Research Article
Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images
Table 2
Evaluation metrics applied in actual breast images regarding the five segmentation techniques applied in the tests.
| ā | AOM (%) | AUM (%) | AVM (%) | CM (%) | CP (%) | CR (%) | (%) | (%) | Err. (%) | FPR (%) |
| Active contour | 81.69 | 8.57 | 11.53 | 87.20 | 91.43 | 88.47 | 81.69 | 95.83 | 4.17 | 3.05 | Region growing | 70.85 | 19.42 | 25.55 | 93.22 | 67.13 | 92.07 | 62.32 | 89.79 | 10.21 | 2.19 | Fuzzy -means | 59.86 | 24.51 | 33.63 | 71.96 | 77.41 | 72.84 | 57.36 | 85.19 | 14.81 | 10.87 | -means | 38.92 | 30.74 | 57.02 | 42.26 | 87.65 | 45.65 | 41.61 | 67.29 | 32.71 | 37.89 | SOM | 75.25 | 19.75 | 24.09 | 93.97 | 67.46 | 96.77 | 65.15 | 91.33 | 8.66 | 0.62 |
| Required value | 100 | 0 | 0 | 100 | 100 | 100 | 100 | 100 | 0 | 0 |
|
|