基于[18F]FDG PET/CT与Stacking的非侵入模型预测弥漫大B细胞淋巴瘤双表达
回顾性纳入143例弥漫大B细胞淋巴瘤患者,基于基线[18F]FDG PET/CT提取临床、影像组学与深度学习特征构建模型预测双表达淋巴瘤。测试集中Stacking_LR融合模型AUC达0.948,准确率95.3%,特异度100%,敏感度88.2%,校准与决策曲线分析证实临床净获益。
要点
- 基线PET/CT深度学习影像组学模型可无创识别DLBCL双表达,Stacking融合模型测试AUC 0.948。
- Stacking_LR模型特异度100%、敏感度88.2%,有助于DLBCL风险分层与活检决策。
- SHAP分析显示深度学习特征对模型贡献最大,列线图可直观用于临床。
核心结论
- 基于基线[18F]FDG PET/CT的深度学习影像组学可有效无创识别DLBCL中的双表达淋巴瘤,Stacking集成策略提升多模态融合性能并提供可解释工具。
研究设计与样本
- 回顾性研究,纳入2019年1月至2025年7月143例DLBCL患者(男82例、女61例,中位年龄61.5岁),按7:3随机分为训练集与测试集,行患者水平分析。
- 以2016年WHO免疫组化作为DLBCL诊断与DEL分型的组织病理参考标准。
- 提取临床、影像组学与深度学习特征,经LASSO筛选后构建单模态与融合模型,使用ROC、校准曲线与DCA评估,SHAP与列线图解释。
诊断标准与关键数值
- 测试集中ViT_KNN模型AUC为0.936(95%CI 0.856-1.000),优于临床模型AUC 0.857(95%CI 0.722-0.993)与影像组学模型AUC 0.706(95%CI 0.547-0.865)。
- Stacking_LR融合模型测试集AUC 0.948(95%CI 0.865-1.000),准确率95.3%,特异度100%,敏感度88.2%。
临床应用与阅片要点
- 可利用基线[18F]FDG PET/CT深度学习影像组学模型无创预测DEL,辅助DLBCL风险分层与活检决策。
- Stacking_LR列线图可作为直观临床工具,SHAP提示深度学习特征权重最高,阅片时应关注PET/CT深层纹理与空间特征。
局限性
- 回顾性单中心设计,样本量143例,结论需外部多中心验证。
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: To develop and validate an interpretable multimodal model integrating deep learning radiomics with clinical data using baseline [18F] FDG PET/CT for non-invasive identification of the double-expressor lymphoma (DEL) in diffuse large B-cell lymphoma (DLBCL).
MATERIALS AND METHODS: The histopathological reference standard for DLBCL diagnosis and DEL subtyping was immunohistochemistry according to the 2016 WHO. Patients from January 2019 to July 2025 were retrospectively enrolled and randomly divided into training and test sets at 7:3, and a patient-level analysis was performed. Clinical, radiomics and deep learning features were extracted. After LASSO selection, individual and fusion models were constructed. Statistical analyses were performed using Python (3.6), and p-value < 0.05 was considered significant. Model performance was assessed via receiver operating characteristic (ROC), calibration and decision curve analysis (DCA). SHAP and a nomogram were used for interpretation.
RESULTS: A total of 143 patients (82 males, 61 females, median age 61.5 years) were enrolled. ViT_KNN model achieved a test AUC of 0.936 (95%Cl 0.856-1.000), outperforming clinical (AUC 0.857, 95%Cl 0.722-0.993) and radiomics (AUC 0.706, 95%Cl 0.547-0.865) models. Late fusion, especially Stacking_LR, achieved the best performance (AUC 0.948, 95%Cl 0.865-1.000, accuracy 95.3%, specificity 100%, sensitivity 88.2%). Calibration and DCA confirmed clinical net benefit. SHAP analysis highlighted deep learning features as most influential. The Stacking_LR nomogram offers an intuitive clinical tool.
CONCLUSION: Deep learning radiomics based on baseline [18F] FDG PET/CT enables effective non-invasive identification of DEL. The stacking ensemble strategy enhances multimodal fusion and provides a highly accurate, interpretable tool for DLBCL risk stratification.
引用
- Liang J, Lu G, Zhong Q, et al. Prediction of Double-Expressor Lymphoma in Diffuse Large B-Cell Lymphoma Using a Non-invasive Model Based on [18F] FDG PET/CT and Stacking. Acad Radiol. 2026. PMID: 42934072. doi:10.1016/j.acra.2026.08.091
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。