文献速递肿瘤 PET/CT

整合PET与表格数据的可解释Transformer模型用于滤泡性淋巴瘤组织学分级与预后:一项多机构数字活检研究

An explainable transformer model integrating PET and tabular data for histologic grading and prognosis of follicular lymphoma: a multi-institutional digital biopsy study.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-01-30

本研究回顾性纳入5家独立医院中心的513例滤泡性淋巴瘤(FL)患者,开发整合3D PET肿瘤图像与表格数据的多模态融合Transformer模型用于无创预测FL分级。模型在训练队列AUC为0.964-0.985、准确率90.2-96.7%,验证队列AUC为0.936-0.971、准确率86.4-97.0%,并可有效进行生存风险分层(P < 0.05)。

要点

  • 多模态融合Transformer模型无创预测FL分级,验证队列AUC达0.936-0.971。
  • 融合模型优于单模态模型(AUC 0.974 vs 0.956,准确率89.8% vs 85.8%)。
  • PET图像贡献81-89%的预测价值,模型可进行生存风险分层(P < 0.05)。

核心结论

  • 研究开发了可解释的多模态融合Transformer模型,用于FL的准确分级和预后评估,有潜力辅助临床决策。

研究设计与样本

  • 回顾性纳入5家独立医院中心的513例FL患者,随机分为训练、内部验证和外部验证队列。
  • 开发整合3D PET肿瘤图像与表格数据的多模态融合Transformer模型预测FL分级。
  • 模型配备Grad-CAM、SHAP分析及模态预测贡献比计算等可解释模块,以AUC和准确率评估性能并评估预后价值。

主要发现

  • 训练队列AUC为0.964-0.985,准确率90.2-96.7%;验证队列AUC为0.936-0.971,准确率86.4-97.0%。
  • 消融研究显示融合模型优于单模态模型(AUC 0.974 vs 0.956,准确率89.8% vs 85.8%)。
  • 可解释性分析显示PET图像贡献81-89%的预测价值,Grad-CAM突出肿瘤及瘤周区域。
  • 模型可有效进行生存风险分层(P < 0.05)。

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)。

原文

BACKGROUND: Pathological grade is a critical determinant of clinical outcomes and decision-making of follicular lymphoma (FL). This study aimed to develop a deep learning model as a digital biopsy for the non-invasive identification of FL grade. METHODS: This study retrospectively included 513 FL patients from five independent hospital centers, randomly divided into training, internal validation, and external validation cohorts. A multimodal fusion Transformer model was developed integrating 3D PET tumor images with tabular data to predict FL grade. Additionally, the model is equipped with explainable modules, including Gradient-weighted Class Activation Mapping (Grad-CAM) for PET images, SHapley Additive exPlanations analysis for tabular data, and the calculation of predictive contribution ratios for both modalities, to enhance clinical interpretability and reliability. The predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) and accuracy, and its prognostic value was also assessed. RESULTS: The Transformer model demonstrated high accuracy in grading FL, with AUCs of 0.964-0.985 and accuracies of 90.2-96.7% in the training cohort, and similar performance in the validation cohorts (AUCs: 0.936-0.971, accuracies: 86.4-97.0%). Ablation studies confirmed that the fusion model outperformed single-modality models (AUCs: 0.974 - 0.956, accuracies: 89.8%-85.8%). Interpretability analysis revealed that PET images contributed 81-89% of the predictive value. Grad-CAM highlighted the tumor and peri-tumor regions. The model also effectively stratified patients by survival risk (P < 0.05), highlighting its prognostic value. CONCLUSIONS: Our study developed an explainable multimodal fusion Transformer model for accurate grading and prognosis of FL, with the potential to aid clinical decision-making.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Jiang C, Jiang Z, Zhang Z, et al. An explainable transformer model integrating PET and tabular data for histologic grading and prognosis of follicular lymphoma: a multi-institutional digital biopsy study. Eur J Nucl Med Mol Imaging. 2025. PMID: 39883138. doi:10.1007/s00259-025-07090-9

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。