Filtration-histogram based texture analysis and CALIPER based pattern analysis as quantitative CT techniques in idiopathic pulmonary fibrosis: head-to-head comparison

Abstract

Objective To assess the prognostic performance of two quantitative CT (qCT) techniques in idiopathic pulmonary fibrosis (IPF) compared to established clinical measures of disease severity (GAP index). Methods: Retrospective analysis of high-resolution CT scans for 59 patients (age 70.5 ± 8.8 years) with two qCT methods. Computer-aided lung informatics for pathology evaluation and ratings based analysis classified the lung parenchyma into six different patterns: normal, ground glass, reticulation, hyperlucent, honeycombing and pulmonary vessels. Filtration histogram-based texture analysis extracted texture features: mean intensity, standard deviation (SD), entropy, mean of positive pixels (MPPs), skewness and kurtosis at different spatial scale filters. Univariate Kaplan–Meier survival analysis assessed the different qCT parameters' performance to predict patient outcome and refine the standard GAP staging system. Multivariate cox regression analysis assessed the independence of the significant univariate predictors of patient outcome. Results The predominant parenchymal lung pattern was reticulation (16.6% ± 13.9), with pulmonary vessel percentage being the most predictive of worse patient outcome (p = 0.009). Higher SD, entropy and MPP, in addition to lower skewness and kurtosis at fine texture scale (SSF2), were the most significant predictors of worse outcome (p < 0.001). Multivariate cox regression analysis demonstrated that SD (SSF2) was the only independent predictor of survival (p < 0.001). Better patient outcome prediction was achieved after adding total vessel percentage and SD (SSF2) to the GAP staging system (p = 0.006). Conclusion: Filtration-histogram texture analysis can be an independent predictor of patient mortality in IPF patients. Advances in knowledge: qCT analysis can help in risk stratifying IPF patients in addition to clinical markers.