Research Article
A New Kernel-Based Fuzzy Level Set Method for Automated Segmentation of Medical Images in the Presence of Intensity Inhomogeneity
Table 2
Comparison of proposed method with the famous level-set-based algorithms in terms of accuracy based on Dice coefficient and CPU time in second.
| Methods | Images | Accuracy % (Dice coefficient) | CPU time (second) | Brain | Vessel | Heart | Breast | Brain | Vessel | Heart | Breast |
| GKFCM_CV | 65 | 85 | 88 | 64 | 9.6 | 10.49 | 19.42 | 17.36 | GKFCM_Lankton | 48 | 79 | 67 | 53 | 10.9 | 13.93 | 20.57 | 16.99 | GKFCM_FTC | 80 | 84 | 90 | 68 | 8.7 | 7.36 | 14.48 | 16.27 | Proposed method | 96 | 91 | 98 | 84 | 14.3 | 12.56 | 26.51 | 34.19 |
|
|