Comparison of Usual Interstitial Pneumonia and Nonspecific Interstitial Pneumonia: Quantification of Disease Severity and Discrimination between Two Diseases on HRCT Using a Texture-Based Automated System

Objective: To evaluate the usefulness of an automated system for quantification and discrimination of usual interstitial pneumonia (UIP) and nonspecific interstitial pneumonia (NSIP). Materials and Methods: An automated system to quantify six regional high-resolution CT (HRCT) patterns: normal, NL: ground-glass opacity, GGO: reticular opacity, RO: honeycombing, HC: emphysema, EMPH: and consolidation, CONS, was developed using texture and shape features. Fifty-four patients with pathologically proven UIP (n = 26) and pathologically proven NSIP (n = 28) were included as part of this study. Inter-observer agreement in measuring the extent of each HRCT pattern between the system and two thoracic radiologists were assessed in 26 randomly selected subsets using an interclass correlation coefficient (ICC). A linear regression analysis was used to assess the contribution of each disease pattern to the pulmonary function test parameters. The discriminating capacity of the system between UIP and NSIP was evaluated using a binomial logistic regression. Results: The overall ICC showed acceptable agreement among the system and the two radiologists (r = 0.895 for the abnormal lung volume fraction, 0.706 for the fibrosis fraction, 0.895 for NL, 0.625 for GGO, 0.626 for RO, 0.893 for HC, 0.800 for EMPH, and 0.430 for CONS). The volumes of NL, GGO, RO, and EMPH contribute to forced expiratory volume during one second ($FEV_1$) (r = 0.72, $\beta$ values, 0.84, 0.34, 0.34 and 0.24, respectively) and forced vital capacity (FVC) (r = 0.76, $\beta$ values, 0.82, 0.28, 0.21 and 0.34, respectively). For diffusing capacity ($DL_{CO}$), the volumes of NL and HC were independent contributors in opposite directions (r = 0.65, $\beta$ values, 0.64, -0.21, respectively). The automated system can help discriminate between UIP and NSIP with an accuracy of 82%. Conclusion: The automated quantification system of regional HRCT patterns can be useful in the assessment of disease severity and may provide reliable agreement with the radiologists' results. In addition, this system may be useful in differentiating between UIP and NSIP.