Integrating CT-based radiomics and deep learning for invasive prediction of ground-glass nodules in lung adenocarcinoma: a multicohort study.
Authors
Affiliations (10)
Affiliations (10)
- Department of Radiology, Ordos Central Hospital, Ordos, 017000, Inner Mongolia, China.
- Department of Radiology, Affiliated Zhongshan Hospital of Dalian University, Dalian, 116001, Liaoning, China.
- Department of Oncology, Ordos Central Hospital, Ordos, 017000, Inner Mongolia, China.
- Fujian Medical University, Fuzhou, 350001, Fujian, China.
- Department of Radiology, Dalian Public Health Clinical Center, Dalian, 116031, Liaoning, China.
- Department of Radiology, Zhangjiagang Hospital affiliated to Soochow University / The First People's Hospital of Zhangjiagang City, Zhangjiagang, 215600, Jiangsu, China.
- Clinical application department, Zhejiang Yizhun Intelligent Technology Co., Ltd, Lishui, 323010, Zhejiang, China.
- Stem Cell Clinical Research Center, The First Affiliated Hospital of Dalian Medical University, Dalian, 116021, Liaoning, China. [email protected].
- Dalian Innovation Institute of Stem Cell and Precision Medicine, Dalian, 116085, Liaoning, China. [email protected].
- Department of Radiology, Affiliated Zhongshan Hospital of Dalian University, Dalian, 116001, Liaoning, China. [email protected].
Abstract
This study aimed to explore a multiple-instance learning (MIL) framework incorporating radiomics features and deep learning representations to predict the invasiveness of ground-glass nodules (GGNs) in lung adenocarcinoma (LUAD) using preoperative CT. We retrospectively analyzed 1247 GGNs from 1182 LUAD patients across six hospitals, and divided them into training, validation and three test sets. According to postoperative pathological findings, the data were further classified into invasive and non-invasive subgroups. Five kinds of predictive models were developed: radiomics models, 3D deep learning models, 2.5D deep learning models, deep learning-based MIL (MIL-DL) models, and deep learning and radiomics-based MIL (MIL-DL-Rad) models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). The MIL-DL-Rad model with the ExtraTrees classifier exhibited superior and consistent performance across all sets, achieving AUCs of 0.936, 0.881, 0.868, 0.926, and 0.918 in training, validation and external test sets. In contrast, the AUC performance of MIL-DL and radiomics models was relatively unstable. The calibration curve and DCA indicated that the integrated model achieved favorable predictive efficiency and clinical predictive benefits. The MIL-DL-Rad model showed better overall performance for invasiveness prediction of GGNs in LUAD patients, providing a novel perspective on feature fusion that can contribute to more accurate preoperative predictions in clinical practice. Multi-instance learning integrating deep learning and radiomics enhances the prediction of ground-glass nodule (GGN) invasiveness and is expected to provide optimal preoperative clinical decision-making for lung adenocarcinoma patients. Ground-glass nodules invasiveness directly influences surgical strategies and prognosis. Multiple-instance learning framework integrates radiomics and deep learning features. Integrated model achieves superior accuracy and consistency in invasiveness prediction.