Segmentation of elongated structures in medical images

The research described in this thesis concerns the automatic
detection, recognition and segmentation of elongated structures in
medical images. For this purpose techniques have been developed to
detect subdimensional pointsets (e.g. ridges, edges) in images of
arbitrary dimension. These pointsets are grouped into primitives, such
as line elements and surface patches. The primitives form the basis
for recognition and segmentation task, which is accomplished with
classifiers from statistical pattern recognition. Two applications are
given: segmentation of the vasculature in color images of the human
retina and detection, labeling and segmentation of ribs in CT-scans
(computed tomography) of the thorax.