文献速递乳腺乳腺X线

卷积神经网络迁移学习用于计算机辅助诊断:数字乳腺断层合成与全视野数字乳腺X线的比较

Transfer Learning From Convolutional Neural Networks for Computer-Aided Diagnosis: A Comparison of Digital Breast Tomosynthesis and Full-Field Digital Mammography.
PubMed 文献 · Acad Radiol · 2018-08-01

本研究回顾性收集76例患者78个活检证实病灶的FFDM与DBT图像,用预训练卷积神经网络提取特征并经支持向量机分类预测恶性可能性。合并头尾位与内外斜位数据后,DBT关键层图像AUC最高(0.89,SE=0.04);仅分析肿块与结构扭曲时,DBT显著优于FFDM(p=0.024)。

要点

  • 合并双体位后DBT关键层图像AUC达0.89(SE=0.04),为各图像类型中最高。
  • 仅针对肿块与结构扭曲病灶,DBT分类性能显著优于FFDM(p=0.024)。
  • 合成2D图像在头尾位(AUC=0.81,SE=0.05)与内外斜位(AUC=0.88,SE=0.04)单体位分析中表现最佳。

核心结论

  • 在肿块与结构扭曲病灶的合并体位分类中,DBT显著优于FFDM,提示CNN从DBT图像提取的信息可能与病灶恶性状态更相关,为DBT计算机辅助诊断在此类病灶评估中的效能提供支持证据。

研究设计与样本

  • 回顾性研究,收集76例患者78个活检证实病灶的FFDM与DBT图像;对FFDM、合成2D及DBT关键层图像勾画感兴趣区,用预训练卷积神经网络提取特征,输入支持向量机分类器预测恶性可能性,并以ROC分析评估。

诊断标准与关键数值

  • 全部78个病灶的ROC分析:合成2D图像头尾位AUC=0.81(SE=0.05),内外斜位AUC=0.88(SE=0.04),为单体位中最佳。
  • 每例头尾位与内外斜位数据经软投票合并后,DBT关键层图像AUC=0.89(SE=0.04),为合并分析中最佳。
  • 仅纳入肿块与结构扭曲(ARDs)病灶时,DBT显著优于FFDM(p=0.024)。

局限性

  • 本研究为回顾性收集FFDM与DBT图像,样本为76例患者78个活检证实病灶。

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: With the growing adoption of digital breast tomosynthesis (DBT) in breast cancer screening, we compare the performance of deep learning computer-aided diagnosis on DBT images to that of conventional full-field digital mammography (FFDM).

MATERIALS AND METHODS: In this study, we retrospectively collected FFDM and DBT images of 78 biopsy-proven lesions from 76 patients. A region of interest was selected for each lesion on FFDM, synthesized 2D, and DBT key slice images. Features were extracted from each lesion using a pretrained convolutional neural network (CNN) and served as input to a support vector machine classifier trained in the task of predicting likelihood of malignancy.

RESULTS: From receiver operating characteristic (ROC) analysis of all 78 lesions, the synthesized 2D image performed best in both the cradiocaudal view (area under the ROC curve [AUC] = 0.81, SE = 0.05) and mediolateral oblique view (AUC = 0.88, SE = 0.04) in the task of lesion characterization. When cradiocaudal and mediolateral oblique data of each lesion were merged through soft voting, DBT key slice image performed best (AUC = 0.89, SE = 0.04). When only masses and architectural distortions (ARDs) were considered, DBT performed significantly better than FFDM (p = 0.024).

CONCLUSION: DBT performed significantly better than FFDM in the merged view classification of mass and ARD lesions. The increased performance suggests that the information extracted by the CNN from DBT images may be more relevant to lesion malignancy status than the information extracted from FFDM images. Therefore, this study provides supporting evidence for the efficacy of computer-aided diagnosis on DBT in the evaluation of mass and ARD lesions.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Mendel K, Li H, Sheth D, et al. Transfer Learning From Convolutional Neural Networks for Computer-Aided Diagnosis: A Comparison of Digital Breast Tomosynthesis and Full-Field Digital Mammography. Acad Radiol. 2018. PMID: 30076083. doi:10.1016/j.acra.2018.06.019

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。