Usefulness of Texture Analysis in Differentiating Transient from Persistent Part-solid Nodules(PSNs): A Retrospective Study

Abstract

Background: Early discrimination between transient and persistent par-solid ground-glass nodules (PSNs) at CT is essential for patient management. The objective of our study was to retrospectively investigate the value of texture analysis in differentiating pulmonary transient and persistent PSNs in addition to clinical and CT features. Methods: This retrospective study was performed with IRB approval and a waiver of the requirement for patients' informed consent. From January 2007 to October 2009, we identified 77 individuals (39 men and 38 women; mean age, 55 years) with 86 PSNs on thin-section chest CT. Thirty-nine PSNs in 31 individuals were transient and 47 PSNs in 46 patients were persistent. The clinical, CT, and texture features of PSNs were evaluated. To investigate the additional value of texture analysis in differentiating transient from persistent PSNs, logistic regression analysis and C-statistics were performed. Results: Between transient and persistent PSNs, there were significant differences in age, gender, smoking history, and eosinophil count among the clinical features. As for thin-section CT features, there were significant differences in lesion size, solid portion size, and lesion multiplicity. In terms of texture features, there were significant differences in mean attenuation, skewness of whole PSN, attenuation ratio of whole PSN to inner solid portion, and 5-, 10-, 25-, 50-percentile CT numbers of whole PSN. Multivariate analysis revealed eosinophilia, lesion size, lesion multiplicity, mean attenuation of whole PSN, skewness of whole PSN, and 5-percentile CT number were significant independent predictors of transient PSNs. (P < 0.05) C-statistics revealed that texture analysis incorporating clinical and CT features (AUC, 92.9%) showed significantly higher differentiating performance of transient from persistent PSNs compared with the clinical and CT features alone (AUC, 79.0%). (P = 0.004) Conclusion: Texture analysis of PSNs in addition to clinical and CT features analysis has the potential to improve the differentiation of transient from persistent PSNs.