Statistical-based deformable models with simultaneous optimization of object gray-level and shape characteristics

A statistical-based deformable model is being developed that improves upon existing point distribution models (PDM). Existing PDM boundary finding techniques often suffer from the following shortcomings: (1) global shape and gray-level information are treated independently during boundary optimization; (2) a priori local shape characteristics are not utilized; and (3) there is no existing metric that provides a confidence measure of segmentation performance. A new deformable model algorithm is under development in which the objective function used during optimization of the boundary encompasses several important characteristics. First the objective function includes both global shape and local gray-level characteristics, so optimization occurs with respect to both pieces of information simultaneously. In addition, local shape characteristics, as derived from the training set, are also incorporated into the boundary finding process. Finally, the objective function is formulated in a way that leads directly to a confidence metric that indicates how well the final boundary fits the underlying object as defined in the target image, This new algorithm is being applied to high-resolution X-ray computed tomography (CT) images of laboratory mice for the purposes of abdominal structure (primarily kidney) identification. Preliminary results are shown for mouse kidney and spine segmentation.