Osteophyte is an additional bony growth on a normal bone surface limiting or stopping motion in a deteriorating joint.
Detection and quantification of osteophytes from CT images is helpful in assessing disease status as well as treatment and
surgery planning. However, it is difficult to segment osteophytes from healthy bones using simple thresholding or
edge/texture features in CT imaging. Here, we present a new method, based on active shape model (ASM), to solve this
problem and evaluate its application to ex vivo μCT images in an ACLT rabbit femur model. The common idea behind
most ASM based segmentation methods is to first build a parametric shape model from a training dataset and during
application, find a shape instance from the model that optimally fits to target image. However, it poses a fundamental
difficulty for the current application because a diseased bone shape is significantly altered at regions with osteophyte
deposition misguiding an ASM method that eventually leads to suboptimum segmentation results. Here, we introduce a
new partial ASM method that uses bone shape over healthy regions and extrapolate its shape over diseased region
following the underlying shape model. Once the healthy bone region is detected, osteophyte is segmented by subtracting
partial-ASM derived shape from the overall diseased shape. Also, a new semi-automatic method is presented in this paper
for efficiently building a 3D shape model for rabbit femur. The method has been applied to μCT images of 2-, 4-, and
8-week post ACLT and sham-treated rabbit femurs and results of reproducibility and sensitivity analyses of the new
osteophyte segmentation method are presented.