2026-10-11T21:18:57Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33771772 2026-09-15T05:35:14Z category_450 portal_316 item_type_3 month_year_09_2026

Data Sheet 1_Imaging-based development and validation of artificial intelligence models for lung adenocarcinoma precursor lesions and early lung adenocarcinoma presenting as pulmonary nodules.docx Junbao Zhang (15406312) Yanyi Hou (24912580) Yikang Yang (24141972) Ziyan Zhang (800393) Yi Gao (112914) Ping Xu (122619) Knowledge Representation and Machine Learning DINOv3 invasiveness prediction lung adenocarcinoma multimodal learning pulmonary nodules Background<p>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.</p>Methods<p>This retrospective single-centre study included 1,179 pathologically confirmed pulmonary nodules: 247 glandular precursor lesions comprising atypical adenomatous hyperplasia and adenocarcinoma in situ, 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.</p>Results<p>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 in situ from atypical adenomatous hyperplasia.</p>Conclusion<p>The proposed framework achieved internally validated discrimination of pulmonary nodule invasiveness. External multicentre and prospective validation is required before clinical implementation.</p> 2026-09-15T05:35:14Z Dataset Dataset 10.3389/frai.2026.1889248.s001 https://figshare.com/articles/dataset/Data_Sheet_1_Imaging-based_development_and_validation_of_artificial_intelligence_models_for_lung_adenocarcinoma_precursor_lesions_and_early_lung_adenocarcinoma_presenting_as_pulmonary_nodules_docx/33771772 CC BY 4.0