The aim of this project is to classify CT Scan images of pa- tients with or without pneumonia. More specifically, we trained a Convolutional Neural Network(CNN) of differ- ent parameters with chest CT Scan images of children and the outcome classes are two: ”Pneumonia” or ”Non - pneumo- nia”. The findings follow in the next sections. The primary objective of this work is to develop an efficient and reliable model that can automatically classify chest CT scan images into two categories: pneumonia and non- pneumonia. For this purpose, Convolutional Neural Networks (CNNs) are utilized due to their proven effectiveness in image classification tasks. The model leverages transfer learning and fine-tuning techniques using pre-trained architectures, enabling better performance even with limited medical datasets. In addition, data augmentation methods such as rotation, zooming, flipping, and shifting are applied to enhance the diversity of the dataset and reduce overfitting. Various optimizers, including RMSprop and Adam, are implemented and compared to improve the training efficiency and accuracy of the model. Experimental results demonstrate that the proposed system achieves high accuracy and strong performance in distinguishing between infected and healthy lung images.