A framework for predictive modeling of anatomical deformations

A framework for modeling and predicting anatomical deformations is presente d, and tested on simulated images. Although a variety of deformations can b e modeled in this framework, emphasis is placed on surgical planning, and p articularly on modeling and predicting changes of anatomy between preoperat ive and intraoperative positions, as well as on deformations induced by tum or growth. Two methods are examined. The first is purely shape-based and ut ilizes the principal modes of co-variation between anatomy and deformation in order to statistically represent deformability. When a patient's anatomy is available, it is used in conjunction with the statistical model to pred ict the way in which the anatomy will/can deform. The second method is rela ted, and it uses the statistical model in conjunction with a biomechanical model of anatomical deformation. It examines the principal modes of co-vari ation between shape and forces, with the latter driving the biomechanical m odel, and thus predicting deformation. Results are shown on simulated image s, demonstrating that systematic deformations, such as those resulting from change in position or from tumor growth, can be estimated very well using these models. Estimation accuracy will depend on the application, and parti cularly on how systematic a deformation of interest is.