Deep Learning to Improve Breast Cancer Detection on Screening Mammography
Deep Learning to Improve Breast Cancer Detection on Screening Mammography
复制标题
DOI：
10.1038/s41598-019-48995-4
复制
发表时间：
2019-08-29
影响因子：
4.6
通讯作者：
Sieh, Weiva
中科院分区：
文献类型：
--
作者：
Shen, Li;Margolies, Laurie R.;Sieh, Weiva
深度学习这一机器学习技术家族的迅速发展，引起了人们对其在医学成像问题中的应用的极大兴趣。在这里，我们开发了一种深度学习算法，它可以在筛查乳房X光照片时准确地检测出乳腺癌，该算法使用一种端到端的训练方法，该方法有效地利用了具有完整临床注释或仅具有整个图像的癌症状态(标签)的训练数据集。在这种方法中，只有在最初的训练阶段需要病变注释，而后续阶段只需要图像级别的标签，从而消除了对很少可用的病变注释的依赖。与以前的方法相比，我们的全卷积网络方法在筛选乳房X线片分类中取得了优异的性能。在数字化乳腺摄影数据库(CBIS-DDSM)的独立测试集上，最好的单一模型每幅图像的AUC为0.88，四个模型的平均AUC提高到0.91(敏感性：86.1%，特异性：80.1%)。在来自INBAME数据库的一组独立的全场数字乳房X光摄影(FFDM)图像上，最好的单一模型每幅图像的AUC为0.95，四个模型的平均AUC提高到0.98(敏感性：86.7%，特异性：96.1%)。我们还展示了在CBIS-DDSM数字化胶片乳房X光照片上使用我们的端到端方法训练的整个图像分类器可以仅使用乳房内数据的子集来进行微调，而不需要进一步依赖病变注释的可用性，就可以将其传输到INBAME FFDM图像。这些发现表明，自动深度学习方法可以很容易地训练，以在不同的乳房X光检查平台上获得高精度，并为改进临床工具以减少假阳性和假阴性筛查乳房X光检查结果带来巨大希望。代码和型号请访问：https://github.com/lishen/end2end-all-conv.
The rapid development of deep learning, a family of machine learning techniques, has spurred much interest in its application to medical imaging problems. Here, we develop a deep learning algorithm that can accurately detect breast cancer on screening mammograms using an "end-to-end" training approach that efficiently leverages training datasets with either complete clinical annotation or only the cancer status (label) of the whole image. In this approach, lesion annotations are required only in the initial training stage, and subsequent stages require only image-level labels, eliminating the reliance on rarely available lesion annotations. Our all convolutional network method for classifying screening mammograms attained excellent performance in comparison with previous methods. On an independent test set of digitized film mammograms from the Digital Database for Screening Mammography (CBIS-DDSM), the best single model achieved a per-image AUC of 0.88, and four-model averaging improved the AUC to 0.91 (sensitivity: 86.1%, specificity: 80.1%). On an independent test set of full-field digital mammography (FFDM) images from the INbreast database, the best single model achieved a per-image AUC of 0.95, and four-model averaging improved the AUC to 0.98 (sensitivity: 86.7%, specificity: 96.1%). We also demonstrate that a whole image classifier trained using our end-to-end approach on the CBIS-DDSM digitized film mammograms can be transferred to INbreast FFDM images using only a subset of the INbreast data for fine-tuning and without further reliance on the availability of lesion annotations. These findings show that automatic deep learning methods can be readily trained to attain high accuracy on heterogeneous mammography platforms, and hold tremendous promise for improving clinical tools to reduce false positive and false negative screening mammography results. Code and model available at: https://github.com/lishen/end2end-all-conv.