PT Journal
AU Debora Gil
   Sergio Vera
   Agnes Borras
   Albert Andaluz
   Miguel Angel Gonzalez Ballester
TI Anatomical Medial Surfaces with Efficient Resolution of Branches Singularities
SO Medical Image Analysis
JI MIA
PY 2017
BP 390
EP 402
VL 35
DI 10.1016/j.media.2016.07.002
DE Medial Representations; Shape Recognition; Medial Branching Stability; Singular Points
AB Medial surfaces are powerful tools for shape description, but their use has been limited due to the sensibility existing methods to branching artifacts. Medial branching artifacts are associated to perturbations of the object boundary rather than to geometric features. Such instability is a main obstacle for a condent application in shape recognition and description. Medial branches correspond to singularities of the medial surface and, thus, they are problematic for existing morphological and energy-based algorithms. In this paper, we use algebraic geometry concepts in an energy-based approach to compute a medial surface presenting a stable branching topology. We also present an ecient GPU-CPU implementation using standard image processing tools. We show the method computational eciency and quality on a custom made synthetic database. Finally, we present some results on a medical imaging application for localization of abdominal pathologies.
ER