In the current situation, deep learning has developed as the most powerful tool for the interpretation of brain tumors. However, the performance of these ways is often finite by the standards of the input datasets. In this project, an amalgamated convolutional neural network (CNN) deep learning model is combined with advanced characteristics engineering techniques to develop the correctness of brain tumor detection. In the abstract, we propose a pipeline architecture in which the photos’ characteristics are extracted through advanced feature engineering; this transformed data can now be used to train any Machine Learning model and can be applied or given to Deep Learning Models. The main aim of advanced feature engineering is to optimize the working of the model by which the model can now be implemented over a low range of resources with high accuracy. The process of converting unprocessed data into numerical features that can be manipulated, all while retaining the inherent information within the original dataset, is commonly referred to as feature extraction. This approach tends to yield superior results compared to applying machine learning algorithms directly to the raw data. The suggested hybrid model performs better than cutting-edge techniques in terms of precision and accuracy, making it a promising tool for classifying brain cancers. For the differentiation of brain tumors, our hybrid deep learning model provides a promising method. We can improve accuracy and precision by combining CNNs with sophisticated feature engineering methods, which may help with the detection and management of brain tumors.