文献速递头颈US

多特征融合网络在灰阶超声中的应用:有效鉴别腺淋巴瘤与多形性腺瘤

Multi-feature Fusion Network on Gray Scale Ultrasonography: Effective Differentiation of Adenolymphoma and Pleomorphic Adenoma.
PubMed 文献 · Acad Radiol · 2024-06-12

本研究基于两个中心287例经组织学确诊的腮腺多形性腺瘤或腺淋巴瘤患者的灰阶超声图像,构建整合深度学习特征、影像组学特征和临床特征的多特征融合网络(DLRN)。DLRN模型在内部验证队列和外部验证队列的AUC均为0.908,区分能力优于临床、影像组学、深度迁移学习和深度学习影像组学模型。

要点

  • DLRN模型在内部和外部验证队列AUC均为0.908,优于其他模型。
  • 模型整合了灰阶超声的深度学习特征、影像组学特征和临床特征。
  • 研究纳入两个中心共287例经组织学确诊的腮腺肿瘤患者。

核心结论

  • 基于灰阶超声构建的DLRN模型显著提高了良性唾液腺肿瘤的诊断性能,可提供无创且准确的诊断方法,具有重要临床意义和价值;与单独使用Resnet50相比,多模型集成有助于缓解小数据集上的过拟合。

研究设计与样本

  • 研究纳入两个中心共287例经组织学确诊的腮腺多形性腺瘤或腺淋巴瘤患者,其中训练队列162例、内部验证队列70例、外部验证队列55例。

诊断标准与关键数值

  • 内部验证队列AUC:DLRN模型0.908,DLR模型0.863,Rad模型0.841,Clinic模型0.767,DTL模型0.740。
  • 外部验证队列AUC:DLRN模型0.908,DLR模型0.859,DTL模型0.825,Clinic模型0.777,Rad模型0.748。

临床应用与阅片要点

  • 作者认为DLRN模型可基于灰阶超声提供无创且准确的诊断方法,具有重要临床意义和价值。
  • 作者指出与单独使用Resnet50相比,多模型集成有助于缓解小数据集上的过拟合。

局限性

  • 作者指出与单独使用Resnet50相比,多模型集成有助于缓解小数据集上的过拟合。

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 a deep learning radiomics graph network (DLRN) that integrates deep learning features extracted from gray scale ultrasonography, radiomics features and clinical features, for distinguishing parotid pleomorphic adenoma (PA) from adenolymphoma (AL) MATERIALS AND METHODS: A total of 287 patients (162 in training cohort, 70 in internal validation cohort and 55 in external validation cohort) from two centers with histologically confirmed PA or AL were enrolled. Deep transfer learning features and radiomics features extracted from gray scale ultrasound images were input to machine learning classifiers including logistic regression (LR), support vector machines (SVM), KNN, RandomForest (RF), ExtraTrees, XGBoost, LightGBM, and MLP to construct deep transfer learning radiomics (DTL) models and Rad models respectively. Deep learning radiomics (DLR) models were constructed by integrating the two features and DLR signatures were generated. Clinical features were further combined with the signatures to develop a DLRN model. The performance of these models was evaluated using receiver operating characteristic (ROC) curve analysis, calibration, decision curve analysis (DCA), and the Hosmer-Lemeshow test.

RESULTS: In the internal validation cohort and external validation cohort, comparing to Clinic (AUC=0.767 and 0.777), Rad (AUC=0.841 and 0.748), DTL (AUC=0.740 and 0.825) and DLR (AUC=0.863 and 0.859), the DLRN model showed greatest discriminatory ability (AUC=0.908 and 0.908) showed optimal discriminatory ability.

CONCLUSION: The DLRN model built based on gray scale ultrasonography significantly improved the diagnostic performance for benign salivary gland tumors. It can provide clinicians with a non-invasive and accurate diagnostic approach, which holds important clinical significance and value. Ensemble of multiple models helped alleviate overfitting on the small dataset compared to using Resnet50 alone.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Mao Y, Jiang LP, Wang JL, et al. Multi-feature Fusion Network on Gray Scale Ultrasonography: Effective Differentiation of Adenolymphoma and Pleomorphic Adenoma. Acad Radiol. 2024. PMID: 38871552. doi:10.1016/j.acra.2024.05.023

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。