A system and method for pre-operatively obtaining a prediction of a post-operative image of at least part of a body is disclosed. A 3D pre-operative description is determined of at least part of a body, and a pre-operative 2D photograph is acquired of the at least part of the body from any viewing position. The 3D pre-operative description is matched with the pre-operative 2D photograph, and a deformation field is determined for deforming the 3D pre-operative description. A predicted post-operative image of a 3D post-operative description of the at least part of the body is derived by means of the deformation field and the pre-operative 2D photograph.