METHOD FOR SEGMENTATION OF OBJECTS FROM A THREE DIMENSIONAL IMAGE DATA SET WITH A DEFORMABLE MODEL

摘要

The present invention relates to a method for segmentation of an object of interest from a three dimensional image data set, wherein a deformable model is adapted to the boundary of the object of interest (BOI), wherein the deformable multi layer mesh model comprises at least two layers (L1, L2), each layer having a mesh structure of interconnected mesh points (M1-1, M1-2, M1-3, M2-1, M2-2, M2-3), wherein each mesh point of a layer is connected with at least one other mesh point of the same layer by a layer link (11-1, 11-2, 11-3, 12-1, 12-2, 12-3), a first layer (L1) forms an outer surface of the model, at least one inner layer (L2) is located inside the outer surface of the model, each of the mesh points of the first layer (M1-1, M1-2, M1-3) is connected with a corresponding mesh point of a neighbouring inner layer (M2-1, M2-2, M2-3) by a depth link (D12-1, D12-2, D12-3), in case of any further inner layer (L3), each mesh point of each inner layer (M2-1, M2-2, M2-3) is connected with a corresponding mesh point of each neighbouring inner layer (M3-1, M3-2, M3-3) by a depth link (D23-1, D23-2, D23-3), and wherein the deformable multi layer mesh model is adapted to the boundary of the object of interest (BOI). The invention further relates to an image processing system comprising image data processing means for segmentation of an object of interest, to a medical examination apparatus, and to a computer program which is adapted to perform the segmentation-method of the invention.