Medical image processing has become an essential aspect of healthcare, enabling accurate disease diagnosis and monitoring through advanced technologies. One of the most widely used methods in this domain is the Convolutional Neural Network (CNN), which has demonstrated high effectiveness in segmentation and classification tasks, particularly for chest X-ray images used in diagnosing lung-related diseases. This study aims to evaluate and analyze various CNN architectures implemented in lung X-ray imaging through a Systematic Literature Review (SLR) approach. The research explores the application, accuracy, challenges, and future opportunities of CNN-based models such as VGG, ResNet, AlexNet, and GoogLeNet. A total of 15 relevant studies published between 2019 and 2023 were selected after applying rigorous inclusion and exclusion criteria. The findings indicate that CNN architectures significantly enhance the accuracy of lung disease detection and support both segmentation and classification tasks. However, challenges such as dataset variability, model generalization, and ethical implications remain. This review provides comprehensive insights into CNN applications in medical imaging, emphasizing their potential and highlighting areas for further research.