PurposeThis study is performed to investigate the imaging characteristics of the International Association for the study of lung cancer (IASLC) grade 3 invasive adenocarcinoma (IAC) on PET/CT and the value of PET/CT for preoperative predicting this tumor.Materials and MethodsWe retrospectively enrolled patients with IAC from August 2015 to September 2022. The clinical characteristics, serum tumor markers, and PET/CT features were analyzed. T test, Mann-Whitney U test, χ2test, Logistic regression analysis, and receiver operating characteristic (ROC) analysis were used to predict grade 3 tumor and evaluate the prediction effectiveness.ResultsGrade 3 tumors had a significantly higher maximum standardized uptake value (SUVmax) (P< 0.001), while Grade 1 - 2 tumors were prone to present with air bronchogram sign or vacuole sign (P< 0.001). Multivariate logistic regression analysis revealed that only SUVmax(OR = 1.137; 95% CI: 1.037, 1.247;P< 0.05) and air bronchogram sign or vacuole sign (OR = 0.225; 95% CI: 0.088, 0.572;P< 0.05) were independent predictors for Grade 3 tumors. The established prediction formula for Grade 3 tumors was P = one / [one + EXP (1.112 - 0.187 × SUVmax+ 1.395 × air bronchogram sign or vacuole sign)], which generated a high AUC (0.825) and negative predictive value (0.924), respectively.ConclusionOur study demonstrates that grade 3 IAC has a unique PET/CT imaging feature. The prediction model established with SUVmaxand air bronchogram sign or vacuole sign can effectively predict grade 3 tumors before the operation.