Medical imaging plays a crucial role in detecting various disorders, including brain cancers, through multimodal images like Computed Tomography (CT) and Magnetic Resonance Image (MRI). This study proposes a comprehensive approach to brain tumour detection, leveraging CT and MRI data fusion. The method includes pre-processing with a combination of median filtering and adaptive histogram equalization to enhance image quality. Subsequently, the pre-processed fused image undergoes Otsu segmentation, which makes it possible to identify discrete regions of interest followed by feature extraction using Grey-Level Co-occurrence Matrix (GLCM) for textural information capture. A gradient descent neural network is then employed for tumour classification, benefiting from rapid convergence and efficient weight updates. By combining multimodal image fusion, pre-processing, feature extraction and classification techniques, the proposed method shows promising results in brain tumour identification. This approach harnesses the unique strengths of CT and MRI scans, leading to improved accuracy and robustness in diagnosis. Ultimately, it holds potential for enhancing clinical decision-making and patient care in neuroimaging-based disease detection.