Yang Xiaolong, Wang Jiayang, Wang Ping, Li Yingjie, Wen Zhubin, Shang Jiming, Chen Kaige, Tang Chao, Liang Shuang, Meng Wei
Department of Radiology, Harbin Medical University, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, Heilongjiang 150081, China.
Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing 100035, China.
Eur J Radiol. 2025 Sep;190:112252. doi: 10.1016/j.ejrad.2025.112252. Epub 2025 Jun 18.
To develop and validate a CT image-based multiple time-series deep learning model for the longitudinal prediction of benign and malignant pulmonary ground-glass nodules (GGNs).
A total of 486 GGNs from an equal number of patients were included in this research, which took place at two medical centers. Each nodule underwent surgical removal and was confirmed pathologically. The patients were randomly assigned to a training set, validation set, and test set, following a distribution ratio of 7:2:1. We established a transformer-based deep learning framework that leverages multi-temporal CT images for the longitudinal prediction of GGNs, focusing on distinguishing between benign and malignant types. Additionally, we utilized 13 different machine learning algorithms to formulate clinical models, delta-radiomics models, and combined models that merge deep learning with CT semantic features. The predictive capabilities of the models were assessed using the receiver operating characteristic (ROC) curve and the area under the curve (AUC).
The multiple time-series deep learning model based on CT images surpassed both the clinical model and the delta-radiomics model, showcasing strong predictive capabilities for GGNs across the training, validation, and test sets, with AUCs of 0.911 (95% CI, 0.879-0.939), 0.809 (95% CI,0.715-0.908), and 0.817 (95% CI,0.680-0.937), respectively. Furthermore, the models that integrated deep learning with CT semantic features achieved the highest performance, resulting in AUCs of 0.960 (95% CI, 0.912-0.977), 0.878 (95% CI,0.801-0.942), and 0.890(95% CI, 0.790-0.968).
The multiple time-series deep learning model utilizing CT images was effective in predicting benign and malignant GGNs.
开发并验证一种基于CT图像的多时间序列深度学习模型，用于对良性和恶性肺磨玻璃结节（GGN）进行纵向预测。
本研究纳入了来自两个医疗中心的同等数量患者的486个GGN。每个结节均接受手术切除并经病理证实。患者按照7:2:1的分配比例随机分为训练集、验证集和测试集。我们建立了一个基于Transformer的深度学习框架，该框架利用多期CT图像对GGN进行纵向预测，重点是区分良性和恶性类型。此外，我们使用13种不同的机器学习算法构建临床模型、增量放射组学模型以及将深度学习与CT语义特征相结合的联合模型。使用受试者操作特征（ROC）曲线和曲线下面积（AUC）评估模型的预测能力。
基于CT图像的多时间序列深度学习模型优于临床模型和增量放射组学模型，在训练集、验证集和测试集中对GGN均展现出强大的预测能力，其AUC分别为0.911（95%CI，0.879 - 0.939）、0.809（95%CI，0.715 - 0.908）和0.817（95%CI，0.680 - 0.937）。此外，将深度学习与CT语义特征相结合的模型性能最佳，其AUC分别为0.960（95%CI，0.912 - 0.977）、0.878（95%CI，0.801 - 0.942）和0.890（95%CI，0.790 - 0.968）。
利用CT图像的多时间序列深度学习模型在预测良性和恶性GGN方面是有效的。
