Computed tomography radiomics in growth prediction of pulmonary ground-glass nodules. Issue 159 (February 2023)

• Record Type: Journal Article
• Authors: Sun, Yingli; Ma, Zongjing; Zhao, Wei; Jin, Liang; Gao, Pan; Wang, Kun; Huang, Xuemei; Duan, Shaofeng; Li, Ming
• Is Part Of: European journal of radiology. Issue 159(2023)
• Publication Date: 2023-02
• Subjects: Computed tomography -- Lung cancer -- Ground glass nodules -- Radiomics; ACCP American College of Chest Physicians -- AUC area under the curve -- CI confidence interval -- CT computed tomography -- CTR consolidation tumor ratio -- GGN ground-glass nodule -- GLCM gray level co-occurrence matrix -- GLSZM gray-level size zone matrix -- ICC intraclass correlation coefficient -- LASSO least absolute shrinkage and selection operator -- mRMR minimum redundancy maximum relevance -- NCCN National Comprehensive Cancer Network -- PGGN pure ground-glass nodule -- PSN part-solid nodule -- ROC receiver operating characteristic -- VOI volume of interest; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2022.110684
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: We developed a nomogram model to predict the growth of ground-glass nodules (GGNs) The prediction nomogram model combined radiomics and clinical features. Age, location, and size were independent predictors of GGN growth. The nomogram model achieved good performance for predicting GGN growth. Traditional radiographic features have limited value in predicting GGN growth. Abstract: Purpose: Individualized follow-up of pulmonary ground-glass nodules (GGNs) remains challenging in clinical practice. Accurate prediction of the growth or long-term stability of persistent GGNs is essential to optimize the follow-up intervals. Methods: In this retrospective study, 253 patients with 1115 computed tomography (CT) images were recruited. In total, 1115 CT images were randomized into training (70%) and validation sets (30%). We developed models for the growth or long-term stable prediction of GGNs using radiomics and clinical features. We evaluated the prediction accuracy of the models using receiver operating characteristic (ROC) curve analysis, and the areas under the curve (AUCs) were established. The ROC curves of the models were compared using the DeLong method. Results: The growth and stable groups contained 535 and 580 GGNs, respectively. Traditional radiographic features have limited value in the prediction of growth or long-term stability of GGNs. The prediction nomogram model combining radiomics and clinical features (size, location, and age) yielded the best AUC in both the training and validation sets (AUC = 0.843 and 0.824, respectively). The radiomics model outperformed the clinical model in both sets (AUC: 0.836 vs 0.772 and 0.818 vs 0.735, respectively). The radiomics signature and nomogram model achieved similar AUCs (Delong test, training set: P = 0.09; validation set: P = 0.37). Conclusions: We developed and validated a nomogram model combining radiomics signature, size, age, and location to predict the growth or long-term stability of GGNs. The model achieved good performance and may provide a basis for the improvement of follow-up management of GGNs.