Improved interobserver agreement on nodule type and Lung-RADS classification of subsolid nodules using computer-aided solid component measurement

Abstract

PurposeThe Lung CT Screening Reporting and Data System (Lung-RADS) classification of subsolid nodules (SSNs) can be challenging due to limited interobserver agreement in determining the type and size of the nodule. Our study aimed to assess the effect of a computer-aided method on the interobserver agreement of Lung-RADS classification for SSNs. Materials and methodsThis study consisted of 156 SSNs in 121 patients who underwent initial CT screening for lung cancer. Three independent readers determined the nodule type and measured the size of the entire nodule as well as the solid component, first without and then assisted by a semi-automated computer-aided tool. They assigned to each nodule the corresponding Lung-RADS 1.1 category. Agreement in size measurements was assessed by intraclass correlation coefficient (ICC) and Bland-Altman indexes, while agreement in nodule type and Lung-RADS was determined using Fleiss kappa statistics. The relationship between final diagnosis of the nodules and Lung-RADS classifications was also evaluated. ResultsAmong the 156 nodules, manual size measurement reached an ICC of 0.994, and 48 nodules contained solid component measured by all the three readers both manually and semi-automatically. ICCs for the solid component measurement were 0.952, 0.997 and 0.996 for manual diameter, semi- automated diameter and volume measurement, respectively. Bias and 95% limits of agreement for average diameter of solid component were smaller with semi-automated measurements than with manual measurements. Kappa values of semi-automated assessment for nodule type (0.974) and Lung-RADS classification (0.958 for diameter and 0.952 for volume) were higher than with the manual measurements (0.783 for nodule type and 0.652 for Lung-RADS classification). Compared to manual work, the semi-automated assessment identified more 4B nodules among the 26 pathologically confirmed invasive adenocarcinomas (IACs). ConclusionSemi-automated assessment could improve the interobserver agreement of nodule type and Lung-RADS classification for SSNs, and be inclined to classify SSNs corresponding to pathologically confirmed IACs into higher risk categories.