Staib and Duncan : Model - Based Deformable Surface Finding

|This paper describes a new global shape param-etrization for smoothly deformable three-dimensional (3D) objects, such as those found in biomedical images, whose diversity and irregularity make them diicult to represent in terms of xed features or parts. This representation is used for geometric surface matching to 3D medical image data, such as from magnetic resonance imaging (MRI). The parametrization decomposes the surface into sinusoidal basis functions. Four types of surfaces are modeled: tori, open surfaces, closed surfaces and tubes. This parametrization allows a wide variety of smooth surfaces to be described with a small number of parameters. Extrinsic model-based information is incorporated by introducing prior probabilities on the parameters. Surface nding is formulated as an optimization problem. Results of the method applied to synthetic images and 3D medical images of the heart and brain are presented.