[Progress of artificial intelligence technology in pneumoconiosis imaging diagnosis and disease burden assessment]

Pneumoconiosis is an occupational lung disease caused by long-term inhalation of industrial or mineral dust, with chronic lung inflammation and progressive pulmonary fibrosis as the main pathological features. Early-stage pneumoconiosis often presents with atypical clinical symptoms, while late-stage pneumoconiosis poses severe harm to patients with limited treatment options. Therefore, early screening, accurate diagnosis, and prediction of disease burden are crucial for effectively controlling the progression of pneumoconiosis and reducing associated complications. These measures are vital for improving patients' quality of life and enhancing the efficiency of pneumoconiosis prevention and treatment. Currently, intelligent auxiliary diagnostic systems can assist clinicians in improving the accuracy of pneumoconiosis imaging diagnosis and aid in clinical treatment evaluation. This paper reviews recent literature on the application of artificial intelligence (AI) technologies in pneumoconiosis imaging and disease burden prediction. It provides an in-depth analysis of the advancements in AI for early screening, diagnosis, and disease burden assessment and prediction of pneumoconiosis. Furthermore, it explores future directions for the development of intelligent imaging diagnosis and disease burden prediction for pneumoconiosis, aiming to better support clinical decision-making.