NEUROSCAN: A Deep Learning-Based Framework for Brain Tumor Detection Using Convolutional Neural Networks

Abstract

Brain tumors are among the most critical and life-threatening neurological disorders,
requiring early and accurate diagnosis for effective treatment. Traditional diagnostic
methods rely heavily on radiologists, making the process time-consuming and prone to
human error. With the rapid advancement of artificial intelligence, deep learning
techniques, particularly Convolutional Neural Networks (CNNs), have shown remarkable
performance in medical image analysis.This paper presents NEUROSCAN, a deep
learning-based system designed for automated brain tumor detection using CT scan
images. The system integrates image processing, CNN-based classification, and a userfriendly
graphical interface for real-time predictions. The proposed framework classifies
brain images into two categories: tumor and normal.The system begins with dataset
collection and preprocessing, where CT scan images are resized and normalized to ensure
uniformity. The CNN model is constructed using multiple convolutional and pooling
layers to extract spatial features from images. These features are then passed through
fully connected layers to perform classification using a sigmoid activation function.
The model is trained using labeled datasets and evaluated using training and validation
splits. The use of binary cross-entropy loss and the Adam optimizer enhances model
convergence and accuracy. The trained model is integrated into a Tkinter-based graphical
user interface, allowing users to upload CT images and receive instant
predictions.Experimental results demonstrate that the system achieves high accuracy in
distinguishing between tumor and normal brain images. The simplicity of the architecture
ensures low computational requirements, making it suitable for real-time and lowresource
environments.Compared to traditional methods, the proposed system reduces
dependency on manual diagnosis and provides faster results. It can assist healthcare
professionals in decision-making and improve diagnostic efficiency