基于MRI深度学习特征联合视觉Transformer预测局部晚期鼻咽癌新辅助化疗疗效
本研究回顾性纳入266例接受标准新辅助化疗的局部晚期鼻咽癌患者,按RECIST 1.1分为CR组和非CR组,按3:1分为训练集和测试集。比较传统影像组学与2D/2.5D/3D深度学习模型,并将最优单模型提取的深度学习特征输入视觉Transformer进行全局上下文建模,融合模型验证AUC达0.926,显著优于既往所有模型(均P<0.05)。
要点
- 融合多序列MRI深度学习特征与视觉Transformer的模型验证AUC为0.926,优于传统影像组学和单一深度学习模型。
- 传统影像组学中T2-FS序列XGBoost模型验证AUC为0.760;深度学习模型中2D模型AUC最低(0.502-0.653),2.5D最佳AUC为0.713,3D最佳AUC为0.755。
- 最优单模型为2.5D-ResNet50和3D-DenseNet121,融合后输入ViT架构进行全局上下文建模。
核心结论
- 联合多序列MRI深度学习特征与视觉Transformer的融合模型显著提升了局部晚期鼻咽癌新辅助化疗疗效的预测性能,验证AUC为0.926、准确率为0.903、F1分数为0.927,显著优于所有既往模型(均P<0.05)。
研究设计与样本
- 回顾性纳入266例接受标准新辅助化疗的局部晚期鼻咽癌患者,按RECIST 1.1分为CR组和非CR组,按3:1分为训练集和测试集,比较传统影像组学与2D/2.5D/3D深度学习模型,选取最优架构作为特征提取器,经PCA降维后输入视觉Transformer。
诊断标准与关键数值
- 采用RECIST 1.1将患者分为CR组和非CR组;传统影像组学中T2-FS序列XGBoost模型验证AUC为0.760;深度学习模型中2D模型AUC为0.502-0.653,2.5D最佳AUC为0.713,3D最佳AUC为0.755;融合模型验证AUC为0.926、准确率为0.903、F1分数为0.927。
局限性
- 本研究为回顾性研究。
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: Predicting neoadjuvant chemotherapy (NACT) efficacy is vital for advanced nasopharyngeal carcinoma (LA-NPC) management. Existing models have limited generalizability. The combination of MRI-based deep learning features (DLF) and Vision Transformer (ViT) for this purpose remains unexplored. This study therefore aims to evaluate the value of multi-sequence MRI-based DLF combined with ViT for predicting NACT efficacy in LA-NPC.
MATERIALS AND METHODS: This study retrospectively enrolled 266 LA-NPC patients receiving standard NACT, categorized by RECIST 1.1 into CR and non-CR groups, and split into training and testing sets (3:1). Traditional radiomics and 2D/2.5D/3D deep learning models were built and compared. Select the optimal architecture as the feature extractor, features were reduced via PCA and input into ViT.
RESULTS: The XGBoost model on T2-FS sequences performed best among traditional radiomics models, with a validation AUC of 0.760. For deep learning models, performance improved with model complexity: 2D models were least effective (AUC: 0.502-0.653), followed by 2.5D (best AUC: 0.713), while 3D models were optimal (best AUC: 0.755). Ultimately, we integrated the deep learning features extracted from the two optimal single models (2.5D-ResNet50 and 3D-DenseNet121) and input them into the ViT architecture for global context modeling. This fused model achieved superior performance, with a validation AUC of 0.926, accuracy of 0.903, and F1-score of 0.927, significantly outperforming all previous models (all P < 0.05).
CONCLUSION: The integrated model combining multi-sequence MRI DLF with ViT significantly enhances predictive performance for NACT efficacy in LA-NPC.
引用
- Yang Y, Mu X, Liu L, et al. Prediction of Neoadjuvant Chemotherapy Efficacy for Locally Advanced Nasopharyngeal Carcinoma Using MRI-Based Deep Learning Features Combined with Vision Transformer. Acad Radiol. 2026. PMID: 41775615. doi:10.1016/j.acra.2026.02.003
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。