基于深度学习的多模态分类实现鼻咽癌高效T分期
本研究纳入609例鼻咽癌患者(训练队列487例、验证队列122例),构建整合MRI图像与报告的多模态学习框架,采用ViT提取视觉特征、BERT编码文本特征、Q-Former融合信息,并以分层分类策略(DeepTree)完成T分期。融合图像与文本的Q-Former方法整体表现优于单模态方法,IT-DTM-BLIP2模型准确率0.787(95%CI 0.714-0.860),T2 vs T3/T4的AUC为0.815(0.71-0.900),T3 vs T4的AUC为0.876(0.782-0.945)。作者认为该多模态方法可免去手动勾画肿瘤,简化流程、减少主观性并提供决策支持。
要点
- 融合MRI图像与报告文本的Q-Former多模态模型整体优于单模态方法。
- IT-DTM-BLIP2准确率0.787(95%CI 0.714-0.860),验证队列122例。
- T2 vs T3/T4的AUC为0.815(95%CI 0.71-0.900),T3 vs T4的AUC为0.876(95%CI 0.782-0.945)。
核心结论
- 多模态方法整合MRI图像与报告文本后整体表现良好,提供免手动勾画的自动化T分期方案,可简化工作流程、减少主观性并提供决策支持。
研究设计与样本
- 研究论文;共纳入609例鼻咽癌患者,训练队列487例、验证队列122例;采用多模态学习框架整合MRI图像与报告,自动勾画ROI作为掩膜,ViT提取视觉特征、BERT编码文本特征、Q-Former融合信息,分层分类策略(DeepTree)完成T分期;以准确率、AUC、精确率、敏感度、特异度评价性能。
诊断标准与关键数值
- IT-DTM-BLIP2准确率0.787(95%CI 0.714-0.860);AUC1(T2 vs T3/T4)为0.815(95%CI 0.71-0.900),AUC2(T3 vs T4)为0.876(95%CI 0.782-0.945)。
临床应用与阅片要点
- 作者认为该多模态方法可免去手动肿瘤勾画、简化工作流程、减少主观性,并提供可能改善工作流程效率与一致性的决策支持。
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
BACKGROUND: Accurate T staging of nasopharyngeal carcinoma (NPC) is crucial for precision therapeutic strategies. The T staging process is associated with significant challenges, including time consumption and variability among observers. This study aimed to develop an efficient, automated T staging system that supports personalized treatment and optimizes clinical workflows.
METHODS: A total of 609 NPC patients were included, with 487 in the training cohort and 122 in the validation cohort. We employed a multi-modal learning framework that integrates MRI images and reports. Automatically delineated regions of interest (ROIs) served as masks. A hierarchical classification strategy (DeepTree) addressed complex staging challenges. We utilized Vision Transformer (ViT) to extract visual features and BERT to encode text features. To improve data fusion, we applied a Q-Former to integrate visual and textual information. The performances of the methods were evaluated using accuracy (ACC), the area under the receiver operating characteristic curve (AUC), precision, sensitivity (SEN), and specificity (SPE).
RESULTS: Integrating images and text via Q-Former demonstrated superior performance overall, significantly surpassing single-modality methods. IT-DTM-BLIP2 demonstrated strong performance, achieving an accuracy (ACC) of 0.787 (95% CI 0.714-0.860). The area under the receiver operating characteristic curve (AUC) values were AUC1 (T2 vs. T3/T4) at 0.815 (0.71-0.900) and AUC2 (T3 vs. T4) at 0.876 (0.782-0.945).
CONCLUSION: Our multi-modal approach consistently performs well, offering a robust automated solution that eliminates the need for manual tumor delineation. This streamlines workflows, reduces subjectivity, and offers decision-making support that may improve workflow efficiency and encourage consistency.
引用
- Song D, Han X, Li Y, et al. Efficient T staging in nasopharyngeal carcinoma via deep Learning-Based Multi-Modal classification. Eur J Radiol. 2025. PMID: 40945208. doi:10.1016/j.ejrad.2025.112407
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。