基于经阴道超声影像组学的多模态模型预测卵巢癌腹膜转移风险:一项多中心研究
这项回顾性队列研究纳入619例卵巢癌患者,整合人口学数据、影像组学特征、O-RADS标准化描述、临床生物标志物及组织学结果构建腹膜转移预测模型。影像组学经3D Slicer与Pyradiomics提取、LASSO回归筛选,最终多模态列线图在训练集、内部测试集和外部测试集的AUC分别为0.912、0.883和0.831,诊断效能优于单模态模型。
要点
- 多模态列线图预测卵巢癌腹膜转移,外部测试集AUC为0.831。
- 腹水、输卵管受侵、最大径、HE4及D-二聚体为腹膜转移的显著预测因子。
- 影像组学特征观察者间一致性高,1049个特征经回归分析筛选出7个。
核心结论
- 整合多模态信息(影像组学、O-RADS描述、临床生物标志物及组织学)的腹膜转移预测模型有助提高诊断准确性并指导个体化治疗。
研究设计与样本
- 回顾性队列研究,纳入619例卵巢癌患者,收集人口学数据、影像组学、O-RADS标准化描述、临床生物标志物及组织学结果;影像组学特征经3D Slicer与Pyradiomics提取、LASSO回归筛选,采用逻辑回归与机器学习方法建模并在训练集、内部测试集和外部测试集验证。
关键影像表现/征象
- 腹水、输卵管受侵、最大径、HE4及D-二聚体水平为腹膜转移的显著预测因子。
诊断标准与关键数值
- 影像组学特征观察者间一致性高,初始提取1049个特征,经回归分析筛选出7个特征。
- 多模态影像组学列线图AUC在训练集为0.912、内部测试集为0.883、外部测试集为0.831。
- 列线图诊断效能优于单模态模型。
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
RATIONALE AND OBJECTIVES: This study aimed to develop a predictive model for peritoneal metastasis (PM) in ovarian cancer using a combination radiomics and clinical biomarkers to improve diagnostic accuracy.
PATIENTS AND METHODS: This retrospective cohort study of 619 ovarian cancer patients involved demographic data, radiomics, O-RADS standardized description, clinical biomarkers, and histological findings. Radiomics features were extracted using 3D Slicer and Pyradiomics, with selective feature extraction using Least Absolute Shrinkage and Selection Operator regression. Model development and validation were carried out using logistic regression and machine learning methods RESULTS: Interobserver agreement was high for radiomics features, with 1049 features initially extracted and 7 features selected through regression analysis. Multi-modal information such as Ascites, Fallopian tube invasion, Greatest diameter, HE4 and D-dimer levels were significant predictors of PM. The developed radiomics nomogram demonstrated strong discriminatory power, with AUC values of 0.912, 0.883, and 0.831 in the training, internal test, and external test sets respectively. The nomogram displayed superior diagnostic performance compared to single-modality models.
CONCLUSION: The integration of multimodal information in a predictive model for PM in ovarian cancer shows promise for enhancing diagnostic accuracy and guiding personalized treatment. This multi-modal approach offers a potential strategy for improving patient outcomes in ovarian cancer management with PM.
引用
- Zhou Y, Duan Y, Zhu Q, et al. A Multimodal Model Based on Transvaginal Ultrasound-Based Radiomics to Predict the Risk of Peritoneal Metastasis in Ovarian Cancer: A Multicenter Study. Acad Radiol. 2025. PMID: 39814662. doi:10.1016/j.acra.2024.12.074
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。