Image Processing Based Brain Tumor Classification Using VGG16 Compared with SVM to Improve Accuracy

The primary goal of this study is to compare the performance of the Visual Geometry Group (VGG16) algorithm to that of the SVM algorithm in classification MRI images of brain tumors. The research includes two groups, each group has a sample size of 30. Simulation has been done with 80% G power. The performance metrics like accuracy and precision are calculated to assess the performance of the VGG16. Based on the results obtained by simulating using SPSS the VGG16 has an accuracy of 88.59 % and precision is 15.06 and accuracy of SVM is 84.58 % and precision of SVM is 13.70. The statistical significance is 0.032 where p<0.05. According to the results, VGG16 performs significantly better than the SVM in terms of accuracy and precision.