作者: Fatemeh Abdolali , Reza Aghaeizadeh Zoroofi
DOI: 10.1109/ICBME.2014.7043884
关键词:
摘要: This paper presents a method for automatic segmentation of mandibular canal from CBCT (cone beam CT) images based on 3D Active Appearance Models (AAM) and shape context registration. The proposed algorithm consists two stages: Firstly, Shape Context non-rigid surface registration the manual segmented is used to obtain point correspondence between given training cases. Subsequently, an AAM segment 60 evaluated using 5-fold cross validation over 5 repetitions. mean Dice similarity coefficient 95% Hausdorff distance are 0.86 0.90 mm, respectively.