文献速递乳腺乳腺X线

基于乳腺X线摄影的多任务深度学习预测浸润性乳腺癌广泛导管内成分

Multitask deep learning on mammography to predict extensive intraductal component in invasive breast cancer.
PubMed 文献 · Eur Radiol · 2023-10-09

该研究纳入2010至2019年1459例浸润性乳腺癌的3076张乳腺X线图像,构建多任务深度学习模型同时分类影像表现并预测广泛导管内成分(EIC)。三任务模型预测EIC的AUC在图像水平和乳腺水平分别为0.758和0.775,肿块分类AUC为0.915,多任务方法较单任务模型训练有所改善但无显著差异。

要点

  • 多任务深度学习模型可在乳腺X线上同时分类影像表现并预测EIC,三任务模型EIC预测AUC图像水平0.758、乳腺水平0.775。
  • 肿块是分类最准确的影像表现(AUC=0.915),钙化及肿块伴钙化AUC分别为0.878和0.824,细胞受体状态预测准确性较低(AUC=0.625-0.653)。
  • 多任务方法较单任务模型改善模型训练,但无显著效应。

核心结论

  • 基于乳腺X线的多任务深度学习模型可同时进行影像表现分类和EIC预测,展现出从乳腺X线中提取更多信息用于临床决策的潜力。

研究设计与样本

  • 研究纳入2010至2019年浸润性乳腺癌乳腺X线图像,由两名放射科医师进行图像分割和影像表现标注,图像随机分为训练集、验证集和测试集。在EfficientNet-B0神经网络上采用多任务方法主要预测EIC并分类影像表现,另训练单任务模型(预测EIC)、两任务模型(预测EIC和细胞受体状态)和三任务模型(结合上述任务)进行比较,并在浸润性导管癌亚组中训练这些模型,采用DeLong检验比较模型性能差异。

诊断标准与关键数值

  • 共纳入1459例乳腺癌的3076张图像,EIC阳性率为29.0%;三任务模型为最佳深度学习模型,EIC预测AUC在图像水平为0.758、在乳腺(患者)水平为0.775;肿块分类AUC=0.915,钙化AUC=0.878,肿块伴钙化AUC=0.824;细胞受体状态预测AUC=0.625-0.653。

临床应用与阅片要点

  • 多任务深度学习模型可同时分类乳腺X线影像表现并预测EIC,EIC预测性能接近放射科医师阅片;肿块分类准确性最高,细胞受体状态预测准确性较低。

局限性

  • 多任务方法较单任务模型改善模型训练,但无显著效应。

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 a multitask deep learning (DL) algorithm to automatically classify mammography imaging findings and predict the existence of extensive intraductal component (EIC) in invasive breast cancer.

METHODS: Mammograms with invasive breast cancers from 2010 to 2019 were downloaded for two radiologists performing image segmentation and imaging findings annotation. Images were randomly split into training, validation, and test datasets. A multitask approach was performed on the EfficientNet-B0 neural network mainly to predict EIC and classify imaging findings. Three more models were trained for comparison, including a single-task model (predicting EIC), a two-task model (predicting EIC and cell receptor status), and a three-task model (combining the abovementioned tasks). Additionally, these models were trained in a subgroup of invasive ductal carcinoma. The DeLong test was used to examine the difference in model performance.

RESULTS: This study enrolled 1459 breast cancers on 3076 images. The EIC-positive rate was 29.0%. The three-task model was the best DL model with an area under the curve (AUC) of EIC prediction of 0.758 and 0.775 at the image and breast (patient) levels, respectively. Mass was the most accurately classified imaging finding (AUC = 0.915), followed by calcifications and mass with calcifications (AUC = 0.878 and 0.824, respectively). Cell receptor status prediction was less accurate (AUC = 0.625-0.653). The multitask approach improves the model training compared to the single-task model, but without significant effects.

CONCLUSIONS: A mammography-based multitask DL model can perform simultaneous imaging finding classification and EIC prediction.

CLINICAL RELEVANCE STATEMENT: The study results demonstrated the potential of deep learning to extract more information from mammography for clinical decision-making.

KEY POINTS: • Extensive intraductal component (EIC) is an independent risk factor of local tumor recurrence after breast-conserving surgery. • A mammography-based deep learning model was trained to predict extensive intraductal component close to radiologists' reading. • The developed multitask deep learning model could perform simultaneous imaging finding classification and extensive intraductal component prediction.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Tsai HY, Kao YW, Wang JC, et al. Multitask deep learning on mammography to predict extensive intraductal component in invasive breast cancer. Eur Radiol. 2023. PMID: 37812297. doi:10.1007/s00330-023-10254-6

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。