DICOM2FEM is an application for semi-automatic generation of finite element meshes using computed tomography scans. The input is a CT data set stored in a serie of DICOM files, the pydicom package is used to import the volumetric data, see [1]. The segmentation method is based on the graph cut algorithm (pygco library, [2]) and machine learning algorithms from scikit-learn.

The program can generate volume (hexahedral or tetrahedral) and surface (triangle or quadrilateral) FE meshes. The Taubin smoothing algorithm and Marching cubes algorithm are implemented in order to produce more realistic geometrical models of body parts. The meshes can be exported to HyperMesh, Comsol, HDF5, VTK or Nastran file formats. The PyQT and VTK libraries are used for the user interface.

CT scan visualizations - VolView:

Generated FE mesh of carotid artery:

DICOM2FEM - Segmentation editor:

[1] http://code.google.com/p/pydicom

[2] https://github.com/amueller/gco_python