Brain Tumor Detection in MRI Scans Using a Deep CNN

Abstract

Enhancement of brain tumor detection is achieved through deep learning-based image analysis. Existing systems use methods like manual segmentation, traditional machine learning, and pre-trained models, but they often struggle with small datasets, low contrast in MRI scans, or high false-negative rates. Many approaches also fail to generalize across diverse medical imaging devices, limiting real-world applicability. Our project addresses these challenges by developing a custom Convolutional Neural Network (CNN) optimized for brain MRI analysis. The system automatically detects tumors by analysing structural patterns in MRI scans with high accuracy and a high F1-score, minimizing diagnostic errors. By incorporating data augmentation and lightweight architecture, the model achieves high precision without relying on transfer learning, making it suitable for resource-constrained clinical environments.