are the structural symmetry of the brain and the angle of rotation commonly encountered when working with axial CT images. Both of these must be takes into account prior to measuring the brain width and length. The algorithm was designed and tested to operate on a database containing CT brain scans from 530 patients. The results indicate that the algorithm has a 90.56% success rate.