Clustering analysis of HRCT parameters measured using a texture-based automated system: relationship with clinical outcomes of IPF

This study investigates the use of automated quantitative analysis of high-resolution CT (HRCT) parameters to predict clinical outcomes in idiopathic pulmonary fibrosis (IPF) patients. HRCT images from 159 IPF patients were analyzed using the AVIEW software (Coreline Soft) to quantify lung texture patterns, including honeycombing, reticulation, emphysema, consolidation, and ground glass opacity. Cluster analysis grouped patients into three clusters based on these parameters. Cluster 1, with the lowest values for all parameters, had the longest survival and relatively well-preserved lung function (FVC and DLCO). Cluster 2, characterized by high reticulation and consolidation scores, had the lowest lung function and the shortest survival, predominantly affecting female patients. Cluster 3 had high honeycombing and emphysema scores, with most patients being male smokers and intermediate survival rates. The study concludes that automated quantitative CT analysis can effectively predict clinical outcomes in IPF and identify high-risk groups for targeted management.