Research Article
A Deep Learning Framework for Leukemia Cancer Detection in Microscopic Blood Samples Using Squeeze and Excitation Learning
Table 7
Comparison with existing work.
| Sr. No. | Authors | Methods | Dataset | Accuracy (%) |
| 1 | Ahmed et al. [32] | CNN | ALL_IDB | 88.25 | 2 | Shafique and Tehsin [2] | AlexNet-based transfer learning | ALL_IDB | 99.50 | 3 | Jothi et al. [74] | Jaya, SVM | ALL_IDB | 99 | 4 | Mishra et al. [42] | DOST, PCA, LDA | ALL_IDB1 | 99.66 | 5 | Jiang et al. [54] | Vision transformer– based CNN | ISBI2019 | 99.03 | 6 | Agaian et al. [75] | SVM with cell energy feature | ALL_IDB1 | 94 | 7 | Tuba and Tuba [60] | Gao-based methods | ALL_IDB2 | 93.84 | 8 | Jha and Dutta [58] | SCA-based deep CNN | ALL_IDB2 | 98.70 | 9 | Proposed | Squeeze and excitation based CNN | ALL_IDB1 | 100 | 10 | Proposed | Squeeze and excitation based CNN | ALL_IDB2 | 99.98 | 11 | Proposed | Squeeze and excitation based CNN | ALL_IDB1 + ALL_IB2 | 98.3 |
|
|