Table 9.
Performance comparison of the state-of-the-art methods against the proposed approach on MRI brain dataset (Number of utilized images 595 (where, normal = 115, and abnormal = 480)).
| Published Methods | Used Methods | Recognition Rates | Misclassification |
|---|---|---|---|
| Orouskhani, et al. [44] | Conditional Deep Triplet Network | 92.5% | 1.2% |
| Inglese, et al. [45] | Decision Support System | 81.0% | 2.5% |
| Mandle, et al. [46] | Kernel-based SVM | 90.2% | 3.3% |
| Abdulmunem, et al. [47] | Deep Belief Network | 88.9% | 3.5% |
| Jang, et al. [48] | Sorting Algorithm | 72.6% | 4.6% |
| Popuri, et al. [49] | Ensemble Learning | 90.3% | 3.1% |
| Latif, et al. [50] | Neural-Network-Based Features with SVM Classifier | 89.9% | 0.9% |
| Nawaz, et al. [51] | Multilayer Perception, J48, Meta Bagging, Random Tree | 83.8% | 2.0% |
| Assam, et al. [52] | Random Forest | 94.1% | 3.9% |
| Islam, et al. [53] | Convolutional Neural Network | 78.9% | 4.8% |
| Dehkordi, et al. [54] | Evolutionary Convolutional Neural Network | 91.3% | 2.0% |
| Krishna, et al. [55] | Local Linear Radial Basis Function Neural Network | 88.7% | 3.9% |
| Takrouni, et al. [56] | Deep Convolutional Network | 92.5% | 2.0% |
| Fayaz, et al. [57] | Convolutional Neural Network | 86.8% | 5.2% |
| Proposed Scheme | Logistic Regression | 96.6% | 3.4% |