文献速递胸部CT

基于CT图像的多时间序列深度学习模型用于肺磨玻璃结节良恶性的纵向预测

Deep learning model using CT images for longitudinal prediction of benign and malignant ground-glass nodules.
PubMed 文献 · Eur J Radiol · 2025-06-18

研究纳入两个医疗中心486例经手术病理证实的肺磨玻璃结节,按7:2:1随机分为训练集、验证集和测试集,构建基于Transformer的多时间序列CT深度学习模型区分良恶性。该模型在训练集、验证集和测试集的AUC分别为0.911、0.809和0.817,优于临床模型和Δ影像组学模型;融合深度学习与CT语义特征的联合模型表现最佳,三个集AUC分别为0.960、0.878和0.890。

要点

  • 多时间序列深度学习模型可纵向预测肺磨玻璃结节良恶性,测试集AUC为0.817。
  • 融合深度学习与CT语义特征的联合模型三个集AUC分别为0.960、0.878和0.890。
  • 深度学习模型性能超过临床模型和Δ影像组学模型。

核心结论

  • 基于CT图像的多时间序列深度学习模型能有效预测肺磨玻璃结节的良恶性。

研究设计与样本

  • 多时间序列深度学习模型开发与验证研究,纳入两个医疗中心的486个肺磨玻璃结节(来自等量患者),每个结节均经手术切除并病理证实,按7:2:1随机分为训练集、验证集和测试集。

诊断标准与关键数值

  • 多时间序列深度学习模型训练集AUC 0.911(95%CI 0.879-0.939),验证集AUC 0.809(95%CI 0.715-0.908),测试集AUC 0.817(95%CI 0.680-0.937)。
  • 融合深度学习与CT语义特征的联合模型训练集AUC 0.960(95%CI 0.912-0.977),验证集AUC 0.878(95%CI 0.801-0.942),测试集AUC 0.890(95%CI 0.790-0.968)。
  • 多时间序列深度学习模型在训练集、验证集和测试集的预测能力均超过临床模型和Δ影像组学模型。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: 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).

METHODS: 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).

RESULTS: 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).

CONCLUSION: The multiple time-series deep learning model utilizing CT images was effective in predicting benign and malignant GGNs.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Yang X, Wang J, Wang P, et al. Deep learning model using CT images for longitudinal prediction of benign and malignant ground-glass nodules. Eur J Radiol. 2025. PMID: 40544718. doi:10.1016/j.ejrad.2025.112252

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。