文献速递乳腺乳腺X线

深度学习鉴别可疑微钙化:导管原位癌与浸润性导管癌

Differentiation of Suspicious Microcalcifications Using Deep Learning: DCIS or IDC.
PubMed 文献 · Acad Radiol · 2025-08-20

本研究回顾性纳入两中心294例乳腺钼靶表现为可疑微钙化的乳腺癌病例(106例导管原位癌、188例浸润性导管癌),构建临床模型、深度学习模型及联合模型。外部验证集中深度学习模型与联合模型鉴别导管原位癌与浸润性导管癌的AUC均为0.97,均优于临床模型(AUC 0.67,p<0.05),而深度学习模型与联合模型诊断效能相当(p>0.05)。

要点

  • 深度学习模型鉴别表现为可疑微钙化的导管原位癌与浸润性导管癌,外部验证AUC 0.97、敏感度0.94、特异度0.92、准确率0.93。
  • 联合模型(深度学习特征+临床变量)外部验证AUC 0.97、敏感度0.96、特异度0.92、准确率0.95,与深度学习模型效能相当(p>0.05)。
  • 临床模型仅纳入病变类型与BI-RADS分类,外部验证AUC 0.67、敏感度0.53、特异度0.81、准确率0.63,效能低于两个深度学习相关模型(p<0.05)。

核心结论

  • 深度学习为钼靶上表现为可疑微钙化的导管原位癌与浸润性导管癌的鉴别提供了一种有效的无创方法。

研究设计与样本

  • 回顾性研究,纳入两中心294例乳腺癌病例(106例导管原位癌、188例浸润性导管癌),随机分为训练集、内部验证集和外部验证集;使用Resnet101提取深度学习特征,经mRMR和LASSO筛选后建模,并以受试者工作特征曲线下面积(AUC)评估模型性能。

诊断标准与关键数值

  • 外部验证集中,临床模型(基于多因素分析确定的病变类型和BI-RADS分类)AUC 0.67、敏感度0.53、特异度0.81、准确率0.63;深度学习模型AUC 0.97、敏感度0.94、特异度0.92、准确率0.93;联合模型AUC 0.97、敏感度0.96、特异度0.92、准确率0.95。

临床应用与阅片要点

  • 原文结论认为深度学习为鉴别钼靶上表现为可疑微钙化的导管原位癌与浸润性导管癌提供了有效的无创方法;深度学习模型与联合模型诊断效能相当(p>0.05),且均优于临床模型(p<0.05)。

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 explore the value of a deep learning-based model in distinguishing between ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) manifesting suspicious microcalcifications on mammography.

MATERIALS: A total of 294 breast cancer cases (106 DCIS and 188 IDC) from two centers were randomly allocated into training, internal validation and external validation sets in this retrospective study. Clinical variables differentiating DCIS from IDC were identified through univariate and multivariate analyses and used to build a clinical model. Deep learning features were extracted using Resnet101 and selected by minimum redundancy maximum correlation (mRMR) and least absolute shrinkage and selection operator (LASSO). A deep learning model was developed using deep learning features, and a combined model was constructed by combining these features with clinical variables. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of each model.

RESULTS: Multivariate logistic regression identified lesion type and BI-RADS category as independent predictors for differentiating DCIS from IDC. The clinical model incorporating these factors achieved an AUC of 0.67, sensitivity of 0.53, specificity of 0.81, and accuracy of 0.63 in the external validation set. In comparison, the deep learning model showed an AUC of 0.97, sensitivity of 0.94 and specificity of 0.92, accuracy of 0.93. For the combined model, the AUC, sensitivity, specificity and accuracy were 0.97, 0.96, 0.92 and 0.95, respectively. The diagnostic efficacy of the deep learning model and combined model was comparable (p>0.05), and both models outperformed the clinical model (p<0.05).

CONCLUSION: Deep learning provides an effective non-invasive approach to differentiate DCIS from IDC presenting as suspicious microcalcifications on mammography.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Xu W, Deng S, Mao G, et al. Differentiation of Suspicious Microcalcifications Using Deep Learning: DCIS or IDC. Acad Radiol. 2025. PMID: 40835571. doi:10.1016/j.acra.2025.07.062

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。