International Journal of Scientific Research and Engineering Development

Brain tumor detection is a critical task in medical imaging, as early and accurate diagnosis plays a vital rolein effective treatment planning and patient survival. Manual interpretation of brain images by radiologists is timeconsuming and prone to inter-observer variability, motivating the development of automated computer-aided diagnosis systems. This paper presents an efficient and reliable framework for brain tumor detection and classification using medical imaging techniques implemented in the MATLAB environment. Magnetic Resonance Imaging (MRI) is employed due to its superior soft-tissue contrast and non-invasive nature. The proposed methodology follows a structured pipeline consisting of image preprocessing, tumor segmentation, feature extraction, and classification. Preprocessing techniques are applied to enhance image quality and suppress noise, while tumor regions are segmented using thresholding and clustering-based approaches. Discriminative features are extracted using texture, frequency, and shape-based descriptors, including Gray-Level Co-occurrence Matrix (GLCM) and Discrete Wavelet Transform (DWT). Classification is performed using both traditional machine learning algorithms and deep learning models. Performance evaluation is carried out using standard metrics such as accuracy, sensitivity, specificity, F1-score, Dice coefficient, and Receiver Operating Characteristic (ROC) analysis. Experimental results demonstrate that the proposed MATLAB-based framework achieves high detection accuracy and robustness, highlighting its potential as a reliable decision-support tool for automated brain tumor analysis in clinical applications.

Lisa Saha, Sumanta Kuila, Amrita Sarkar,"Brain Tumor Detection and Classification in Medical Imaging" International Journal of Scientific Research and Engineering Development, V9(1): Page(2169-2173) Jan-Feb 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.