基于超声的影像组学不同机器学习模型鉴别乳腺BI-RADS 4A良恶性病变
研究纳入936例经病理证实的BI-RADS 4A乳腺病变(训练队列655例,测试队列281例),从灰阶超声图像提取影像组学特征,采用逻辑回归、支持向量机、随机森林、XGBoost和多层感知机五种算法构建影像组学模型及联合临床参数的联合模型,并与放射科医师判读比较。影像组学模型训练队列AUC为0.829-0.945、测试队列0.805-0.857;逻辑回归联合模型表现最佳(训练队列AUC 0.909,测试队列0.905),优于放射科医师表现。
要点
- 逻辑回归联合模型鉴别BI-RADS 4A良恶性表现最佳,测试队列AUC 0.905。
- 影像组学模型测试队列AUC 0.805-0.857,联合模型优于医师判读。
- 决策曲线分析示逻辑回归联合模型临床效能优于临床模型和影像组学模型。
核心结论
- 整合影像组学与临床特征的联合模型在鉴别BI-RADS 4A良恶性病变中表现出色,可能提供一种无创高效的辅助临床决策方法。
研究设计与样本
- 共纳入936例经病理证实的BI-RADS 4A病变患者(训练队列n=655,测试队列n=281),从灰阶超声图像提取影像组学特征,采用逻辑回归、支持向量机、随机森林、XGBoost和多层感知机五种算法建模,并以病理为参考标准。
关键影像表现/征象
- 从灰阶超声图像共提取1561个影像组学特征,经降维和特征选择后36个特征被认为显著。
- SHAP方法通过按特征对评估的贡献排序来阐明影像组学模型。
诊断标准与关键数值
- 影像组学模型训练队列AUC为0.829-0.945,测试队列AUC为0.805-0.857。
- 逻辑回归联合模型表现最佳,训练队列AUC 0.909、测试队列AUC 0.905,优于放射科医师表现。
- 该联合模型决策曲线分析示临床效能优于临床模型和影像组学模型。
临床应用与阅片要点
- 作者认为整合影像组学与临床特征的联合模型可能为鉴别BI-RADS 4A良恶性提供无创高效的临床决策辅助方法。
局限性
- 原文未报告局限性。
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 investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions.
METHODS: A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n = 655; test cohort: n = 281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation.
RESULTS: A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models.
CONCLUSIONS: The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.
引用
- Ye J, Chen Y, Pan J, et al. US-based Radiomics Analysis of Different Machine Learning Models for Differentiating Benign and Malignant BI-RADS 4A Breast Lesions. Acad Radiol. 2024. PMID: 39191562. doi:10.1016/j.acra.2024.08.024
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。