Research Article
Automated Feature Extraction in Brain Tumor by Magnetic Resonance Imaging Using Gaussian Mixture Models
Table 1
Performance metrics (%) based on the GMM features.
| Classifier | Sequence | Accuracy | False alarm | Missed detection |
| NB | T1-WI | 97.05 | 2.95 | 0 | T2-WI | 97.05 | 0 | 2.95 | FLAIR | 94.11 | 5.89 | 0 | Entire GBM | 86.27 | 2.94 | 10.78 |
| SVM | T1-WI | 70.58 | 0 | 29.41 | T2-WI | 64.70 | 5.88 | 29.41 | FLAIR | 67.64 | 2.94 | 29.41 | Entire GBM | 66.66 | 4.90 | 28.43 |
| PNN | T1-WI | 94.11 | 5.89 | 0 | T2-WI | 70.58 | 11.76 | 17.64 | FLAIR | 94.11 | 2.94 | 2.94 | Entire GBM | 86.27 | 2.94 | 10.78 |
|
|
Entire GBM refers to T1-WI, T2-WI, and FLAIR features combined together.
|