Hybrid CNN-BI-LSTM Network for the Accurate Brain Tumour Prediction in MRI Image

Brain tumors remain an important global health concern due to their high mortality rates. Accurate and early estimation plays a crucial role in improving patient outcomes. This study introduces a hybrid model combining Convolutional Neural Networks (CNN) and Bidirectional Long Short Term Memory (Bi-LSTM) networks for MRI based brain tumor detection. The proposed framework includes preprocessing steps such as resizing and cropping to standardize input dimensions, followed by OTSU segmentation for effective tumor delineation. Texture features are extracted using Gray Level Co-occurrence Matrix (GLCM), and hybrid CNN-Bi-LSTM model leverages spatial and temporal dependencies to enhance prediction accuracy. Experimental results accomplished using Python demonstrate that a hybrid model outperforms conventional CNN and Bi-LSTM approaches, achieving an accuracy of 93.5% and a specificity of 92%. Thereby, proposed approach provides a reliable and efficient solution for automated brain tumour diagnosis, paving the way for improved early detection and clinical decision-making.