DETECTIVE TUMOUR GROWTH USING DEEPLEARNING

Abstract

Early and accurate detection of brain tumours is crucial for improving patient survival and 
treatment planning. This study presents a framework based on deep learning for automated 
brain tumour detection and classification using magnetic resonance imaging (MRI) scans. A 
convolutional neural network (CNN) architecture was developed and trained on a curated 
dataset of labeled brain MRI images. This model can distinguish between tumour and non
tumour cases, as well as different tumour categories. The proposed model uses preprocessing 
techniques like image normalization, resizing, and augmentation to improve generalization and 
reduce overfitting. The network architecture includes multiple convolutional layers with ReLU 
activation, max-pooling operations, batch normalization, and fully connected layers, followed 
by a softmax classifier. We evaluated model performance using standard metrics such as 
accuracy, precision, recall, F1-score, and loss analysis. Experimental results show high 
classification performance, with strong accuracy and balanced precision-recall characteristics 
across validation and test datasets. Training and validation curves indicate stable convergence 
with minimal overfitting. A comparative analysis with baseline machine learning approaches 
confirms that the proposed deep learning framework is superior in feature extraction and 
classification robustness. The system has potential for real-time clinical decision support, 
helping radiologists with early tumour identification and reducing their diagnostic workload.