Objectives: Deep learning-based artificial intelligence (AI) tools have been gradually used to detect and segment pulmonary nodules in clinical practice. This study aimed to assess the diagnostic performance of quantitative measures derived from a commercially available AI software for predicting the invasiveness of pulmonary adenocarcinomas that manifested as pure ground-glass nodules (pGGNs) on low-dose CT (LDCT) in lung cancer screening. Methods: A total of 388 pGGNs were consecutively enrolled and divided into a training cohort (198 from center 1 between February 2019 and April 2022), testing cohort (99 from center 1 between April 2022 and March 2023), and external validation cohort (91 from centers 2 and 3 between January 2021 and August 2023). The automatically extracted quantitative measures included diameter, volume, attenuation, and mass. The diameter was also manually measured by radiologists. The agreement of diameter between AI and radiologists was evaluated by intra-class correlation coefficient (ICC) and Bland-Altman method. The diagnostic performance was evaluated by the area under curve (AUC) of receiver operating characteristic curve. Results: The ICCs of diameter between AI and radiologists were from 0.972 to 0.981 and Bland-Altman biases were from -1.9% to -2.3%. The mass showed the highest AUCs of 0.915 (0.867-0.950), 0.913 (0.840-0.960), and 0.893 (0.810-0.948) in the training, testing, and external validation cohorts, which were higher than those of diameters of radiologists and AI, volume, and attenuation (all p < 0.05). Conclusions: The automated measurement of pGGNs diameter using the AI software demonstrated comparable accuracy to that of radiologists on LDCT images. Among the quantitative measures of diameter, volume, attenuation, and mass, mass was the most optimal predictor of invasiveness in pulmonary adenocarcinomas on LDCT, which might be used to assist clinical decision of pGGNs during lung cancer screening.