Mammographic Breast Density Assessment Using Deep Learning: Clinical Implementation
Mammographic Breast Density Assessment Using Deep Learning: Clinical Implementation
复制标题
DOI：
10.1148/radiol.2018180694
复制
发表时间：
2019-01-01
期刊：
影响因子：
19.7
通讯作者：
Barzilay, Regina
中科院分区：
文献类型：
--
作者：
Lehman, Constance D.;Yala, Adam;Barzilay, Regina
目的：开发一种深度学习 (DL) 算法来评估乳房 X 光检查乳腺密度。材料和方法：在这项回顾性研究中，根据经验丰富的放射科医生对 2009 年 1 月至 2011 年 5 月期间 27 684 名女性获得的 41 479 幅数字筛查乳房 X 光照片的原始解释，训练深度卷积神经网络来评估乳腺成像报告和数据系统 (BI-RADS) 乳腺密度。对 5741 名女性进行了 8677 次乳房 X 光检查。此外，五名放射科医生对从测试集中随机选择的 500 张乳房 X 光照片进行了读者研究。最后，该算法在常规临床实践中得到实施，八位放射科医生审查了使用该模型评估的 10 763 个连续乳房 X 光检查。 DL 模型和三组读数的 BI-RADS 类别一致 - (a) 测试集中的放射科医生，(b) 在读者研究集中一致工作的放射科医生，以及 (c) 临床实施集中的放射科医生 - 使用线性加权 k 统计量进行估计，并在 5000 个 bootstrap 样本之间进行比较以评估显着性。 结果：DL 模型与测试集中的放射科医生表现出良好的一致性（kappa = 0.67； 95% 置信区间 [CI]: 0.66, 0.68) 并与放射科医生在读者研究集中达成共识 (kappa = 0.78; 95% CI: 0.73, 0.82)。与临床实施组中的放射科医生的一致性非常好（kappa = 0.85；95% CI：0.84，0.86）；对于致密或非致密乳房的二元分类，10 763 例中的 10 149 例 (94%; 95% CI: 94%, 95%) DL 评估被解读放射科医师接受。 结论：该 DL 模型可用于评估经验丰富的乳房 X 线照相技师水平的乳房 X 线照相乳房密度。 (c) 北美放射学会，2018
Purpose: To develop a deep learning (DL) algorithm to assess mammographic breast density.Materials and Methods: In this retrospective study, a deep convolutional neural network was trained to assess Breast Imaging Reporting and Data System (BI-RADS) breast density based on the original interpretation by an experienced radiologist of 41 479 digital screening mammograms obtained in 27 684 women from January 2009 to May 2011. The resulting algorithm was tested on a held-out test set of 8677 mammograms in 5741 women. In addition, five radiologists performed a reader study on 500 mammograms randomly selected from the test set. Finally, the algorithm was implemented in routine clinical practice, where eight radiologists reviewed 10 763 consecutive mammograms assessed with the model. Agreement on BI-RADS category for the DL model and for three sets of readings-(a) radiologists in the test set, (b) radiologists working in consensus in the reader study set, and (c) radiologists in the clinical implementation set-were estimated with linear-weighted k statistics and were compared across 5000 bootstrap samples to assess significance.Results: The DL model showed good agreement with radiologists in the test set (kappa = 0.67; 95% confidence interval [CI]: 0.66, 0.68) and with radiologists in consensus in the reader study set (kappa = 0.78; 95% CI: 0.73, 0.82). There was very good agreement (kappa = 0.85; 95% CI: 0.84, 0.86) with radiologists in the clinical implementation set; for binary categorization of dense or nondense breasts, 10 149 of 10 763 (94%; 95% CI: 94%, 95%) DL assessments were accepted by the interpreting radiologist.Conclusion: This DL model can be used to assess mammographic breast density at the level of an experienced mammographer. (c) RSNA, 2018