文献速递骨肌神经MR

基于常规MRI的深度学习与Transformer特征融合鉴别脊柱溶骨性骨转移瘤和多发性骨髓瘤

Deep learning and transformer-based feature fusion of conventional MRI for differentiating spinal osteolytic bone metastases and multiple myeloma.
PubMed 文献 · Eur J Radiol · 2025-10-02

回顾性纳入两个医疗中心663例患者(骨转移瘤342例、多发性骨髓瘤321例),利用T1WI、T2WI和T2WI-fs序列提取深度学习特征并比较单序列与融合模型。外部测试集中Transformer融合模型(T2WI+T2WI-fs)表现最佳,AUC为0.783,但各模型间差异无统计学意义(均P>0.05)。作者认为基于常规MRI的Transformer特征融合可实现无创鉴别。

要点

  • 单序列模型中T2WI-fs表现最佳,AUC为0.765、准确率为0.726。
  • 融合模型中T2WI+T2WI-fs_Transformer表现最佳,AUC为0.783、准确率为0.723。
  • 外部测试集中各模型间差异均无统计学意义(均P>0.05)。

核心结论

  • 作者认为基于常规MRI序列的Transformer特征融合可实现脊柱溶骨性骨转移瘤与多发性骨髓瘤的准确无创鉴别,具有显著临床实用性。

研究设计与样本

  • 回顾性研究,纳入两个医疗中心663例患者(平均年龄62.13±9.57岁,男性378例),其中骨转移瘤342例、多发性骨髓瘤321例。
  • 所有患者均行MRI检查,序列包括T1WI、T2WI和T2WI-fs。
  • 采用DenseNet169提取深度学习特征,构建MLP、SVM、梯度提升、AdaBoost和朴素贝叶斯分类模型。
  • 应用特征级融合和Transformer融合两种方法,模型训练集421例、外部测试集242例。
  • 采用ROC曲线、校准曲线和决策曲线分析(DCA)评估性能,以AUC为主要评价指标,Delong检验比较模型性能。

诊断标准与关键数值

  • 单序列模型中T2WI-fs表现最佳,AUC为0.765、准确率为0.726。
  • 融合模型中T2WI+T2WI-fs_Transformer表现最佳,AUC为0.783、准确率为0.723。
  • T2WI+T2WI-fs_early融合模型AUC为0.762。
  • 外部测试集中各模型间差异均无统计学意义(均P>0.05)。

临床应用与阅片要点

  • 作者认为Transformer融合模型具有更优的临床净获益和稳健的泛化能力。

局限性

  • 外部测试集中各模型间差异均无统计学意义(均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)。

英文原文(摘要)· 点击展开

OBJECTIVE: To develop a deep learning model utilizing conventional MRI sequences integrated with Transformer-based feature fusion to differentiate spinal osteolytic bone metastases (OBM) from multiple myeloma (MM).

MATERIALS AND METHODS: This retrospective study included 663 patients (mean age: 62.13 ± 9.57 years; 378 males) from two medical centers, comprising 342 cases of OBM and 321 cases of MM. All patients underwent MRI examinations with T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and fat-suppressed T2-weighted imaging (T2WI-fs) sequences. Deep learning features were extracted with DenseNet169 to construct classification models, including Multilayer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boosting, AdaBoost, and Naive Bayes. Both feature-level fusion and Transformer-based fusion methods were applied to enhance diagnostic performance. Models were trained (n = 421) and externally tested (n = 242). Their performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA), with the AUC serving as the primary evaluation metric. The Delong test was used to compare model performance.

RESULTS: Among the single-sequence models, T2WI-fs achieved the highest performance, with an AUC of 0.765 and an accuracy of 0.726. Among the fusion methods, the T2WI+T2WI-fs_Transformer fusion model performed best, with an AUC of 0.783, an accuracy of 0.723, followed by the T2WI+T2WI-fs_early fusion model (AUC = 0.762). Although the differences among models were not statistically significant in the external test set (all P > 0.05), the Transformer fusion model demonstrated superior clinical net benefit and robust generalizability.

CONCLUSION: Transformer-based feature fusion of conventional MRI sequences enables accurate, non-invasive differentiation between spinal OBM and MM, providing significant clinical utility.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Bian H, Tian N, Zhang Y, et al. Deep learning and transformer-based feature fusion of conventional MRI for differentiating spinal osteolytic bone metastases and multiple myeloma. Eur J Radiol. 2025. PMID: 41176822. doi:10.1016/j.ejrad.2025.112463

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。