This paper introduces an innovative deep learning framework tailored for the classification of chest CT scan images with a specific focus on aiding the diagnosis of respiratory ailments such as pneumonia, tuberculosis, lung cancer, and covid-19, leveraging cutting-edge convolutional neural networks CNNs. Our methodology encompasses rigorous data preprocessing augmentation and model fine-tuning to optimize performance throughout the training process. We employ a suite of strategic callbacks to facilitate convergence and mitigate overfitting our empirical findings that underscore the models high accuracy in accurately distinguishing among diverse respiratory conditions showcasing its potential as a valuable tool for early disease detection in clinical settings. This research represents a significant contribution to the burgeoning field of medical image analysis with wide-ranging applications in areas such as radiology, pathology, and beyond ultimately. Our approach promises to enhance patient care by enabling timely interventions and informed medical decisions.