Deep Learning-Based CNN with LSTM for Accurate Brain Tumor Classification Using MRI Data

The purpose of this research is to investigate the creation and deployment of a Convolutional Neural Network (CNN) model that is based on deep learning and is integrated with Long Short-Term Memory (LSTM) for the classification of brain cancers using Magnetic Resonance Imaging (MRI) data. Following the use of convolutional operations for feature extraction and transformer blocks to capture long-range dependencies, the suggested model then employs classification layers in order to provide the output in multiple classes. There are considerable gains in accuracy and decreases in loss as the number of epochs grows, according to the findings of the research, which evaluates the performance of this architecture across several epochs or periods. The level of accuracy that the model is capable of achieving is 99.38%, with a loss of 0.0222 that corresponds to it. This demonstrates that the model is effective in properly categorizing photos of brain tumors to be healthy is a basic service and is very important for healthcare.