Volume-related structures predict UIP pathology in those with a non-IPF pattern on CT

Objectives To determine if a quantitative imaging variable (volume-related structures [VRS]) could identify subjects with a non-IPF diagnosis CT pattern who were highly likely to have UIP histologically. Methods Subjects with a multidisciplinary diagnosis of interstitial lung disease including surgical lung biopsy and chest CT within 1 year of each other were included in the study. Non-contrast CT scans were analyzed using the Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) program, which quantifies the amount of various abnormal CT patterns on chest CT. Quantitative data were analyzed relative to pathological diagnosis as well as the qualitative CT pattern. Results CALIPER-derived volumes of reticulation (p = 0.012), honeycombing (p = 0.017), and VRS (p < 0.001) were associated with a UIP pattern on pathology on univariate analysis but only VRS was associated with a UIP pathology on multivariable analysis (p = 0.013). Using a VRS cut-off of 173 cm(3), the sensitivity and specificity for pathological UIP were similar to those for standard qualitative CT assessment (55.9% and 80.4% compared to 60.6% and 80.4%, respectively). VRS differentiated pathological UIP cases in those with a non-IPF diagnosis CT category (p < 0.001) but not in other qualitative CT patterns (typical UIP, probable UIP, and indeterminate for UIP). The rate of pathological UIP in those with VRS greater than 173 cm(3) (84.2%) was nearly identical to those who had a qualitative CT pattern of probable UIP (88.9%). Conclusions VRS may be an adjunct to CT in predicting pathology in patients with interstitial lung disease.

Automated summary

The study indicates that VRS can differentiate patients with UIP histological features from non-IPF diagnosis in CT images, showing predictive value. The sensitivity and specificity of VRS in predicting pathological UIP are comparable to standard qualitative CT assessment.