Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease 2023 (AIIB23)

AIIB23数据集是由帝国理工学院生物工程系和帝国-X创建的，专门用于评估肺纤维化疾病中的气道相关定量成像生物标志。该数据集包含120个高分辨率计算机断层扫描（HRCT），这些扫描由三名经验丰富的放射科医生精心标注。数据集的目标是鼓励参与者开发具有高鲁棒性和泛化能力的自动气道分割模型，并探索与死亡率预测最相关的QIB。此外，数据集还包括专家标注和死亡状态，以支持模型的训练和验证。AIIB23数据集的应用领域主要集中在提高对肺纤维化疾病的诊断和预后评估，通过先进的计算方法来提取复杂的气道结构，并探索这些结构与疾病进展之间的关系。

The AIIB23 dataset was created by the Department of Bioengineering at Imperial College London and Imperial-X, and is specifically dedicated to evaluating airway-associated quantitative imaging biomarkers (QIBs) in pulmonary fibrosis. This dataset includes 120 high-resolution computed tomography (HRCT) scans, which were meticulously annotated by three experienced radiologists. The core goal of this dataset is to encourage participants to develop automated airway segmentation models with high robustness and generalization ability, and to identify the QIBs most relevant to mortality prediction. Additionally, the dataset provides expert annotations and mortality status to facilitate model training and validation. The application scope of the AIIB23 dataset primarily focuses on advancing the diagnosis and prognostic evaluation of pulmonary fibrosis, extracting intricate airway structures via advanced computational methods, and exploring the associations between these structures and disease progression.