Artificial intelligence-based density proportion analysis in predicting the invasiveness of neoplastic ground glass nodules

Abstract

Background: A positive correlation has been observed between CT value and the invasiveness of neoplastic ground glass nodules (GGNs). However, the traditional mean CT value cannot reflect nodule heterogeneity in density. Purpose: To explore the value of artificial intelligence (AI)-based density proportion analysis in predicting the invasiveness of neoplastic ground glass nodules (GGNs). Methods: Between January 2019 and May 2023, a total of 687 neoplastic GGNs (247 adenocarcinomas in situ[AISs], 231 minimally invasive adenocarcinomas [MIAs], and 209 invasive adenocarcinomas [IACs]) in 654 patients were retrospectively analyzed. AI software was used to obtain the density histograms of nodules, and subsequently the proportions of the components in lesions with higher density at different density thresholds were recorded. The optimal density threshold and the corresponding proportion cutoff value for determining invasive lesions (ILs) (MIAs and IACs) and IACs were respectively explored by conducting receiver operating characteristic curve analysis. Results: For determining the ILs and IACs, the optimal density threshold and the cutoff value for the proportion of components with density higher than the threshold were ≥ −350 HU and 17.22% (area under the curve [AUC]: 0.801, 95% confidence interval (CI): 0.769–0.830, sensitivity: 51.59%, specificity: 93.52%), and ≥ −250HU and 5.64% (AUC: 0.882, 95% CI: 0.855–0.905; sensitivity: 85.65%, specificity: 76.15%), respectively. In combination with these indicators, the AUCs of the morphological features in predicting ILs and IACs increased from 0.794 to 0.849 and from 0.843 to 0.902 (each P < 0.001), respectively. Conclusion: AI-based density analysis has a potential role in determining the invasiveness of neoplastic GGNs.