AIIB 2023

Data from Airway-related quantitative imaging biomarkers (QIB) are crucial for examination, diagnosis, and prognosis in lung diseases, while the manual delineation of airway structures is unduly burdensome [1, 2]. Several efforts have been made to improve the performance of automatic airway modelling [3-7]; however, current datasets only focus on diseases that have minor tracheal changes and do not incorporate complex pulmonary diseases. For instance, the honeycombing within the lung tissue in patients with fibrotic lung disease makes the annotation much more complicated and error-prone. To bridge this gap, 285 cases (235 from patients with fibrotic lung disease and 50 from patients with COVID-19) were collected and included in this challenge. The airway structures were meticulously annotated by three experienced radiologists.