Table 5. Quality evaluation of CCC segmentation [3].
| Methods | KRC, mean ± SD | DSC, mean ± SD | SSIM, mean ± SD | HD, mean ± SD (px) | AHD, mean ± SD (px) |
|---|---|---|---|---|---|
| SNAKE | 0.6735±0.1157 | 0.7603±0.0879 | 0.7636±0.0529 | 55.3089±26.8671 | 3.5231±4.6711 |
| DRLSE | 0.6444±0.0982 | 0.7236±0.0753 | 0.7447±0.0412 | 54.6655±25.8281 | 3.8592±4.3156 |
| C-V | 0.5968±0.1033 | 0.7943±0.0839 | 0.6836±0.0677 | 75.1000±29.8133 | 3.8606±5.0408 |
| RSF | 0.6338±0.0966 | 0.7061±0.0741 | 0.7393±0.0410* | 56.3961±25.4791 | 4.1356±4.2407 |
| ACWE | 0.6513±0.1739 | 0.8223±0.1209 | 0.7319±0.0926 | 56.0623±27.2610 | 2.8226±5.6080 |
| LBF | 0.6204±0.1907 | 0.7624±0.1176 | 0.7005±0.1202 | 66.7879±38.9074 | 3.8926±5.2375 |
| GLFIF | 0.6396±0.1517 | 0.7956±0.1013 | 0.6952±0.0930 | 79.9539±34.5955 | 3.7200±4.7642 |
| ALF | 0.6296±0.1455 | 0.6050±0.0857 | 0.6693±0.0685 | 106.8502±24.2695 | 9.2019±3.9525 |
| Proposed | 0.8312*±0.0669* | 0.8955*±0.0483* | 0.8475*±0.0499 | 28.4420*±20.2059* | 0.7071*±1.2097* |
*, optimal result. CCC, corpus callosum-cavum septum pellucidum complex; KRC, Kendall rank correlation; DSC, dice similarity coefficient; SSIM, structural similarity index measure; HD, Hausdorff distance; AHD, average Hausdorff distance; SD, standard deviation; px, pixels; SNAKE, Snakes Active Contour Model; DRLSE, Distance Regularized Level Set Evolution; C-V, Chan-Vese Active Contour Model; RSF, Active Contour Model Based on Region-scalable Fitting; ACWE, Active Contour Without Edges; LBF, Active Contour Model Based on Local Binary Fitting Energy; GLFIF, Global and Local Fuzzy Implicit Active Contours Driven by Weighted Fitting Energy; ALF, Implicit Active Contours Driven by Local Binary Fitting Energy.