文献速递乳腺US

基于自动乳腺全容积扫描图像优化的影像组学模型鉴别乳腺良恶性病变:机器学习方法比较

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions: Comparison of Machine Learning Methods: Comparison of Machine Learning Methods.
PubMed 文献 · J Ultrasound Med · 2021-10-05

研究纳入200例接受ABVS检查的乳腺病变患者,从轴位和冠状面图像提取208个影像组学特征,比较不同特征选择与分类器组合构建的模型。递归特征消除联合支持向量机在轴位与冠状面联合时表现最优,平均AUC为0.857,敏感度87.9%、特异度68.2%、准确率80.7%、精确率82.9%。联合平面模型优于单平面模型,结论认为优化模型可为术前鉴别乳腺良恶性病变提供有价值信息,尚需外部验证。

要点

  • ABVS轴位与冠状面联合的影像组学模型鉴别乳腺良恶性病变表现优于单平面模型。
  • 递归特征消除联合支持向量机为最优组合,平均AUC 0.857。
  • 该模型敏感度87.9%、特异度68.2%,特异度相对偏低需注意假阳性。

核心结论

  • 基于ABVS图像优化的影像组学模型可为术前鉴别乳腺良恶性病变提供有价值信息并指导临床治疗。
  • 联合轴位与冠状面的机器学习模型优于单平面模型,递归特征消除联合支持向量机表现最佳。

研究设计与样本

  • 研究纳入200例接受ABVS检查的乳腺病变患者,从轴位和冠状面图像提取208个影像组学特征。
  • 采用递归特征消除、随机森林和卡方检验进行特征选择,以支持向量机、逻辑回归和极端梯度提升作为分类器。
  • 通过5折交叉验证验证模型泛化能力,以AUC、敏感度、特异度、准确率和精确率评价模型性能。

诊断标准与关键数值

  • 轴位与冠状面联合时,递归特征消除联合支持向量机模型平均AUC为0.857±0.058(95%CI 0.763-0.957)。
  • 该最优模型平均敏感度87.9%、特异度68.2%、准确率80.7%、精确率82.9%。

临床应用与阅片要点

  • 阅片时可关注ABVS轴位与冠状面联合提供的影像组学信息,辅助术前乳腺病变良恶性鉴别。
  • 模型特异度68.2%相对偏低,报告时需结合常规影像征象综合判断,避免过度依赖模型假阳性结果。

局限性

  • 原文指出需要进一步外部验证。

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

OBJECTIVES: To develop and test an optimized radiomics model based on multi-planar automated breast volume scan (ABVS) images to identify malignant and benign breast lesions.

METHODS: Patients (n = 200) with breast lesions who underwent ABVS examinations were included. For each patient, 208 radiomics features were extracted from the ABVS images, including axial plane and coronal plane. Recursive feature elimination, random forest, and chi-square test were used to select features. A support vector machine, logistic regression, and extreme gradient boosting were utilized as classifiers to differentiate malignant and benign breast lesions. The area under the curve, sensitivity, specificity, accuracy, and precision was used to evaluate the performance of the radiomics models. Generalization of the radiomics models was verified through 5-fold cross-validation.

RESULTS: For a single plane or a combination of planes, a combination of recursive feature elimination, and support vector machine yielded the best performance when identifying breast lesions. The machine learning models based on a combination of planes performed better than those based on a single plane. Regarding the axial plane and coronal plane, the machine learning model using a combination of recursive feature elimination and support vector machine yielded the optimal identification performance: average area under the curve (0.857 ± 0.058, 95% confidence interval, 0.763-0.957); the average values of sensitivity, specificity, accuracy, and precision were 87.9, 68.2, 80.7, and 82.9%, respectively.

CONCLUSIONS: The optimized radiomics model based on ABVS images can provide valuable information for identifying benign and malignant breast lesions preoperatively and guide the accurate clinical treatment. Further external validation is required.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Wang H, Yang X, Ma S, et al. An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions: Comparison of Machine Learning Methods: Comparison of Machine Learning Methods. J Ultrasound Med. 2021. PMID: 34609750. doi:10.1002/jum.15845

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。