Skip to main content

Table 1 Comparison of existing knee segmentation methods

From: Fully automated, level set-based segmentation for knee MRIs using an adaptive force function and template: data from the osteoarthritis initiative

Authors

Key algorithm

Segmentation tissues

Modalities

Tesla

Subject numbers

Template image

Tamez-Pena et al. [6]

Fuzzy voting algorithm

Femoral cartilage, tibial cartilage

T1-weighted MRI (3-D DESS WE)

3T

12

Used

Shan et al. [5]

kNN classification

Femoral cartilage, tibial cartilage, femur, tibia

T1-weighted and partially T2-weighted MRI

18

Used

Ringenbach et al. [4]

Fast marching algorithm (region growing)

Femur, tibia, patella

CT

20

Used

Ababneh et al. [7]

Graph-cut algorithm

Femur, tibia

T2-weighted MRI

3T

200 (14 slices per each subject)

Used

Dodin et al. [11]

Ray casting technique

Femur, tibia

T2-weighted MRI (3-D-FISP)

1.5T

161

Unused

Dodin et al. [10]

Bayesian decision criterion

Femoral cartilage, tibial cartilage

T1-weighted MRI (3-D DESS WE)

3T

14

Unused