Background

Supplemental screening with MRI has proved beneficial in women with extremely dense breasts. Most MRI examinations show normal anatomic and physiologic variation that may not require radiologic review. Thus, ways to triage these normal MRI examinations to reduce radiologist workload are needed.

Purpose

To determine the feasibility of an automated triaging method using deep learning (DL) to dismiss the highest number of MRI examinations without lesions while still identifying malignant disease.

Materials and Methods

This secondary analysis of data from the Dense Tissue and Early Breast Neoplasm Screening, or DENSE, trial evaluated breast MRI examinations from the first screening round performed in eight hospitals between December 2011 and January 2016. A DL model was developed to differentiate between breasts with lesions and breasts without lesions. The model was trained to dismiss breasts with normal phenotypical variation and to triage lesions (Breast Imaging Reporting and Data System [BI-RADS] categories 2–5) using eightfold internal-external validation. The model was trained on data from seven hospitals and tested on data from the eighth hospital, alternating such that each hospital was used once as an external test set. Performance was assessed using receiver operating characteristic analysis. At 100% sensitivity for malignant disease, the fraction of examinations dismissed from radiologic review was estimated.

Results

A total of 4581 MRI examinations of extremely dense breasts from 4581women (mean age, 54.3 years; interquartile range, 51.5–59.8 years) were included. Of the 9162 breasts, 838 had at least one lesion (BI-RADS category 2–5, of which 77 were malignant) and 8324 had no lesions. At 100% sensitivity for malignant lesions, the DL model considered 90.7% (95% CI: 86.7, 94.7) of the MRI examinations with lesions to be nonnormal and triaged them to radiologic review. The DL model dismissed 39.7% (95% CI: 30.0, 49.4) of the MRI examinations without lesions. The DL model had an average area under the receiver operating characteristic curve of 0.83 (95% CI: 0.80, 0.85) in the differentiation between normal breast MRI examinations and MRI examinations with lesions.

Conclusion

Automated analysis of breast MRI examinations in women with dense breasts dismissed nearly 40% of MRI scans without lesions while not missing any cancers.

ClinicalTrials.gov: NCT01315015

© RSNA, 2021

Online supplemental material is available for this article.

See also the editorial by Joe in this issue.

中文翻译：

---

深度学习用于 DENSE 试验中 4581 次乳房 MRI 检查的自动分类

背景

事实证明，使用 MRI 进行的补充筛查对乳房非常致密的女性有益。大多数 MRI 检查显示正常的解剖和生理变化，可能不需要放射学检查。因此，需要对这些正常 MRI 检查进行分类以减少放射科医生工作量的方法。

目的

确定使用深度学习 (DL) 的自动分类方法的可行性，以消除最多数量的没有病变的 MRI 检查，同时仍能识别恶性疾病。

材料和方法

对致密组织和早期乳腺肿瘤筛查 (DENSE) 试验数据的二次分析评估了 2011 年 12 月至 2016 年 1 月期间在八家医院进行的第一轮筛查的乳腺 MRI 检查。开发了一个 DL 模型来区分有病变的乳房和没有病变的乳房。该模型经过训练，可以剔除具有正常表型变异的乳房，并使用八倍内外验证对病变进行分类（乳房成像报告和数据系统 [BI-RADS] 类别 2-5）。该模型使用来自七家医院的数据进行训练，并根据来自第八家医院的数据进行测试，交替使用每家医院作为外部测试集。使用接收器操作特征分析评估性能。对恶性疾病的敏感性为 100%，

结果

共纳入了 4581 名女性（平均年龄 54.3 岁；四分位间距 51.5-59.8 岁）的 4581 次极致密乳房 MRI 检查。在 9162 个乳房中，838 个有至少一个病变（BI-RADS 2-5 类，其中 77 个是恶性的），8324 个没有病变。在对恶性病变的敏感性为 100% 时，DL 模型认为 90.7% (95% CI: 86.7, 94.7) 的 MRI 检查有病变是不正常的，并将它们分类为放射学检查。DL 模型忽略了 39.7% (95% CI: 30.0, 49.4) 的 MRI 检查而没有病变。DL模型在区分正常乳腺MRI检查和有病变的MRI检查时，平均受试者工作特征曲线下面积为0.83（95% CI：0.80，0.85）。

结论

对乳房致密的女性进行的乳房 MRI 检查的自动分析排除了近 40% 的没有病变的 MRI 扫描，同时也没有漏掉任何癌症。

ClinicalTrials.gov：NCT01315015

© 北美放射学会，2021

本文提供在线补充材料。

另请参阅本期 Joe 的社论。