Pattern-based volumetric CT quantification to predict radiation pneumonitis in patients with non-small-cell lung cancer who have diffuse parenchymal lung disease.

Background: Diffuse parenchymal lung disease (DPLD) is a well-known risk factor for radiation pneumonitis (RP) after radiation therapy (RT) for lung cancer. However, it is hard to evaluate the exact extent of DPLD and to predict RP. This study sought to quantify the extent of DPLD and to determine which pattern(s) of DPLD lead to RP using texture analysis of pre-treatment computed tomography (CT) scans. Methods: Lung cancer patients with impaired lung function or fibrosis scheduled for proton therapy were prospectively included. Pre-treatment chest CT was assessed, and patterns were classified semi-automatically by quantitative analysis software. Texture patterns included emphysema, ground-glass opacities (GGOs), reticulation, and honeycombing. Univariable and multivariable logistic regression analyses were used to analyze independent risk factors for RP. Results: A total of 54 patients [median age, 71.5 years (range, 57-87 years); 50 men] were enrolled from August 2018 to January 2020. RP of grade ≥3 occurred in seven patients (12.9%). The median extent of emphysematous tissue was 4.8% (range, 0-34.1%), and the median interstitial lung disease (ILD) extent was 5.5% (range, 0-27.3%). During the multivariable analysis, the "sex + total ILD extent" and "sex + total fibrosis extent" models showed the best performance. In the first model, RP of grade ≥3 was associated with female sex and a high total ILD percentage [odds ratios (ORs), 18.0 and 1.2, respectively]. Conclusions: High percentage of lung volume occupied by ILD, especially fibrosis correlates with severe RP.