2009 IEEE International Conference on
Systems, Man, and Cybernetics |
![]() |
Abstract
The brain shape shows the regional specificity of deformation caused by cerebropathy and the degree of its progress. Therefore quantitative evaluation of the deformation using MR images is effective for the diagnosis of cerebropathy. The conventional methods normalize the brain shape by deforming the evaluating brain to the standardized brain. Because their methods do not take into account anatomical features such as the cerebral sulci and the gyri, in some cases the deformation results that one sulcus of the evaluating brain locates the other sulcus. This paper proposes a homologous brain shape modeling method for quantitative evaluation of the brain shape in MR images. We define a new image feature called sulcal-distribution index (SDI) to represent the 3-D distribution of sulci, and the proposed method deforms a brain model so that SDI of the deformed brain model is similar to SDI of the template brain model. The deformation is performed with elastic model. By using SDI, the proposed method can take into account anatomical features of the cerebral sulci and the gyri. The experimental results showed that the proposed method homologically models the brain with a mean displacement of 1.3 mm.