Classification of medical images using Deep Learning

Abstract

This report explores medical image classification through Convolutional Neural Networks (CNNs), integrating theoretical foundations with practical application. It begins with a review of essential AI and deep learning principles, with particular emphasis on CNN architecture and its effectiveness in feature extraction. For the practical component, a DenseNet-121 model is implemented to classify two distinct medical imaging datasets: chest X-rays (COVID-19, pneumonia, and normal cases) and brain MRIs (three tumour types and normal). Following preprocessing and training, the model demonstrated excellent performance, achieving an accuracy and F1-score both exceeding 0.99. These results highlight the robustness of CNNs in medical image analysis and their potential in supporting clinical diagnostic processes. Keywords: .