Exploring the Landscape of Lung Diseases: A Comprehensive Literature Survey

The lung is the sensitive organ of our body. Modern developments in deep learning and machine learning have completely changed how medical imaging is used to diagnose and classify lung problems. Consequently, there is a wealth of literature exploring the application of these technologies in this domain. This study undertakes a broad survey of the utilization of deep learning and machine learning methods for diagnosing lung illnesses in medical images. Its primary objectives include delineating the taxonomy of cutting-edge deep learning-driven systems for detecting lung diseases, interpreting recent research trends, and identifying persistent challenges and potential future directions. By proposing a machine learning-based classification of contemporary lung diseases, this research aims to furnish a framework crucial for researchers across various domains to structure their contributions and investigations. This classification encompasses several common survey attributes, including the types of data utilized, the spectrum of lung diseases addressed, and the collection of machine learning and deep learning procedures employed. Such a framework is pivotal for augmenting the efficacy and accuracy of machine learning in the precise identification and categorization of lung disorders, thereby minimizing diagnostic errors.