Enhancing Brain Tumor Classification with Data Augmentation and DenseNet121

Abstract

This research paper presents a comprehensive study on the development and evaluation of a brain tumor classification model using advanced image processing and deep learning techniques. The primary objective of this study was to create an accurate and robust system for distinguishing between brain tumors and normal brain images, utilizing both an original dataset and an augmented dataset. With a focus on improving medical diagnosis, the research aimed to enhance the performance of brain tumor detection by leveraging state-of-the-art machine learning methods. The model pipeline comprised various image preprocessing steps, including cropping, resizing, denoising, and normalization, followed by feature extraction using the DenseNet121 architecture and classification using sigmoid activation. The dataset was meticulously divided into training, validation, and testing sets, with an emphasis on achieving high recall, precision, F1-score, and accuracy as key research objectives. The results demonstrate that the model achieved impressive performance, with a training recall of 92.87%, precision of 93.82%, F1-score of 93.15%, and an accuracy of 94.83%. These findings underscore the potential of deep learning and data augmentation in enhancing brain tumor detection systems, supporting the research's core objective of advancing medical image analysis for clinical applications.