Table 9 Classification accuracy comparison of proposed and state-of-the-art-methods
From: Multimodal hybrid convolutional neural network based brain tumor grade classification
Author | Year | Method | Dataset | Images | Accuracy outcome (%) |
|---|---|---|---|---|---|
Isselmou Abd El Kader [15] | 2021 | Dilatdifferential deep-CNN architecture CNN | Tianjin Universal Centre of Medical Imaging and Diagnostic | 3200 | 99.25 |
Chirodip Lodh Choudhury [16] | 2020 | Convolutional neural network | Kaggle | 1900 | 96.08 |
Anushka Singh [17] | 2020 | Brilliant deep convolutional neural networks | Figshare Dataset | 2100 | 93 |
Saran Raj [18] | 2023 | Neural Autoregressive Distribution Estimation | CE-MR brain dataset | 3064 | 96 |
Suci Aulia [19] | 2022 | Clip Limit Adaptive Histogram Equalization | TCIA | 7858 | 90.37 |
Proposed model | 2023 | Hybrid Deep Learning | Kaggle | 2100 | 99.11 |