Radiomic model with SHAP-based interpretability for predicting invasiveness of pure ground-glass nodules: a retrospective study based on high-resolution computed tomography (HRCT) volumetric datasets.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Yantaishan Hospital, Yantai, 264000, Shandong, China.
- Department of Respiratory Medicine, Dongying Hospital of Traditional Chinese Medicine, Dongying, 257000, Shandong, China.
- Department of Radiology, Shengli Oilfield Central Hospital, Dongying, 257000, China. [email protected].
- Department of Radiology, Yantai Yuhuangding Hospital, Tianjin, 264000, Shandong, China.
- Department of Radiology, Tianjin Beichen Traditional Chinese Medicine Hospital, Tianjin, 300400, China.
Abstract
Radiomics holds promise for lung cancer diagnosis. This study developed an interpretable radiomics-clinical model to predict the invasiveness of pure ground-glass nodules (pGGNs) on high-resolution computed tomography (HRCT). To address the model's "black box" nature, we applied the SHapley Additive exPlanations (SHAP) framework. We retrospectively analyzed 235 surgically resected, histopathologically confirmed pGGNs, classified as non-invasive (AAH/AIS/MIA) or invasive (IAC) according to the 2015 WHO classification of lung tumors. We developed three prediction models: clinical, radiomic, and combined. Feature selection for the radiomic and combined models employed LASSO regression. Model performance was assessed using AUC, calibration curves, and decision curve analysis (DCA). Additionally, SHAP was used to quantify feature importance and to generate individualized explanations. Two clinico-radiological features (mean CT value, VolumePercent₋₃₀₀) and eight radiomic features were retained. The combined model yielded AUCs of 0.923 (training) and 0.832 (testing), outperforming the clinical model (0.799/0.733) and the radiomic model (0.917/0.827). Decision curve analysis (DCA) confirmed the superior clinical utility of the combined model. SHAP analysis ranked log_sigma_2_0mm_3D_firstorder_Range as the single most important predictive feature. The SHAP-augmented radiomics-clinical model offers an accurate and interpretable preoperative assessment of pGGN invasiveness. This tool can help clinicians choose the optimal surgical strategy and support individualized decision-making.