文献速递乳腺技术与安全US

基于超声射频时间序列与二维图像特征的机器学习在乳腺BI-RADS 4A类病变诊断中的应用

Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI-RADS 4A Lesions of Breast.
PubMed 文献 · J Ultrasound Med · 2025-10-23

本研究利用130个BI-RADS 4A类乳腺病变的射频信号、二维超声特征和病理诊断构建并验证机器学习模型,其中逻辑回归模型曲线下面积最高(0.81,95%CI 0.66-1.00),各模型间无统计学显著差异。人工智能辅助诊断可提高不同年资医师的诊断准确率(P < .05),尤其对低年资医师提升明显。

要点

  • 逻辑回归模型鉴别BI-RADS 4A类乳腺病变的AUC为0.81(95%CI 0.66-1.00),各模型间无统计学显著差异。
  • AI辅助使低年资(≤3年)医师准确率从27.28%升至52.28%,高年资(≥10年)从63.63%升至81.91%。
  • 融合射频时间序列与二维图像特征有望减少不必要的活检,尤其对经验较少的临床医生。

核心结论

  • 融合射频时间序列与二维图像特征的逻辑回归模型展现出提高诊断精度、减少不必要活检的潜力,尤其对经验较少的临床医生。

研究设计与样本

  • 研究纳入130个BI-RADS 4A类乳腺病变(128例患者)的射频信号、二维超声特征及病理诊断,评估逻辑回归、支持向量机、k近邻和梯度提升四种机器学习模型。

诊断标准与关键数值

  • 从31个特征(28个射频衍生特征和5个二维图像特征)中筛选出6个关键特征;逻辑回归模型AUC最高为0.81(95%CI 0.66-1.00),各模型间DeLong检验P > .05。

临床应用与阅片要点

  • 人工智能辅助诊断可提高不同年资医师的诊断准确率(P < .05):低年资(≤3年)52.28% vs 基线27.28%,中等年资(4-10年)79.54% vs 45.46%,高年资(≥10年)81.91% vs 63.63%。

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

OBJECTIVES: This study aimed to develop and validate machine-learning (ML) models that integrate ultrasonic radiofrequency (RF) time-series signals with gray-scale image features for the preoperative differentiation of breast lesions classified as category 4A of the Breast Imaging Reporting and Data System.

METHODS: A dataset comprising RF signals, 2D ultrasound features, and pathological diagnoses from 130 BI-RADS 4A lesions (128 patients) was analyzed. Five ML models (logistic regression [LR], support vector machine [SVM], k-nearest neighbor [k-NN], and gradient boosting [GB]) were evaluated.

RESULTS: Among 31 features (28 RF-derived and 5 2D image features), 6 key features were selected through feature selection. The LR model achieved the highest area under the curve (0.81, 95% confidence interval: 0.66-1.00), though no statistically significant differences were observed among models (DeLong test, p > .05). Artificial intelligence-assisted diagnosis improved accuracy across physician seniority levels (p < .05): junior (≤3 years: 52.28% versus baseline 27.28%), intermediate (4-10 years: 79.54% versus 45.46%), and senior (≥10 years: 81.91% versus 63.63%).

CONCLUSION: The integration of RF time series and 2D features via LR demonstrates potential to reduce unnecessary biopsies by enhancing diagnostic precision, particularly for less experienced clinicians.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Guo R, Wang Z, Cao X, et al. Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI-RADS 4A Lesions of Breast. J Ultrasound Med. 2025. PMID: 41128617. doi:10.1002/jum.70097

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。