Pulmonary syndromes such as lung cancer, pneumonia, chronic obstructive pulmonary sickness (COPD), and interstitial lung disease (ILD) are major health concerns across the world. An accurate and fast diagnosis is critical for the optimal treatment and management of many disorders. Traditional diagnostic approaches, which rely heavily on radiologists' interpretations of chest Xrays and CT scans, are frequently unreliable and inefficient. This research article presents a thorough overview of recent advances in the use of deep lmodels to diagnose lung illnesses using chest X-rays and chest CT images. The paper emphasizes the potential of deep learning to improve diagnostic accuracy, expedite the diagnostic procedure, and aid in early diagnosis and illness progression monitoring. Integrating deep learning with medical imaging has the latent to meaningly augment patient outcomes and maximize healthcare resources. The survey examines major findings from previous studies, ongoing difficulties, and potential future research areas to enhance the field of pulmonary disease diagnosis.