文献速递乳腺甲状腺与浅表US

基于超声RF信号的多模态多任务模型评估乳腺肿块与腋窝淋巴结

A Multimodal Multitask Deep Learning Model Based on Ultrasound RF Signals for Joint Assessment of Breast Masses and Axillary Lymph Nodes Status.
PubMed 文献 · Ultrasound Med Biol · 2026-07-11

本研究纳入308例乳腺病变患者,利用B模式与射频信号构建多模态多任务深度学习模型,同时判断乳腺肿块良恶性与腋窝淋巴结状态。B+RF联合多任务损失建模效果最优,肿块预测AUC为0.967,淋巴结状态预测AUC为0.922。CAM热图辅助超声医师后相应AUC分别为0.901与0.874。

要点

  • B模式联合RF信号的多任务模型对乳腺肿块及腋窝淋巴结状态均有较高预测效能。
  • CAM热图中淋巴结转移患者红色区域集中于肿块边缘,无转移者以肿块内部为主。
  • 动物实验提示CAM热图红色区域中性粒细胞阳性面积高于蓝色区域。

核心结论

  • 基于B模式与RF信号的多模态多任务深度学习模型可辅助评估乳腺肿块及腋窝淋巴结状态。
  • 淋巴结转移患者CAM热图红色区域倾向位于肿块边缘,无转移者倾向位于肿块中心(p<0.001)。
  • 动物实验显示CAM红色区域中性粒细胞阳性面积大于蓝色区域,转移组红色区域中性粒细胞阳性面积大于非转移组。

研究设计与样本

  • 研究类型为深度学习模型开发与验证,训练集246例、验证集62例,共308例。
  • 以ResNet-18为特征提取网络,采用多任务损失函数设计乳腺肿块分类与腋窝淋巴结状态评估模型。
  • 动物实验使用小鼠移植瘤CAM热图,分析不同热图颜色区域的中性粒细胞分布差异。

关键影像表现/征象

  • 淋巴结转移患者CAM热图红色部分集中于肿块边缘,无转移患者红色部分集中于肿块内部(p<0.001)。
  • 动物实验中转移组与非转移组红色区域中性粒细胞阳性面积均大于蓝色区域。
  • 转移组红色区域中性粒细胞阳性面积大于非转移组红色区域。

诊断标准与关键数值

  • B+RF模式结合多任务损失为最优建模组合。
  • DLMMRF模型预测乳腺肿块AUC为0.967,预测淋巴结状态AUC为0.922,预测患者总体状态AUC为0.944。
  • 超声医师结合CAM辅助时预测乳腺肿块AUC为0.901,预测淋巴结状态AUC为0.874,预测总体状态AUC为0.887。
  • 原文报告了敏感度、特异度、准确率及ROC曲线分析,但摘要中未列出具体数值。

临床应用与阅片要点

  • CAM热图红色区域分布位置可作为判断腋窝淋巴结转移风险的视觉参考,转移风险高时红色区域多位于肿块边缘。
  • 该模型可同时输出乳腺肿块分类与腋窝淋巴结状态评估,有助于超声医师快速判断患者整体状态。

局限性

  • 本研究为单中心数据,样本量308例,训练集与验证集比例固定。
  • 纳入对象均为乳腺癌患者,缺乏非恶性病变及正常对照的独立验证描述。

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

PURPOSE: Developing a deep learning model to simultaneously evaluate lymph node status and distinguish between benign and malignant breast masses has been a challenging clinical task. This study aimed to use radio frequency (RF) signal data to create a deep learning, multimodal multitasking model, incorporating Class Activation Mapping (CAM) heatmaps to assist ultrasonographers in assessing the overall patient state based on their expertise. Research has shown a correlation between lymph node metastases and the heterogeneity of neutrophil distribution in malignancies. Therefore, the study also aimed to analyze the correlation between CAM heatmaps and neutrophil distribution, exploring the physiological mechanisms underlying the model.

METHODS: A total of 308 eligible breast cancer patients with B-mode data, RF data and ultrasound reports were selected as the training set (n = 246) and validation set (n = 62) at the Second Affiliated Hospital of Harbin Medical University from September 2018 to October 2019. Using ResNet-18 as a feature extraction network, a multi-task loss (MTL) function to design a model for breast mass classification and axillary lymph node status assessment. The model's CAM heatmaps were analyzed and integrated with the sonographer's expertise to evaluate the patient's condition. Sensitivity, specificity, accuracy and receiver operating characteristic (ROC) curve analyses were calculated. In the animal experiment, CAM heatmaps from mouse transplanted tumors were analyzed, and differences in neutrophil distribution at different heatmap color locations were examined.

RESULTS: The B + RF mode data with MTL was the optimal combination for modeling. The area under the ROC curve (AUC) for the DLMMRF analysis of breast mass prediction was 0.967, for lymph node status prediction was 0.922 and for patient overall status prediction was 0.944. In CAM heatmaps, the red portion for patients with lymph node metastases focused on mass margins, while for those without metastases, it centered on the mass (p < 0.001). The AUC for sonographers with CAM assistance in breast mass prediction was 0.901, for lymph node status prediction was 0.874 and for patient overall status prediction was 0.887. Animal experiments showed that heatmap patterns correlated with neutrophil distribution in tumors, with a larger neutrophil-positive area in the red section than in the blue section in both metastatic and non-metastatic groups, and a greater neutrophil-positive area in the metastatic group's red section compared to the non-metastatic group.

CONCLUSION: This study developed a multimodal multitasking deep learning model using RF data to generate CAM heatmaps, assisting ultrasonographers in assessing patient status, especially lymph nodes. The CAM heatmaps' red regions displayed higher neutrophil concentrations than the blue areas, with the metastatic group showing more neutrophils in the red regions compared to the non-metastatic group, suggesting a possible association between neutrophil infiltration and the model's attention regions.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Liang, Zhang, Xu, et al. A Multimodal Multitask Deep Learning Model Based on Ultrasound RF Signals for Joint Assessment of Breast Masses and Axillary Lymph Nodes Status. Ultrasound Med Biol. 2026. PMID: 42431776. doi:10.1016/j.ultrasmedbio.2026.05.021

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。