A fast accurate 3D surface reconstruction method of medical image based on modularization

A 3D surface reconstruction method of medical images based on modularization is proposed in this paper. First, an appropriate segmentation method is applied to its slices using features of the original medical image, and the segmentation result is used as the input of "marching cubes" to generate accurate isosurfaces. Then, a voxel-tracing algorithm is developed based on the relativity of triangles of the isosurfaces. Finally, the vertexes are merged according to some constraints. Experimental results demonstrate that the method was efficient and effective.