3D shape recovery of deformable soft-tissue with computed tomography and depth scan

Knowing the tissue environment accurately is very important in minimal invasive surgery (MIS). While, as the soft-tissues is deformable, reconstruction of the soft-tissues environment is challenging. This paper proposes a new framework for recovering the deformation of the soft-tissues by using a single depth sensor. This framework makes use of the morphology information of the soft-tissues from Xray computed tomography, and deforms it by the embedded deformation method. Here, the key is to build a distance field function of the scan from the depth sensor, which can be used to perform accurate model-to-scan deformation together with robust non-rigid shape registration in the same go. Simulations show that soft-tissue shape in the previous step can be efficiently deformed to fit the partially observed scan in the current step by using the proposed method. And the results from the simulated sequential deformation of three different softtissues demonstrate the potential clinical value for MIS.