Imaging-based development and validation of artificial intelligence models for lung adenocarcinoma precursor lesions and early lung adenocarcinoma presenting as pulmonary nodules.
Authors
Affiliations (5)
Affiliations (5)
- Department of Pulmonary and Critical Care Medicine, Huashan Hospital, Fudan University, Shanghai, China.
- Department of Pulmonary and Critical Care Medicine, Peking University Shenzhen Hospital, Shenzhen, China.
- Shenzhen University Medical School, Shenzhen, China.
- Department of Radiotherapy Oncology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
- Department of Radiation Oncology, Sichuan Cancer Hospital and Institute, University of Electronic Science and Technology of China, Chengdu, China.
Abstract
Accurate preoperative assessment of pulmonary nodule invasiveness remains challenging. We developed an internally validated multimodal framework integrating CT representations from a frozen vision foundation model with clinical variables. This retrospective single-centre study included 1,179 pathologically confirmed pulmonary nodules: 247 glandular precursor lesions comprising atypical adenomatous hyperplasia and adenocarcinoma <i>in situ</i>, and 932 invasive lesions comprising minimally invasive and invasive adenocarcinoma. CT volumes were resampled to 0.5-mm isotropic resolution and cropped into 64 × 64 × 64-voxel patches. Slice-level representations were extracted using a pretrained, frozen DINOv3 backbone and aggregated by a trainable Attention Probe. Encoded clinical variables and imaging representations were integrated through self-attention and bidirectional cross-attention, followed by neural classification and regression tree classification. Internal validation used a five-fold rotating train-validation-test procedure, with each fold serving once as the held-out test fold. The held-out test-fold AUCs were 0.848, 0.864, 0.867, 0.882, and 0.822, yielding a mean AUC of 0.8566. Pooled out-of-fold predictions produced an AUC of 0.847, accuracy of 0.809, sensitivity of 0.806, specificity of 0.822, and F1 score of 0.873. DINOv3 and NCART achieved the highest point-estimate AUCs among the evaluated feature extractors and classifiers, respectively, although most pairwise differences were not statistically significant. Intermediate fusion significantly outperformed the Gould score and the clinical-data-only model, but not the imaging-only or late-fusion models. In the prespecified secondary analysis, the model achieved an AUC of 0.780 for distinguishing adenocarcinoma <i>in situ</i> from atypical adenomatous hyperplasia. The proposed framework achieved internally validated discrimination of pulmonary nodule invasiveness. External multicentre and prospective validation is required before clinical implementation.