文献速递乳腺技术与安全US

基于深度学习的计算机辅助诊断系统用于乳腺病灶分类与分级:射频时间序列动态处理方法的探索

Deep Learning-Based CAD System for Enhanced Breast Lesion Classification and Grading Using RFTSDP Approach.
PubMed 文献 · J Ultrasound Med · 2025-10-01

研究提出射频时间序列动态处理(RFTSDP)方法,研制振动发生装置并在11例离体乳腺组织样本上采集超快超声数据,利用深度学习自动提取特征并对乳腺病灶进行2类、3类和5类分类。在65 Hz振动下,基于卷积神经网络的RFTSDP方法分类与分级准确率达99.53±0.47%,5类分类中CNN准确率98.01% vs SVM 95.64%(P<.05),且较无振动及聚焦原始数据分析条件分类准确率提高28.67%。

要点

  • 在65 Hz振动刺激下,基于CNN的RFTSDP方法对乳腺病灶分类与分级准确率达99.53±0.47%。
  • 5类分类中CNN准确率98.01% vs SVM 95.64%,差异有统计学意义(P<.05)。
  • CNN-based RFTSDP较无振动及聚焦原始数据分析条件分类准确率提高28.67%。

核心结论

  • 基于深度学习的RFTSDP计算机辅助诊断系统能够对乳腺病灶进行分类与分级,且与传统方法相比在振动刺激下表现出更高的稳定性和鲁棒性。

研究设计与样本

  • 研究在11例离体乳腺组织样本上,使用研制的振动发生装置在不同刺激条件下采集超快超声数据,采用深度学习进行自动特征提取和病灶分类(2类、3类、5类),并与基于射频时间序列频谱及非线性特征提取联合支持向量机的传统机器学习方法进行比较。

诊断标准与关键数值

  • 在65 Hz振动条件下,基于CNN的RFTSDP方法分类与分级乳腺病灶的准确率为99.53±0.47%;5类分类中CNN准确率为98.01%,SVM为95.64%,差异有统计学意义(P<.05);CNN-based RFTSDP较无振动及聚焦原始数据分析条件分类准确率提高28.67%。

局限性

  • 研究基于11例离体乳腺组织样本,样本量小。
  • 研究为离体组织实验,结论需进一步在体研究验证。

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: Accurate detection of breast lesion type is crucial for optimizing treatment; however, due to the limited precision of current diagnostic methods, biopsies are often required. To address this limitation, we proposed radio frequency time series dynamic processing (RFTSDP) in 2020, which analyzes the dynamic response of tissue and the impact of scatterer displacement on RF echoes during controlled stimulations to enhance diagnostic information.

METHODS: We developed a vibration-generating device and collected ultrafast ultrasound data from 11 ex vivo breast tissue samples under different stimulations. Deep learning (DL) was used for automated feature extraction and lesion classification into 2, 3, and 5 categories. The performance of the convolutional neural network (CNN)-based RFTSDP method was compared with traditional machine learning techniques, which involved spectral and nonlinear feature extraction from RF time series, followed by a support vector machine (SVM).

RESULTS: With 65 Hz vibration, the DL-based RFTSDP method achieved 99.53 ± 0.47% accuracy in classifying and grading breast lesions. CNN consistently outperformed SVM, particularly under vibratory stimulation. In 5-class classification, CNN reached 98.01% versus 95.64% for SVM, with the difference being statistically significant (P < .05). Furthermore, the CNN-based RFTSDP method showed a 28.67% improvement in classification accuracy compared to the non-stimulation condition and the analysis of focused raw data.

CONCLUSIONS: We developed a DL-based CAD system capable of classifying and grading breast lesions. This study demonstrates that the proposed system not only enhances classification but also ensures increased stability and robustness compared to traditional methods.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Ghehi EN, Fallah A, Rashidi S, et al. Deep Learning-Based CAD System for Enhanced Breast Lesion Classification and Grading Using RFTSDP Approach. J Ultrasound Med. 2025. PMID: 41035163. doi:10.1002/jum.70056

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。