Abstract
BACKGROUND: Interstitial lung disease (ILD) is a determinant of morbidity and mortality in idiopathic inflammatory myopathies (IIM), but chest HRCT evaluation remains observer-dependent. Artificial intelligence (AI) may provide reproducible quantitative assessment. We compared AI-based quantification of ILD with expert visual scoring in IIM. METHODS: In this monocentric retrospective study, 107 patients with IIM-associated ILD from a national myositis registry were included. One representative chest HRCT per patient was evaluated by a thoracic radiologist using a semi-quantitative lobar score and by a commercially available AI tool for lung texture analysis. AI-derived volumes were converted to the same 5-point scale as the visual score. Correlations were assessed with Spearman coefficients and agreement with Cohen’s kappa. RESULTS: All CTs were suitable for visual assessment and 106/107 (99%) for AI analysis. AI identified ground-glass opacities (GGO) as the predominant abnormality, with a lower-lobe predominance. Correlations between AI and radiologist scores were strong for normal lung (r = 0.77) and moderate for GGO (r = 0.64) and consolidation (r = 0.60), but weaker for reticulations (r = 0.34) and honeycombing (r = 0.42). Agreement was good for GGO (κ = 0.70) and consolidation (κ = 0.60), moderate for reticulations (κ = 0.37) and low for honeycombing (κ = 0.16). CONCLUSION: In IIM-associated ILD, AI-based chest HRCT quantification showed good agreement with expert visual assessment, particularly for GGO and consolidation, but was less reliable for complex fibrotic patterns. AI may support more objective and reproducible evaluation of interstitial involvement, as a complement to expert interpretation.