Fissure Detection¶

CIRRUS Lung includes an automatic fissure detection algorithm in the form of a fissure enhancement filter. The fissure detection algorithm provides a probability map of fissureness for each voxel in the lungs based on a patter recognition approach using Hessian eigenvalues and first and second order Gaussian derivatives, and a k-nearest neighbor classifier. The fissure detection is mainly used for guiding other algorithms, e.g. lobar segmentation, but also provides the backbone for a fissure completeness computation. For interested users, the fissure probability map can be visualized in CIRRUS Lung as a temparature map.

Technical publications about fissure detection algorithms included in CIRRUS Lung¶

E.M. van Rikxoort, B. van Ginneken, M. Klik and M. Prokop. "Supervised enhancement filters: application to fissure detection in chest CT scans", IEEE Transactions on Medical Imaging 2008;27:1-10. Abstract/PDF DOI PMID