A pulmonary nodule is worth 8 × 8 × 8 words: computed tomography-based 3D vision transformer predicts early-stage high-grade lung adenocarcinoma of micropapillary and/or solid subtypes

Early-stage high-grade lung invasive adenocarcinoma (IAC) has poor prognosis and is hard to identify using conventional radiological assessment. Current reliance on postoperative histology to identify high-grade subtypes delays risk-adapted surgical planning. 3D vision transformers (ViTs) may improve prediction by modeling long-range dependencies in CT scans. This study aims to develop and validate 3D-ViT and Swin Transformer for preoperative CT-based prediction of early-stage high-grade IAC subtypes (micropapillary/solid), benchmarking against ResNet. A multicenter cohort of 1028 patients with surgically confirmed early-stage lung adenocarcinoma was divided into training (n=806), validation (n=100), and external test (n=122) sets. 3D-ViT, SwinT and ResNet models were trained on CT to classify nodules harboring high-grade histologic patterns. A novel decision-aid tool for IAC surgery was provided. Performance was evaluated using AUC, accuracy, sensitivity, specificity, and precision. Attention mapping was performed to interpret 3D-ViT decision-making. The 3D-ViT model achieved AUC values of 0.856 (95% CI: 0.845, 0.877) (validation) and 0.806 (95% CI: 0.790, 0.816) (testing), compared to 0.854 (95% CI: 0.841, 0.872) (validation) and 0.760 (95% CI: 0.743, 0.776) (testing) for the ResNet baseline. 3D-ViT showed balanced accuracy, sensitivity, specificity and precision in validation set. In external testing, 3D-ViT significantly outperformed ResNet in all metrics with p < 0.01. The SwinT-based AlignSen model from decision-aid tool prioritized sensitivity for high-grade IAC (88.0% validation, 93.4% testing), while maintaining specificity (76.0% validation, 54.1% testing) which significantly outperformed ViT and ResNet-based AlignSen models’ specificity (60.0% and 54% validation, 52.5% and 24.6% testing). Attention maps highlighted 3D nodule heterogeneity and peripheral irregularities. The 3D-ViT model demonstrated robust accuracy and generalizability in predicting high-grade IAC subtypes using CT images. Integration of preoperative Swin Transformer into clinical workflows may offer a viable alternative to intraoperative pathology subtyping, potentially reducing reliance on frozen sections while optimizing surgical planning.