Enhancing Brain Tumor Detection Accuracy with an RNN Model Compared to R-CNN Classification

The purpose of the study is to evaluate the performance of Recurrent Neural Networks with Convolutional Neural Networks in terms of accuracy in brain tumor detection. Using a total of 20 samples (ten for RNN and ten for CNN) iterated 20 times to predict brain tumor pathology, recurrent neural networks are employed for the first time to detect brain cancers. Findings: With an accuracy of 92%, recurrent neural networks can be considered more accurate than convolutional neural networks, which have an accuracy of 68%. A significant value of 0.0268 ((p¡0.05) has been obtained for the investigation. When compared to Convolutional Neural Networks, Recurrent Neural Networks outperform them in tracking precision.