Brain Tumor Detection and Classification Using LSTM

Brain tumor detection and classification play a crucial role in medical imaging, where timely and accurate diagnosis can significantly impact patient health. This study proposes an approach that uses Long Short-Term Memory (LSTM) networks for detecting and classifying brain tumors based on MRI imaging data. LSTM, a type of recurrent neural network (RNN), is well-suited for processing sequential data, making it ideal for medical image analysis. The model processes a sequence of MRI images through a pipeline that extracts key features, which are then analyzed by the LSTM network for brain tumor detection and classification. The model has been trained on a dataset containing artificial brain tumors, allowing it to distinguish between false positives and negatives with high accuracy. Experimental results validate the effectiveness of LSTM techniques compared to traditional machine learning algorithms. The performance of the model in both detection and classification tasks has significantly improved due to the precision provided by the LSTM-based approach. The system demonstrates great potential for assisting radiologists by providing valuable diagnostic information and has the potential to improve patient outcomes. The model has achieved an accuracy of 95%. The dataset used in this study includes 7,022 brain MRI images, of which 300 contain glioma, 306 contain meningioma, 405 contain no tumor, and 300 are labeled as no tumor.