Paper Title
Design & Development of CNN Based Deep Learning Model for Brain Tumor Prediction

Abstract
Predicting brain cancers accurately is critical for prompt diagnosis and treatment planning. In order to improve the accuracy of diagnoses, we present a new deep learning model that uses convolutional neural networks (CNNs) for the prediction of brain tumors. We evaluate our CNN model alongside more traditional machine learning techniques, such as ANN, GLCM-CNN, and DT, which stand for Grey Level Co-occurrence Matrix mixed with CNN. With a remarkable 96% accuracy, our experimental results show that the CNN-based model has greater predictive capability. This outperforms all other algorithms considered in this study, including ANN (72%), GLCM-CNN (91%), and DT (93%). The CNN model's exceptional accuracy underscores its potential as a reliable tool for brain tumor prediction in clinical settings. The development of our CNN-based model involved meticulous design and optimization of the network architecture, leveraging the power of using deep learning to routinely extract useful information from magnetic resonance imaging (MRI) scans. The CNN layers learn hierarchical representations, which our model uses to its advantage to accurately detect brain cancers by their subtle patterns.This study adds to the continuing efforts to use sophisticated computational methods for medical image analysis, particularly in the domain of brain tumor diagnosis. The significant performance improvement offered by our CNN-based approach highlights the promising future of deep learning in revolutionizing medical diagnostics and improving patient outcomes. Keywords - CNN, Tumor Detection, F1-score