Photo Credit: designer491

The following is a summary of “Automated AI-based image analysis for quantification and prediction of interstitial lung disease in systemic sclerosis patients,” published in the January 2025 issue of the Respiratory Research by Guiot et al.

Systemic sclerosis (SSc) is a rare connective tissue disorder frequently complicated by the development of interstitial lung disease (ILD), a major contributor to morbidity and mortality in affected patients. The ability to predict ILD progression through imaging-based biomarkers remains a critical unmet need, as early identification of patients with high risk could significantly influence clinical management. This study evaluates the potential of an artificial intelligence (AI)-based automated ILD quantification tool, icolung®, to assess ILD burden from chest CT scans and its correlation with pulmonary function decline in patients with SSc-ILD. A retrospective analysis was conducted on a cohort of 75 patients with either limited or diffuse SSc-ILD, including 30 individuals diagnosed with progressive pulmonary fibrosis (PPF). Image-based quantification revealed that patients with PPF exhibited significantly higher ILD lesion burden, measured as a percentage of total lung volume (TLV), compared to patients with no PPF(3.93% [0.36–8.12] vs. 0.59% [0.09–3.53], respectively; p < 0.05). 

Furthermore, pulmonary function testing demonstrated a significant reduction in forced vital capacity (FVC) in patients with PPF (77 ± 20% vs. 87 ± 19%, p < 0.05), reinforcing the association between increased ILD burden and functional decline. Longitudinal analysis revealed a strong inverse correlation between AI-derived ILD quantification and changes in FVC (r = -0.40, p < 0.01) and diffusing capacity of the lungs for carbon monoxide (DLCO) (r = -0.40, p < 0.01), underscoring the potential of this imaging tool for tracking disease progression. These findings suggest that automated CT-based ILD assessment may serve as a valuable biomarker for monitoring SSc-ILD and predicting disease trajectory. However, further multicenter validation studies are necessary to confirm its clinical utility in guiding treatment strategies and improving patient outcomes.

Source: respiratory-research.biomedcentral.com/articles/10.1186/s12931-025-03117-9