Automated methods for assessing structural lung disease in patients with cystic fibrosis and primary ciliary dyskinesia: a scoping review

Cystic Fibrosis (CF) and Primary Ciliary Dyskinesia (PCD) are rare genetic disorders primarily affecting the respiratory system that can lead to bronchiectasis. They share similar symptoms including recurrent lung infections, cough and difficulties in clearing mucus. Thoracic chest computed tomography (CT) imaging is widely used to assess structural lung disease in both CF and PCD. In an attempt to unify interpretation strategies of structural lung disease, semi-quantitative and quantitative scoring tools were developed for diagnosis, monitoring progression, and evaluating treatment responses. However, the manual scoring procedure is time consuming, tedious and subjective. Its accuracy depends on the expertise and experience of the radiologist performing the analysis. Advances in artificial intelligence (AI) have led to the introduction of several automated CT scoring techniques in the scientific literature to alleviate these challenges. We synthesized findings from 50 peer-reviewed articles to assess trends in automated CT scoring techniques for assessing structural lung changes in patients with CF and PCD, identify the existing challenge to develop clinical grade systems, and propose future research directions to advance the existing research towards mature technology. The results reveal that the attention given to this topic is relatively low both from the algorithmic development perspective and in terms of data availability. Among the included studies, only two focused on PCD. Furthermore, no regulatory-approved solutions were reported so far. This manuscript summarizes the existing progress, the trends compared to relevant fields, the research gaps and the future research avenues. It provides valuable insights for researchers and clinicians on the pathway to developing a fully automated and clinical-grade scoring system for structural lung disease in CF and PCD evaluation. Clinical trial number: Not applicable.