文献速递乳腺技术与安全MR

传统影像组学、深度学习影像组学及融合方法预测乳腺癌腋窝淋巴结转移的比较

Comparison of Traditional Radiomics, Deep Learning Radiomics and Fusion Methods for Axillary Lymph Node Metastasis Prediction in Breast Cancer.
PubMed 文献 · Acad Radiol · 2022-11-11

本研究基于3062张DCE-MRI图像提取手工影像组学特征与深度学习特征,构建传统影像组学模型、深度学习影像组学模型及两种融合策略的融合模型,用于评估乳腺癌腋窝淋巴结状态。决策级融合模型AUC达0.91(95%CI 0.879-0.937),高于传统影像组学模型和深度学习影像组学模型;决策融合模型结合临床特征后AUC达0.93(95%CI 0.899-0.951),也优于其他结合临床特征的模型。研究表明融合模型对预测乳腺癌腋窝淋巴结转移有效。

要点

  • 决策级融合模型预测腋窝淋巴结转移AUC为0.91,优于单一组学模型。
  • 决策融合模型结合临床特征后AUC提升至0.93,为所有模型中最高。
  • 融合策略可整合手工组学与深度学习特征,提升无创评估腋窝淋巴结状态效能。

核心结论

  • 决策级融合模型整合影像组学特征与深度学习特征,预测乳腺癌腋窝淋巴结转移的AUC为0.91(95%CI 0.879-0.937),高于传统影像组学模型和深度学习影像组学模型。
  • 决策融合模型结合临床特征后AUC为0.93(95%CI 0.899-0.951),也优于其他结合临床特征的模型。
  • 融合模型对预测乳腺癌腋窝淋巴结转移有效。

研究设计与样本

  • 研究从3062张DCE-MRI图像中提取手工影像组学特征和深度学习特征。
  • 采用互信息和特征递归消除算法进行特征选择。
  • 传统影像组学模型和深度学习影像组学模型分别使用最优特征和机器学习分类器构建。
  • 采用两种融合策略构建融合模型以区分腋窝淋巴结状态。
  • 比较各模型与MRI报告的淋巴结病变或可疑淋巴结评估腋窝淋巴结状态的性能。

诊断标准与关键数值

  • 决策融合模型(在决策层面整合影像组学特征与深度学习特征)预测腋窝淋巴结转移的AUC为0.91(95%CI 0.879-0.937)。
  • 决策融合模型结合临床特征后AUC为0.93(95%CI 0.899-0.951)。

临床应用与阅片要点

  • 在DCE-MRI影像组学分析中,可考虑采用决策级融合策略整合手工特征与深度学习特征以提升腋窝淋巴结转移预测效能。
  • 结合临床特征构建融合模型可能进一步改善预测性能。

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: Accurate identification of axillary lymph node (ALN) status in breast cancer patients is important for determining treatment options and avoiding axillary overtreatments. Our study aims to comprehensively compare the performance of the traditional radiomics model, deep learning radiomics model, and the fusion models in evaluating breast cancer ALN status based on dynamic contrast-enhanced-magnetic resonance imaging (DCE-MRI) images.

MATERIALS AND METHODS: The handcrafted radiomics features and deep features were extracted from 3062 DCE-MRI images. The feature selection was performed by applying mutual information and feature recursive elimination algorithms. The traditional radiomics model and deep learning radiomics model were built using the optimal features and machine learning classifiers, respectively. The fusion models for distinguishing axillary lymph node status were constructed using two fusion strategies. The performance of the models with MRI-reported lymphadenopathy or suspicious nodes to evaluate axillary lymph node status was also compared.

RESULTS: The decision fusion model, with the integration of the radiomics features and deep learning features at the decision level, achieved an area under the curve (AUC) of 0.91 (95% confidence interval (CI): 0.879-0.937), which was higher than that of the traditional radiomics model and deep learning radiomics model. The results of the decision fusion model with clinical characteristic yielded an AUC of 0.93 (95% CI: 0.899-0.951), which was also superior to other models incorporating clinical characteristic.

CONCLUSION: This study demonstrates the effectiveness of the fusion models for predicting axillary lymph node metastasis in breast cancer.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Li, Yang, Jiao, et al. Comparison of Traditional Radiomics, Deep Learning Radiomics and Fusion Methods for Axillary Lymph Node Metastasis Prediction in Breast Cancer. Acad Radiol. 2022. PMID: 36376154. doi:10.1016/j.acra.2022.10.015

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。