Table 1 Outcome comparison of state-of-the-art methods

Wadhah Ayadi [11]

Deep CNN

We exploited CNN for the problem of brain tumor classification. The proposed model, which contains various layers, aims to classify MRI brain tumor

The proposed model achieved higher accuracy of 97.02% and outperformed the various previous works

Xinyu Lei [12]

Hybrid dilated CNN

Proposed a dilated CNN model, which is built by replacing the convolution kernels of traditional CNN by dilated convolution kernels, and then, the dilated CNN model is tested on the Mnist handwritten digital recognition data set

The dilated CNN model reduces the training time by 12:99% and improves the training accuracy by 2:86% averagely, compared with the dilated CNN model

Himanshu Padole [13]

Graph CNN, graph wavelet transforms

A novel two-stage graph coarsening method rooted in graph signal processing and its application in the GCNN architecture

The proposed model achieved higher accuracy of 99.30% and outperformed the various previous works

Sichao Fu [14]

Graph-based semi-supervised learning, manifold assumption based

SSL algorithms

The spectral graph Hessian convolutions is a combination of the Hessian matrix and the spectral graph convolutions

HesGCN can learn more efficient data features by fusing the original feature information with its structure information based on Hessian

Isselmou Abd El Kader [15]

differential deep-CNN

differential deep convolutional neural network model to classify different types of brain tumor, including abnormal and normal MR images

The experimental results showed that the proposed model achieved an accuracy of 99.25%

Chirodip Lodh Choudhury [16]

Extracting features through a CNN

Deep neural network and incorporates a CNN based model to classify the MRI as “detected” or “not detected”

The model captures a mean accuracy score of 96.08% with f-score of 97.3

Anushka Singh [17]

Deep CNN

The proposed deep learning method which is used to classify Brain tumor types. Our method is based on VGG16 architecture with CNN as the classifier

An accuracy of above 93% along with high precision, recall and F-score was achieved

Saran Raj Sowrirajan [18]

VGG16 and Neural Autoregressive Distribution Estimation

Analyzing MRI through deep learning models is the most prevalent and accurate method of early cancer detection

Prediction accuracy of the proposed hybrid VGG16-NADE is 96.01%, precision 95.72%, recall 95.64%, F-measure 95.68%, ROC 0.91, error rate 0.075, and the MCC 0.3564

Suci Aulia [19]

Clip Limit Adaptive Histogram Equalization

Automatic brain tumor detection technology to identify the presence of a tumor in the brain without requiring human intervention

Highest performance with Acc, Pr, Recall, respectively 90.37%, 90.22%, 87.61%

Rafeek Mamdouh [20]

CNN, Active Contour & Deep Multi-Planar

Combination of two fields of solving segmentation problem to convert through the workflow of a hybrid algorithm structure CNN

System achieved a high result of segmentation, each image contains edges and image size = 256p × 256p, using Active Contour Model can generate multiple results for output, by resizing the threshold frames and gray-scale image and adjustment control, and generate a multi 3D model as output by changing the Histogram and Gaussian equation