Improving prediction accuracy of spread through air spaces in clinical-stage T1N0 lung adenocarcinoma using computed tomography imaging models

Objectives We developed computed tomography (CT)- based models to increase the prediction accuracy of spread through air spaces (STAS) in clinical-stage T1N0 lung adenocarcinoma. Methods Three cohorts of patients with stage T1N0 lung adenocarcinoma (N = 1258) were retrospectively analyzed. Two models utilizing radiomics and deep neural networks (DNNs) were established to predict the lung adenocarcinoma STAS status. For the radiomic models, features were extracted using PyRadiomics, and 10 features with non-zero coefficients were selected using the least absolute shrinkage and selection operator (LASSO) regression to construct the models. For the DNN models, a two-stage (supervised contrastive learning and fine-tuning) deep-learning model named MultiCL was constructed using CT images and the STAS status as training data. The area under the curve (AUC) was used to verify the predictive ability of both model types for the STAS status. Results Among the radiomic models, the linear discriminant analysis model exhibited the best performance, with AUC values of 0.8944 (95% CI: 0.8241–0.9502) and 0.7796 (95% CI: 0.7089–0.8448) for predicting the STAS status on the test and external validation cohorts, respectively. Among the DNN models, MultiCL exhibited the best performance, with AUC values of 0.8434 (95% CI: 0.7580–0.9154) and 0.7686 (95% CI: 0.6991–0.8316) on the test and external validation cohorts, respectively. Conclusion CT-based imaging models (radiomics and DNNs) can accurately identify the STAS status of clinical-stage T1N0 lung adenocarcinoma, potentially guiding surgical decision-making and improving patient outcomes.