An exemplary method of detecting a structure in a three-dimensional (3D)
computed tomography ("CT") knee image is provided. An intensity prior
mask is created based on a two-dimensional (2D) slice of the CT image. A
seed point in the 2D slice is received or estimated. The seed point is in
a Hoffa's pad region. A geometric prior mask is created based on the seed
point. The intensity prior mask and the geometric mask are combined to
form a region mask. A level-set contour is segmented from the 2D slice.
The step of segmenting is constrained by the region mask.